{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.09628345850182939, "eval_steps": 500, "global_step": 500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "grad_norm": 20.216445284675434, "learning_rate": 1.282051282051282e-07, "loss": 1.9775, "step": 1 }, { "epoch": 0.0, "grad_norm": 23.911595589639173, "learning_rate": 2.564102564102564e-07, "loss": 2.1666, "step": 2 }, { "epoch": 0.0, "grad_norm": 23.589768673301773, "learning_rate": 3.846153846153847e-07, "loss": 1.9854, "step": 3 }, { "epoch": 0.0, "grad_norm": 24.568648529053654, "learning_rate": 5.128205128205128e-07, "loss": 2.2656, "step": 4 }, { "epoch": 0.0, "grad_norm": 24.549288858256404, "learning_rate": 6.41025641025641e-07, "loss": 1.9927, "step": 5 }, { "epoch": 0.0, "grad_norm": 23.110487979033767, "learning_rate": 7.692307692307694e-07, "loss": 2.1646, "step": 6 }, { "epoch": 0.0, "grad_norm": 21.9015150661795, "learning_rate": 8.974358974358975e-07, "loss": 2.129, "step": 7 }, { "epoch": 0.0, "grad_norm": 19.501364965637194, "learning_rate": 1.0256410256410257e-06, "loss": 1.9416, "step": 8 }, { "epoch": 0.0, "grad_norm": 17.453575658521874, "learning_rate": 1.153846153846154e-06, "loss": 1.9497, "step": 9 }, { "epoch": 0.0, "grad_norm": 15.607773385934923, "learning_rate": 1.282051282051282e-06, "loss": 2.0166, "step": 10 }, { "epoch": 0.0, "grad_norm": 13.464353749675528, "learning_rate": 1.4102564102564104e-06, "loss": 1.8781, "step": 11 }, { "epoch": 0.0, "grad_norm": 13.97360564518581, "learning_rate": 1.5384615384615387e-06, "loss": 1.9095, "step": 12 }, { "epoch": 0.0, "grad_norm": 10.992113441163921, "learning_rate": 1.6666666666666667e-06, "loss": 1.6395, "step": 13 }, { "epoch": 0.0, "grad_norm": 11.552028290409154, "learning_rate": 1.794871794871795e-06, "loss": 1.5434, "step": 14 }, { "epoch": 0.0, "grad_norm": 8.311907698101182, "learning_rate": 1.9230769230769234e-06, "loss": 1.5281, "step": 15 }, { "epoch": 0.0, "grad_norm": 6.678981025513341, "learning_rate": 2.0512820512820513e-06, "loss": 1.4648, "step": 16 }, { "epoch": 0.0, "grad_norm": 1.0588935799454995, "learning_rate": 2.1794871794871797e-06, "loss": 0.7232, "step": 17 }, { "epoch": 0.0, "grad_norm": 4.903466856108649, "learning_rate": 2.307692307692308e-06, "loss": 1.2737, "step": 18 }, { "epoch": 0.0, "grad_norm": 4.685212001248653, "learning_rate": 2.435897435897436e-06, "loss": 1.3402, "step": 19 }, { "epoch": 0.0, "grad_norm": 4.245435062932411, "learning_rate": 2.564102564102564e-06, "loss": 1.3337, "step": 20 }, { "epoch": 0.0, "grad_norm": 4.158382292780615, "learning_rate": 2.6923076923076923e-06, "loss": 1.3811, "step": 21 }, { "epoch": 0.0, "grad_norm": 4.186622696017208, "learning_rate": 2.8205128205128207e-06, "loss": 1.2546, "step": 22 }, { "epoch": 0.0, "grad_norm": 3.517891507093355, "learning_rate": 2.948717948717949e-06, "loss": 1.18, "step": 23 }, { "epoch": 0.0, "grad_norm": 3.1001253598950638, "learning_rate": 3.0769230769230774e-06, "loss": 1.3383, "step": 24 }, { "epoch": 0.0, "grad_norm": 1.2465679665413227, "learning_rate": 3.205128205128206e-06, "loss": 0.832, "step": 25 }, { "epoch": 0.01, "grad_norm": 3.0120421636293195, "learning_rate": 3.3333333333333333e-06, "loss": 1.3458, "step": 26 }, { "epoch": 0.01, "grad_norm": 1.4484948949766845, "learning_rate": 3.4615384615384617e-06, "loss": 0.8444, "step": 27 }, { "epoch": 0.01, "grad_norm": 3.1110997732647743, "learning_rate": 3.58974358974359e-06, "loss": 1.2984, "step": 28 }, { "epoch": 0.01, "grad_norm": 2.755277848262445, "learning_rate": 3.7179487179487184e-06, "loss": 1.2309, "step": 29 }, { "epoch": 0.01, "grad_norm": 2.860582982001812, "learning_rate": 3.846153846153847e-06, "loss": 1.2708, "step": 30 }, { "epoch": 0.01, "grad_norm": 2.5897985578473377, "learning_rate": 3.974358974358974e-06, "loss": 1.2035, "step": 31 }, { "epoch": 0.01, "grad_norm": 2.5495914062962792, "learning_rate": 4.102564102564103e-06, "loss": 1.1789, "step": 32 }, { "epoch": 0.01, "grad_norm": 2.389696878446986, "learning_rate": 4.230769230769231e-06, "loss": 1.2519, "step": 33 }, { "epoch": 0.01, "grad_norm": 2.076541587027184, "learning_rate": 4.358974358974359e-06, "loss": 1.1727, "step": 34 }, { "epoch": 0.01, "grad_norm": 1.6797871781763094, "learning_rate": 4.487179487179488e-06, "loss": 0.792, "step": 35 }, { "epoch": 0.01, "grad_norm": 2.1243426876134257, "learning_rate": 4.615384615384616e-06, "loss": 1.1818, "step": 36 }, { "epoch": 0.01, "grad_norm": 2.299174657545576, "learning_rate": 4.743589743589744e-06, "loss": 1.2307, "step": 37 }, { "epoch": 0.01, "grad_norm": 2.0371458205650415, "learning_rate": 4.871794871794872e-06, "loss": 1.1005, "step": 38 }, { "epoch": 0.01, "grad_norm": 2.2455222878601098, "learning_rate": 5e-06, "loss": 1.1864, "step": 39 }, { "epoch": 0.01, "grad_norm": 2.1266583614163515, "learning_rate": 5.128205128205128e-06, "loss": 1.15, "step": 40 }, { "epoch": 0.01, "grad_norm": 2.089620655737586, "learning_rate": 5.256410256410257e-06, "loss": 1.1877, "step": 41 }, { "epoch": 0.01, "grad_norm": 2.197147361182619, "learning_rate": 5.384615384615385e-06, "loss": 1.1843, "step": 42 }, { "epoch": 0.01, "grad_norm": 1.1442985310608946, "learning_rate": 5.512820512820514e-06, "loss": 0.8406, "step": 43 }, { "epoch": 0.01, "grad_norm": 2.2343649074177634, "learning_rate": 5.641025641025641e-06, "loss": 1.2641, "step": 44 }, { "epoch": 0.01, "grad_norm": 2.2274293780592904, "learning_rate": 5.769230769230769e-06, "loss": 1.2005, "step": 45 }, { "epoch": 0.01, "grad_norm": 2.1702020802705553, "learning_rate": 5.897435897435898e-06, "loss": 1.2, "step": 46 }, { "epoch": 0.01, "grad_norm": 2.2728644356062087, "learning_rate": 6.025641025641026e-06, "loss": 1.1639, "step": 47 }, { "epoch": 0.01, "grad_norm": 2.296917779568054, "learning_rate": 6.153846153846155e-06, "loss": 1.1447, "step": 48 }, { "epoch": 0.01, "grad_norm": 2.1847920179158975, "learning_rate": 6.282051282051282e-06, "loss": 1.1049, "step": 49 }, { "epoch": 0.01, "grad_norm": 2.305602717661454, "learning_rate": 6.410256410256412e-06, "loss": 1.1454, "step": 50 }, { "epoch": 0.01, "grad_norm": 1.8163614577368297, "learning_rate": 6.538461538461539e-06, "loss": 1.1534, "step": 51 }, { "epoch": 0.01, "grad_norm": 2.0156958103382907, "learning_rate": 6.666666666666667e-06, "loss": 1.1014, "step": 52 }, { "epoch": 0.01, "grad_norm": 2.2061600271142927, "learning_rate": 6.794871794871796e-06, "loss": 1.1111, "step": 53 }, { "epoch": 0.01, "grad_norm": 2.0514290811875346, "learning_rate": 6.923076923076923e-06, "loss": 1.2195, "step": 54 }, { "epoch": 0.01, "grad_norm": 2.009350847624063, "learning_rate": 7.051282051282053e-06, "loss": 1.1672, "step": 55 }, { "epoch": 0.01, "grad_norm": 1.9383085189275544, "learning_rate": 7.17948717948718e-06, "loss": 1.1329, "step": 56 }, { "epoch": 0.01, "grad_norm": 2.231367175822086, "learning_rate": 7.307692307692308e-06, "loss": 1.1168, "step": 57 }, { "epoch": 0.01, "grad_norm": 2.0008003220100643, "learning_rate": 7.435897435897437e-06, "loss": 1.2286, "step": 58 }, { "epoch": 0.01, "grad_norm": 1.8980157371763204, "learning_rate": 7.564102564102564e-06, "loss": 1.0885, "step": 59 }, { "epoch": 0.01, "grad_norm": 1.9742084904113024, "learning_rate": 7.692307692307694e-06, "loss": 1.1383, "step": 60 }, { "epoch": 0.01, "grad_norm": 2.130005401042239, "learning_rate": 7.820512820512822e-06, "loss": 1.1859, "step": 61 }, { "epoch": 0.01, "grad_norm": 1.986055300283839, "learning_rate": 7.948717948717949e-06, "loss": 1.1223, "step": 62 }, { "epoch": 0.01, "grad_norm": 1.901481096038548, "learning_rate": 8.076923076923077e-06, "loss": 1.0932, "step": 63 }, { "epoch": 0.01, "grad_norm": 2.125815394626458, "learning_rate": 8.205128205128205e-06, "loss": 1.2282, "step": 64 }, { "epoch": 0.01, "grad_norm": 1.9414092406206, "learning_rate": 8.333333333333334e-06, "loss": 1.1273, "step": 65 }, { "epoch": 0.01, "grad_norm": 1.9746610829599591, "learning_rate": 8.461538461538462e-06, "loss": 1.048, "step": 66 }, { "epoch": 0.01, "grad_norm": 2.154415501683974, "learning_rate": 8.58974358974359e-06, "loss": 1.0115, "step": 67 }, { "epoch": 0.01, "grad_norm": 1.868695894296507, "learning_rate": 8.717948717948719e-06, "loss": 1.1381, "step": 68 }, { "epoch": 0.01, "grad_norm": 1.8811818709807824, "learning_rate": 8.846153846153847e-06, "loss": 1.1031, "step": 69 }, { "epoch": 0.01, "grad_norm": 2.3006046265407827, "learning_rate": 8.974358974358976e-06, "loss": 1.1062, "step": 70 }, { "epoch": 0.01, "grad_norm": 2.1699669644056137, "learning_rate": 9.102564102564104e-06, "loss": 1.1372, "step": 71 }, { "epoch": 0.01, "grad_norm": 1.8731108123220086, "learning_rate": 9.230769230769232e-06, "loss": 1.043, "step": 72 }, { "epoch": 0.01, "grad_norm": 2.1143191194853337, "learning_rate": 9.358974358974359e-06, "loss": 1.2095, "step": 73 }, { "epoch": 0.01, "grad_norm": 1.9506052984256566, "learning_rate": 9.487179487179487e-06, "loss": 1.1677, "step": 74 }, { "epoch": 0.01, "grad_norm": 2.004755199707491, "learning_rate": 9.615384615384616e-06, "loss": 1.1288, "step": 75 }, { "epoch": 0.01, "grad_norm": 2.2712419994719104, "learning_rate": 9.743589743589744e-06, "loss": 1.1489, "step": 76 }, { "epoch": 0.01, "grad_norm": 1.9915382414879983, "learning_rate": 9.871794871794872e-06, "loss": 1.1356, "step": 77 }, { "epoch": 0.02, "grad_norm": 1.8655506688742343, "learning_rate": 1e-05, "loss": 1.0524, "step": 78 }, { "epoch": 0.02, "grad_norm": 2.1482093297445575, "learning_rate": 1.012820512820513e-05, "loss": 0.9386, "step": 79 }, { "epoch": 0.02, "grad_norm": 1.9215954323448314, "learning_rate": 1.0256410256410256e-05, "loss": 1.1801, "step": 80 }, { "epoch": 0.02, "grad_norm": 1.9081067065165245, "learning_rate": 1.0384615384615386e-05, "loss": 1.0638, "step": 81 }, { "epoch": 0.02, "grad_norm": 1.9407275778581317, "learning_rate": 1.0512820512820514e-05, "loss": 1.1074, "step": 82 }, { "epoch": 0.02, "grad_norm": 2.025638661080253, "learning_rate": 1.0641025641025643e-05, "loss": 1.0776, "step": 83 }, { "epoch": 0.02, "grad_norm": 1.919914713517629, "learning_rate": 1.076923076923077e-05, "loss": 1.0189, "step": 84 }, { "epoch": 0.02, "grad_norm": 2.1903909968624977, "learning_rate": 1.0897435897435898e-05, "loss": 1.1085, "step": 85 }, { "epoch": 0.02, "grad_norm": 2.17664798755956, "learning_rate": 1.1025641025641028e-05, "loss": 1.0529, "step": 86 }, { "epoch": 0.02, "grad_norm": 2.113038538305221, "learning_rate": 1.1153846153846154e-05, "loss": 1.1169, "step": 87 }, { "epoch": 0.02, "grad_norm": 2.0486185050480894, "learning_rate": 1.1282051282051283e-05, "loss": 1.1889, "step": 88 }, { "epoch": 0.02, "grad_norm": 2.045888088194733, "learning_rate": 1.1410256410256411e-05, "loss": 1.1538, "step": 89 }, { "epoch": 0.02, "grad_norm": 1.7806490104735406, "learning_rate": 1.1538461538461538e-05, "loss": 1.0914, "step": 90 }, { "epoch": 0.02, "grad_norm": 2.1971405645771527, "learning_rate": 1.1666666666666668e-05, "loss": 1.048, "step": 91 }, { "epoch": 0.02, "grad_norm": 2.002750992348389, "learning_rate": 1.1794871794871796e-05, "loss": 1.0975, "step": 92 }, { "epoch": 0.02, "grad_norm": 2.187960188699195, "learning_rate": 1.1923076923076925e-05, "loss": 1.0906, "step": 93 }, { "epoch": 0.02, "grad_norm": 2.0174873060151857, "learning_rate": 1.2051282051282051e-05, "loss": 1.0992, "step": 94 }, { "epoch": 0.02, "grad_norm": 2.0443319007612852, "learning_rate": 1.217948717948718e-05, "loss": 1.082, "step": 95 }, { "epoch": 0.02, "grad_norm": 1.2748628196945109, "learning_rate": 1.230769230769231e-05, "loss": 0.7718, "step": 96 }, { "epoch": 0.02, "grad_norm": 1.896137442216524, "learning_rate": 1.2435897435897436e-05, "loss": 1.1549, "step": 97 }, { "epoch": 0.02, "grad_norm": 1.95843096706086, "learning_rate": 1.2564102564102565e-05, "loss": 1.128, "step": 98 }, { "epoch": 0.02, "grad_norm": 2.0686480210411657, "learning_rate": 1.2692307692307693e-05, "loss": 1.1249, "step": 99 }, { "epoch": 0.02, "grad_norm": 1.9404669088500452, "learning_rate": 1.2820512820512823e-05, "loss": 1.115, "step": 100 }, { "epoch": 0.02, "grad_norm": 1.8653249453155127, "learning_rate": 1.294871794871795e-05, "loss": 1.1051, "step": 101 }, { "epoch": 0.02, "grad_norm": 2.10107543117975, "learning_rate": 1.3076923076923078e-05, "loss": 1.0875, "step": 102 }, { "epoch": 0.02, "grad_norm": 1.8747249569118767, "learning_rate": 1.3205128205128207e-05, "loss": 1.0451, "step": 103 }, { "epoch": 0.02, "grad_norm": 1.9850084346269088, "learning_rate": 1.3333333333333333e-05, "loss": 1.0689, "step": 104 }, { "epoch": 0.02, "grad_norm": 2.049123340018695, "learning_rate": 1.3461538461538463e-05, "loss": 1.0905, "step": 105 }, { "epoch": 0.02, "grad_norm": 2.1264307975036925, "learning_rate": 1.3589743589743592e-05, "loss": 1.1224, "step": 106 }, { "epoch": 0.02, "grad_norm": 2.0502742046299907, "learning_rate": 1.3717948717948718e-05, "loss": 1.0915, "step": 107 }, { "epoch": 0.02, "grad_norm": 1.8303440971792886, "learning_rate": 1.3846153846153847e-05, "loss": 1.0949, "step": 108 }, { "epoch": 0.02, "grad_norm": 2.2313836077753413, "learning_rate": 1.3974358974358975e-05, "loss": 1.0429, "step": 109 }, { "epoch": 0.02, "grad_norm": 1.8919532863183655, "learning_rate": 1.4102564102564105e-05, "loss": 1.0763, "step": 110 }, { "epoch": 0.02, "grad_norm": 2.0704343058304526, "learning_rate": 1.4230769230769232e-05, "loss": 1.1657, "step": 111 }, { "epoch": 0.02, "grad_norm": 2.430724552963001, "learning_rate": 1.435897435897436e-05, "loss": 1.0815, "step": 112 }, { "epoch": 0.02, "grad_norm": 1.1085720824994245, "learning_rate": 1.4487179487179489e-05, "loss": 0.866, "step": 113 }, { "epoch": 0.02, "grad_norm": 1.8279405733949405, "learning_rate": 1.4615384615384615e-05, "loss": 1.0434, "step": 114 }, { "epoch": 0.02, "grad_norm": 1.9381964085003, "learning_rate": 1.4743589743589745e-05, "loss": 1.0764, "step": 115 }, { "epoch": 0.02, "grad_norm": 0.9487925657079459, "learning_rate": 1.4871794871794874e-05, "loss": 0.7605, "step": 116 }, { "epoch": 0.02, "grad_norm": 2.1860059019926847, "learning_rate": 1.5000000000000002e-05, "loss": 1.0553, "step": 117 }, { "epoch": 0.02, "grad_norm": 1.9458206802695046, "learning_rate": 1.5128205128205129e-05, "loss": 1.048, "step": 118 }, { "epoch": 0.02, "grad_norm": 1.835280245148161, "learning_rate": 1.5256410256410257e-05, "loss": 1.055, "step": 119 }, { "epoch": 0.02, "grad_norm": 2.0496294448787333, "learning_rate": 1.5384615384615387e-05, "loss": 1.1847, "step": 120 }, { "epoch": 0.02, "grad_norm": 2.218142247887536, "learning_rate": 1.5512820512820516e-05, "loss": 1.0944, "step": 121 }, { "epoch": 0.02, "grad_norm": 2.4654880331995055, "learning_rate": 1.5641025641025644e-05, "loss": 1.1229, "step": 122 }, { "epoch": 0.02, "grad_norm": 1.9292976768956316, "learning_rate": 1.576923076923077e-05, "loss": 1.0633, "step": 123 }, { "epoch": 0.02, "grad_norm": 1.9404361588446972, "learning_rate": 1.5897435897435897e-05, "loss": 1.0854, "step": 124 }, { "epoch": 0.02, "grad_norm": 1.9362855000410057, "learning_rate": 1.602564102564103e-05, "loss": 1.0061, "step": 125 }, { "epoch": 0.02, "grad_norm": 2.083318365558794, "learning_rate": 1.6153846153846154e-05, "loss": 1.0612, "step": 126 }, { "epoch": 0.02, "grad_norm": 2.122373700349859, "learning_rate": 1.6282051282051282e-05, "loss": 0.9871, "step": 127 }, { "epoch": 0.02, "grad_norm": 2.359431021405571, "learning_rate": 1.641025641025641e-05, "loss": 1.0635, "step": 128 }, { "epoch": 0.02, "grad_norm": 1.0429268801216616, "learning_rate": 1.653846153846154e-05, "loss": 0.8406, "step": 129 }, { "epoch": 0.03, "grad_norm": 2.394181875364715, "learning_rate": 1.6666666666666667e-05, "loss": 1.0533, "step": 130 }, { "epoch": 0.03, "grad_norm": 2.0279839342385624, "learning_rate": 1.6794871794871796e-05, "loss": 1.1405, "step": 131 }, { "epoch": 0.03, "grad_norm": 2.133411698576336, "learning_rate": 1.6923076923076924e-05, "loss": 1.1123, "step": 132 }, { "epoch": 0.03, "grad_norm": 2.0961335815701654, "learning_rate": 1.7051282051282053e-05, "loss": 1.1525, "step": 133 }, { "epoch": 0.03, "grad_norm": 2.0054012186334265, "learning_rate": 1.717948717948718e-05, "loss": 1.0072, "step": 134 }, { "epoch": 0.03, "grad_norm": 1.9954089428486153, "learning_rate": 1.730769230769231e-05, "loss": 0.9954, "step": 135 }, { "epoch": 0.03, "grad_norm": 1.9266633957752657, "learning_rate": 1.7435897435897438e-05, "loss": 1.0307, "step": 136 }, { "epoch": 0.03, "grad_norm": 2.0235377885233734, "learning_rate": 1.7564102564102566e-05, "loss": 1.0939, "step": 137 }, { "epoch": 0.03, "grad_norm": 2.0175192551390526, "learning_rate": 1.7692307692307694e-05, "loss": 1.0717, "step": 138 }, { "epoch": 0.03, "grad_norm": 1.0342136013306582, "learning_rate": 1.7820512820512823e-05, "loss": 0.808, "step": 139 }, { "epoch": 0.03, "grad_norm": 2.428830129959296, "learning_rate": 1.794871794871795e-05, "loss": 1.082, "step": 140 }, { "epoch": 0.03, "grad_norm": 1.9642876987686577, "learning_rate": 1.807692307692308e-05, "loss": 1.1122, "step": 141 }, { "epoch": 0.03, "grad_norm": 2.027656601747293, "learning_rate": 1.8205128205128208e-05, "loss": 1.0719, "step": 142 }, { "epoch": 0.03, "grad_norm": 2.183894708322355, "learning_rate": 1.8333333333333333e-05, "loss": 1.1253, "step": 143 }, { "epoch": 0.03, "grad_norm": 2.062043365070345, "learning_rate": 1.8461538461538465e-05, "loss": 1.0173, "step": 144 }, { "epoch": 0.03, "grad_norm": 2.033473969787848, "learning_rate": 1.8589743589743593e-05, "loss": 1.1215, "step": 145 }, { "epoch": 0.03, "grad_norm": 2.062919227268133, "learning_rate": 1.8717948717948718e-05, "loss": 0.9471, "step": 146 }, { "epoch": 0.03, "grad_norm": 2.070479749634218, "learning_rate": 1.8846153846153846e-05, "loss": 1.1518, "step": 147 }, { "epoch": 0.03, "grad_norm": 1.9754065164309047, "learning_rate": 1.8974358974358975e-05, "loss": 1.0442, "step": 148 }, { "epoch": 0.03, "grad_norm": 2.13339324208887, "learning_rate": 1.9102564102564106e-05, "loss": 1.0118, "step": 149 }, { "epoch": 0.03, "grad_norm": 2.369137183205933, "learning_rate": 1.923076923076923e-05, "loss": 1.092, "step": 150 }, { "epoch": 0.03, "grad_norm": 2.1638382502455435, "learning_rate": 1.935897435897436e-05, "loss": 0.9977, "step": 151 }, { "epoch": 0.03, "grad_norm": 2.1783663043501296, "learning_rate": 1.9487179487179488e-05, "loss": 1.0939, "step": 152 }, { "epoch": 0.03, "grad_norm": 1.9497922494089797, "learning_rate": 1.9615384615384617e-05, "loss": 1.0152, "step": 153 }, { "epoch": 0.03, "grad_norm": 2.0547723801429747, "learning_rate": 1.9743589743589745e-05, "loss": 1.0223, "step": 154 }, { "epoch": 0.03, "grad_norm": 2.070242647096933, "learning_rate": 1.9871794871794873e-05, "loss": 0.9549, "step": 155 }, { "epoch": 0.03, "grad_norm": 1.9301029883856002, "learning_rate": 2e-05, "loss": 1.0594, "step": 156 }, { "epoch": 0.03, "grad_norm": 2.1096159037163598, "learning_rate": 1.9999998054972106e-05, "loss": 1.0369, "step": 157 }, { "epoch": 0.03, "grad_norm": 2.1245553998838536, "learning_rate": 1.9999992219889184e-05, "loss": 0.9525, "step": 158 }, { "epoch": 0.03, "grad_norm": 2.131488635617247, "learning_rate": 1.99999824947535e-05, "loss": 1.0323, "step": 159 }, { "epoch": 0.03, "grad_norm": 2.363965004377438, "learning_rate": 1.9999968879568835e-05, "loss": 1.0856, "step": 160 }, { "epoch": 0.03, "grad_norm": 2.0585329850283522, "learning_rate": 1.9999951374340493e-05, "loss": 1.0892, "step": 161 }, { "epoch": 0.03, "grad_norm": 1.9750564938392907, "learning_rate": 1.9999929979075278e-05, "loss": 1.0452, "step": 162 }, { "epoch": 0.03, "grad_norm": 2.141328684995138, "learning_rate": 1.999990469378151e-05, "loss": 1.1101, "step": 163 }, { "epoch": 0.03, "grad_norm": 1.031433061724888, "learning_rate": 1.9999875518469033e-05, "loss": 0.799, "step": 164 }, { "epoch": 0.03, "grad_norm": 2.4065812716730095, "learning_rate": 1.9999842453149192e-05, "loss": 1.0711, "step": 165 }, { "epoch": 0.03, "grad_norm": 2.202667832906497, "learning_rate": 1.999980549783485e-05, "loss": 0.994, "step": 166 }, { "epoch": 0.03, "grad_norm": 2.129957736688869, "learning_rate": 1.9999764652540382e-05, "loss": 1.0424, "step": 167 }, { "epoch": 0.03, "grad_norm": 2.32808847121314, "learning_rate": 1.9999719917281682e-05, "loss": 1.1104, "step": 168 }, { "epoch": 0.03, "grad_norm": 2.402682209687328, "learning_rate": 1.9999671292076145e-05, "loss": 1.1413, "step": 169 }, { "epoch": 0.03, "grad_norm": 2.1985356868714634, "learning_rate": 1.9999618776942692e-05, "loss": 1.0147, "step": 170 }, { "epoch": 0.03, "grad_norm": 2.174198937460871, "learning_rate": 1.999956237190175e-05, "loss": 1.0795, "step": 171 }, { "epoch": 0.03, "grad_norm": 2.5202206051237606, "learning_rate": 1.9999502076975257e-05, "loss": 0.9901, "step": 172 }, { "epoch": 0.03, "grad_norm": 2.1957807846109967, "learning_rate": 1.9999437892186673e-05, "loss": 0.9667, "step": 173 }, { "epoch": 0.03, "grad_norm": 1.9569728406033189, "learning_rate": 1.9999369817560967e-05, "loss": 1.0522, "step": 174 }, { "epoch": 0.03, "grad_norm": 2.245962863895941, "learning_rate": 1.9999297853124614e-05, "loss": 1.0186, "step": 175 }, { "epoch": 0.03, "grad_norm": 2.413279476262106, "learning_rate": 1.9999221998905613e-05, "loss": 1.0631, "step": 176 }, { "epoch": 0.03, "grad_norm": 2.076972357794391, "learning_rate": 1.9999142254933476e-05, "loss": 1.0691, "step": 177 }, { "epoch": 0.03, "grad_norm": 1.972083747779467, "learning_rate": 1.9999058621239217e-05, "loss": 1.0699, "step": 178 }, { "epoch": 0.03, "grad_norm": 2.1755848177736334, "learning_rate": 1.9998971097855372e-05, "loss": 1.1303, "step": 179 }, { "epoch": 0.03, "grad_norm": 1.9839915727644544, "learning_rate": 1.999887968481599e-05, "loss": 1.0598, "step": 180 }, { "epoch": 0.03, "grad_norm": 2.0373868712914938, "learning_rate": 1.9998784382156622e-05, "loss": 1.0762, "step": 181 }, { "epoch": 0.04, "grad_norm": 2.0029728344755298, "learning_rate": 1.9998685189914356e-05, "loss": 1.1297, "step": 182 }, { "epoch": 0.04, "grad_norm": 1.9387023208997487, "learning_rate": 1.999858210812777e-05, "loss": 0.9651, "step": 183 }, { "epoch": 0.04, "grad_norm": 2.1732843858578414, "learning_rate": 1.9998475136836966e-05, "loss": 1.0479, "step": 184 }, { "epoch": 0.04, "grad_norm": 1.954541614593413, "learning_rate": 1.999836427608355e-05, "loss": 0.9924, "step": 185 }, { "epoch": 0.04, "grad_norm": 1.9489826509232497, "learning_rate": 1.9998249525910656e-05, "loss": 1.0869, "step": 186 }, { "epoch": 0.04, "grad_norm": 1.762474252467788, "learning_rate": 1.999813088636292e-05, "loss": 0.9219, "step": 187 }, { "epoch": 0.04, "grad_norm": 2.0627539245716164, "learning_rate": 1.999800835748649e-05, "loss": 1.0559, "step": 188 }, { "epoch": 0.04, "grad_norm": 2.137164696299313, "learning_rate": 1.9997881939329034e-05, "loss": 1.0711, "step": 189 }, { "epoch": 0.04, "grad_norm": 2.102050244558165, "learning_rate": 1.9997751631939724e-05, "loss": 1.0547, "step": 190 }, { "epoch": 0.04, "grad_norm": 1.9560280671941297, "learning_rate": 1.999761743536926e-05, "loss": 1.0285, "step": 191 }, { "epoch": 0.04, "grad_norm": 2.2056335755059853, "learning_rate": 1.9997479349669836e-05, "loss": 1.039, "step": 192 }, { "epoch": 0.04, "grad_norm": 1.857852624351155, "learning_rate": 1.999733737489517e-05, "loss": 1.0525, "step": 193 }, { "epoch": 0.04, "grad_norm": 2.1149817844051846, "learning_rate": 1.9997191511100498e-05, "loss": 1.1631, "step": 194 }, { "epoch": 0.04, "grad_norm": 2.1742104034580874, "learning_rate": 1.9997041758342554e-05, "loss": 1.0704, "step": 195 }, { "epoch": 0.04, "grad_norm": 1.92170752202666, "learning_rate": 1.9996888116679597e-05, "loss": 1.0977, "step": 196 }, { "epoch": 0.04, "grad_norm": 1.8760103416157878, "learning_rate": 1.999673058617139e-05, "loss": 1.0593, "step": 197 }, { "epoch": 0.04, "grad_norm": 2.239018605486002, "learning_rate": 1.9996569166879215e-05, "loss": 1.1451, "step": 198 }, { "epoch": 0.04, "grad_norm": 1.9680194040337873, "learning_rate": 1.9996403858865867e-05, "loss": 1.1002, "step": 199 }, { "epoch": 0.04, "grad_norm": 1.8952136254504348, "learning_rate": 1.9996234662195653e-05, "loss": 1.13, "step": 200 }, { "epoch": 0.04, "grad_norm": 1.7805244417146453, "learning_rate": 1.9996061576934388e-05, "loss": 1.088, "step": 201 }, { "epoch": 0.04, "grad_norm": 1.8466727506858036, "learning_rate": 1.9995884603149403e-05, "loss": 1.0727, "step": 202 }, { "epoch": 0.04, "grad_norm": 1.8297374299414597, "learning_rate": 1.9995703740909542e-05, "loss": 0.9719, "step": 203 }, { "epoch": 0.04, "grad_norm": 1.8430958263907924, "learning_rate": 1.9995518990285166e-05, "loss": 1.0023, "step": 204 }, { "epoch": 0.04, "grad_norm": 2.0008787877943846, "learning_rate": 1.9995330351348135e-05, "loss": 1.1435, "step": 205 }, { "epoch": 0.04, "grad_norm": 1.767812451189823, "learning_rate": 1.999513782417184e-05, "loss": 0.988, "step": 206 }, { "epoch": 0.04, "grad_norm": 1.9499593819305316, "learning_rate": 1.999494140883117e-05, "loss": 1.0819, "step": 207 }, { "epoch": 0.04, "grad_norm": 1.9273733720896404, "learning_rate": 1.9994741105402533e-05, "loss": 0.9283, "step": 208 }, { "epoch": 0.04, "grad_norm": 2.045214086540413, "learning_rate": 1.9994536913963852e-05, "loss": 1.0441, "step": 209 }, { "epoch": 0.04, "grad_norm": 1.9323194027489348, "learning_rate": 1.999432883459455e-05, "loss": 1.0739, "step": 210 }, { "epoch": 0.04, "grad_norm": 1.78702758065982, "learning_rate": 1.9994116867375574e-05, "loss": 1.0648, "step": 211 }, { "epoch": 0.04, "grad_norm": 1.999325292321686, "learning_rate": 1.9993901012389386e-05, "loss": 1.0197, "step": 212 }, { "epoch": 0.04, "grad_norm": 1.9750895391330754, "learning_rate": 1.999368126971995e-05, "loss": 1.0378, "step": 213 }, { "epoch": 0.04, "grad_norm": 2.0645995523227865, "learning_rate": 1.9993457639452748e-05, "loss": 1.0636, "step": 214 }, { "epoch": 0.04, "grad_norm": 2.0348647174788024, "learning_rate": 1.999323012167477e-05, "loss": 1.0233, "step": 215 }, { "epoch": 0.04, "grad_norm": 1.955566109346601, "learning_rate": 1.999299871647453e-05, "loss": 1.1114, "step": 216 }, { "epoch": 0.04, "grad_norm": 2.0108878112553326, "learning_rate": 1.9992763423942038e-05, "loss": 1.0761, "step": 217 }, { "epoch": 0.04, "grad_norm": 1.9661856223780965, "learning_rate": 1.999252424416883e-05, "loss": 1.1253, "step": 218 }, { "epoch": 0.04, "grad_norm": 2.1696126303119874, "learning_rate": 1.9992281177247942e-05, "loss": 1.0375, "step": 219 }, { "epoch": 0.04, "grad_norm": 1.2041115439000005, "learning_rate": 1.999203422327393e-05, "loss": 0.8076, "step": 220 }, { "epoch": 0.04, "grad_norm": 1.9028998749132995, "learning_rate": 1.9991783382342867e-05, "loss": 1.0468, "step": 221 }, { "epoch": 0.04, "grad_norm": 2.2722564344114153, "learning_rate": 1.9991528654552326e-05, "loss": 1.066, "step": 222 }, { "epoch": 0.04, "grad_norm": 2.1410050185723164, "learning_rate": 1.9991270040001396e-05, "loss": 1.0753, "step": 223 }, { "epoch": 0.04, "grad_norm": 2.0921277876178137, "learning_rate": 1.9991007538790686e-05, "loss": 1.0768, "step": 224 }, { "epoch": 0.04, "grad_norm": 2.0882235349073617, "learning_rate": 1.9990741151022302e-05, "loss": 1.0978, "step": 225 }, { "epoch": 0.04, "grad_norm": 1.9414030643468547, "learning_rate": 1.9990470876799876e-05, "loss": 1.002, "step": 226 }, { "epoch": 0.04, "grad_norm": 2.17093585650916, "learning_rate": 1.9990196716228546e-05, "loss": 1.0542, "step": 227 }, { "epoch": 0.04, "grad_norm": 1.955440445323398, "learning_rate": 1.998991866941496e-05, "loss": 1.0849, "step": 228 }, { "epoch": 0.04, "grad_norm": 2.0226531291514176, "learning_rate": 1.9989636736467278e-05, "loss": 1.1224, "step": 229 }, { "epoch": 0.04, "grad_norm": 2.2336914840149285, "learning_rate": 1.9989350917495177e-05, "loss": 1.0551, "step": 230 }, { "epoch": 0.04, "grad_norm": 2.046392279697416, "learning_rate": 1.9989061212609845e-05, "loss": 1.0738, "step": 231 }, { "epoch": 0.04, "grad_norm": 2.248695264268023, "learning_rate": 1.998876762192397e-05, "loss": 1.019, "step": 232 }, { "epoch": 0.04, "grad_norm": 2.3362932243579713, "learning_rate": 1.9988470145551765e-05, "loss": 1.0555, "step": 233 }, { "epoch": 0.05, "grad_norm": 2.149028179411019, "learning_rate": 1.9988168783608955e-05, "loss": 1.0529, "step": 234 }, { "epoch": 0.05, "grad_norm": 1.8633459882398478, "learning_rate": 1.9987863536212765e-05, "loss": 1.0074, "step": 235 }, { "epoch": 0.05, "grad_norm": 2.0594450846907373, "learning_rate": 1.9987554403481938e-05, "loss": 0.966, "step": 236 }, { "epoch": 0.05, "grad_norm": 1.9956893021238926, "learning_rate": 1.9987241385536732e-05, "loss": 1.0367, "step": 237 }, { "epoch": 0.05, "grad_norm": 2.025631177166738, "learning_rate": 1.9986924482498907e-05, "loss": 1.0407, "step": 238 }, { "epoch": 0.05, "grad_norm": 2.0369291335090365, "learning_rate": 1.998660369449175e-05, "loss": 1.0408, "step": 239 }, { "epoch": 0.05, "grad_norm": 1.9777103589259433, "learning_rate": 1.998627902164004e-05, "loss": 1.0964, "step": 240 }, { "epoch": 0.05, "grad_norm": 0.9884611294066915, "learning_rate": 1.998595046407008e-05, "loss": 0.7983, "step": 241 }, { "epoch": 0.05, "grad_norm": 2.0510845934246746, "learning_rate": 1.998561802190968e-05, "loss": 1.0129, "step": 242 }, { "epoch": 0.05, "grad_norm": 2.4092760114986467, "learning_rate": 1.9985281695288165e-05, "loss": 1.076, "step": 243 }, { "epoch": 0.05, "grad_norm": 1.9933609047274952, "learning_rate": 1.998494148433636e-05, "loss": 1.0225, "step": 244 }, { "epoch": 0.05, "grad_norm": 1.0232974321656905, "learning_rate": 1.9984597389186618e-05, "loss": 0.829, "step": 245 }, { "epoch": 0.05, "grad_norm": 2.0605065022696967, "learning_rate": 1.9984249409972794e-05, "loss": 0.9931, "step": 246 }, { "epoch": 0.05, "grad_norm": 2.2454749233665545, "learning_rate": 1.9983897546830243e-05, "loss": 1.0803, "step": 247 }, { "epoch": 0.05, "grad_norm": 1.8431535853254453, "learning_rate": 1.998354179989585e-05, "loss": 0.983, "step": 248 }, { "epoch": 0.05, "grad_norm": 1.8566618675252857, "learning_rate": 1.9983182169308004e-05, "loss": 0.9921, "step": 249 }, { "epoch": 0.05, "grad_norm": 1.9375277651998517, "learning_rate": 1.9982818655206602e-05, "loss": 1.0113, "step": 250 }, { "epoch": 0.05, "grad_norm": 1.9572548426006255, "learning_rate": 1.9982451257733047e-05, "loss": 1.1174, "step": 251 }, { "epoch": 0.05, "grad_norm": 2.0028626956048434, "learning_rate": 1.9982079977030267e-05, "loss": 1.1028, "step": 252 }, { "epoch": 0.05, "grad_norm": 1.96219145866627, "learning_rate": 1.9981704813242685e-05, "loss": 1.0566, "step": 253 }, { "epoch": 0.05, "grad_norm": 2.072795047778876, "learning_rate": 1.9981325766516248e-05, "loss": 1.0744, "step": 254 }, { "epoch": 0.05, "grad_norm": 2.036098657993234, "learning_rate": 1.9980942836998404e-05, "loss": 1.0763, "step": 255 }, { "epoch": 0.05, "grad_norm": 2.1388481294252855, "learning_rate": 1.9980556024838116e-05, "loss": 1.1613, "step": 256 }, { "epoch": 0.05, "grad_norm": 2.067974800297108, "learning_rate": 1.9980165330185857e-05, "loss": 0.998, "step": 257 }, { "epoch": 0.05, "grad_norm": 1.8790643051942517, "learning_rate": 1.9979770753193605e-05, "loss": 0.996, "step": 258 }, { "epoch": 0.05, "grad_norm": 1.9559433697812194, "learning_rate": 1.9979372294014854e-05, "loss": 1.0239, "step": 259 }, { "epoch": 0.05, "grad_norm": 1.9308127181761399, "learning_rate": 1.9978969952804613e-05, "loss": 1.1269, "step": 260 }, { "epoch": 0.05, "grad_norm": 1.924957556737311, "learning_rate": 1.9978563729719386e-05, "loss": 1.0322, "step": 261 }, { "epoch": 0.05, "grad_norm": 2.119914670588116, "learning_rate": 1.99781536249172e-05, "loss": 1.111, "step": 262 }, { "epoch": 0.05, "grad_norm": 2.2814838916359177, "learning_rate": 1.9977739638557593e-05, "loss": 0.9882, "step": 263 }, { "epoch": 0.05, "grad_norm": 1.9764920210183117, "learning_rate": 1.99773217708016e-05, "loss": 1.0747, "step": 264 }, { "epoch": 0.05, "grad_norm": 1.8237059936330955, "learning_rate": 1.997690002181178e-05, "loss": 1.0228, "step": 265 }, { "epoch": 0.05, "grad_norm": 1.7957594475273144, "learning_rate": 1.9976474391752192e-05, "loss": 0.9876, "step": 266 }, { "epoch": 0.05, "grad_norm": 1.9980073321283007, "learning_rate": 1.997604488078841e-05, "loss": 1.0911, "step": 267 }, { "epoch": 0.05, "grad_norm": 2.0146788024415074, "learning_rate": 1.9975611489087516e-05, "loss": 1.022, "step": 268 }, { "epoch": 0.05, "grad_norm": 2.1844582382911173, "learning_rate": 1.9975174216818097e-05, "loss": 1.0328, "step": 269 }, { "epoch": 0.05, "grad_norm": 2.117333899762936, "learning_rate": 1.997473306415026e-05, "loss": 0.9903, "step": 270 }, { "epoch": 0.05, "grad_norm": 1.8007107570814573, "learning_rate": 1.997428803125562e-05, "loss": 0.9672, "step": 271 }, { "epoch": 0.05, "grad_norm": 2.094142577887572, "learning_rate": 1.9973839118307286e-05, "loss": 1.0761, "step": 272 }, { "epoch": 0.05, "grad_norm": 1.9921256605922988, "learning_rate": 1.9973386325479897e-05, "loss": 1.0929, "step": 273 }, { "epoch": 0.05, "grad_norm": 1.7196271013592903, "learning_rate": 1.9972929652949587e-05, "loss": 0.989, "step": 274 }, { "epoch": 0.05, "grad_norm": 1.878734015541386, "learning_rate": 1.9972469100894005e-05, "loss": 1.0751, "step": 275 }, { "epoch": 0.05, "grad_norm": 1.9232024443567461, "learning_rate": 1.9972004669492313e-05, "loss": 1.0705, "step": 276 }, { "epoch": 0.05, "grad_norm": 1.2481706461115407, "learning_rate": 1.997153635892517e-05, "loss": 0.8429, "step": 277 }, { "epoch": 0.05, "grad_norm": 1.8327598842861688, "learning_rate": 1.9971064169374755e-05, "loss": 1.0771, "step": 278 }, { "epoch": 0.05, "grad_norm": 1.7554713225318588, "learning_rate": 1.9970588101024754e-05, "loss": 1.0262, "step": 279 }, { "epoch": 0.05, "grad_norm": 2.1469666455805716, "learning_rate": 1.9970108154060357e-05, "loss": 1.0043, "step": 280 }, { "epoch": 0.05, "grad_norm": 1.67449508407844, "learning_rate": 1.9969624328668267e-05, "loss": 0.9486, "step": 281 }, { "epoch": 0.05, "grad_norm": 1.8820097189830565, "learning_rate": 1.9969136625036694e-05, "loss": 1.0906, "step": 282 }, { "epoch": 0.05, "grad_norm": 2.1303500190062223, "learning_rate": 1.996864504335536e-05, "loss": 1.1237, "step": 283 }, { "epoch": 0.05, "grad_norm": 1.780586955227666, "learning_rate": 1.9968149583815494e-05, "loss": 1.003, "step": 284 }, { "epoch": 0.05, "grad_norm": 1.7489913602886422, "learning_rate": 1.996765024660983e-05, "loss": 0.9842, "step": 285 }, { "epoch": 0.06, "grad_norm": 2.0155100896265767, "learning_rate": 1.996714703193261e-05, "loss": 1.0557, "step": 286 }, { "epoch": 0.06, "grad_norm": 1.9438109572777202, "learning_rate": 1.996663993997959e-05, "loss": 0.9971, "step": 287 }, { "epoch": 0.06, "grad_norm": 1.0728126863662977, "learning_rate": 1.9966128970948038e-05, "loss": 0.8342, "step": 288 }, { "epoch": 0.06, "grad_norm": 1.9934840280210313, "learning_rate": 1.9965614125036712e-05, "loss": 1.0524, "step": 289 }, { "epoch": 0.06, "grad_norm": 2.0936769507538386, "learning_rate": 1.9965095402445898e-05, "loss": 1.1212, "step": 290 }, { "epoch": 0.06, "grad_norm": 1.9745427712772865, "learning_rate": 1.996457280337738e-05, "loss": 1.0978, "step": 291 }, { "epoch": 0.06, "grad_norm": 1.9179177319145042, "learning_rate": 1.996404632803445e-05, "loss": 1.0146, "step": 292 }, { "epoch": 0.06, "grad_norm": 2.052073495470475, "learning_rate": 1.9963515976621914e-05, "loss": 1.0465, "step": 293 }, { "epoch": 0.06, "grad_norm": 1.8225286684088682, "learning_rate": 1.996298174934608e-05, "loss": 1.1047, "step": 294 }, { "epoch": 0.06, "grad_norm": 1.7580289784696486, "learning_rate": 1.996244364641476e-05, "loss": 0.9965, "step": 295 }, { "epoch": 0.06, "grad_norm": 2.0161159763669554, "learning_rate": 1.996190166803729e-05, "loss": 1.1507, "step": 296 }, { "epoch": 0.06, "grad_norm": 1.8172911318254807, "learning_rate": 1.996135581442449e-05, "loss": 1.0353, "step": 297 }, { "epoch": 0.06, "grad_norm": 1.8747317892295494, "learning_rate": 1.996080608578871e-05, "loss": 1.0875, "step": 298 }, { "epoch": 0.06, "grad_norm": 2.0573127120786463, "learning_rate": 1.9960252482343797e-05, "loss": 1.0821, "step": 299 }, { "epoch": 0.06, "grad_norm": 1.900633660421174, "learning_rate": 1.9959695004305097e-05, "loss": 1.0045, "step": 300 }, { "epoch": 0.06, "grad_norm": 1.7491633697794904, "learning_rate": 1.995913365188948e-05, "loss": 1.0168, "step": 301 }, { "epoch": 0.06, "grad_norm": 1.05599591440065, "learning_rate": 1.9958568425315316e-05, "loss": 0.9449, "step": 302 }, { "epoch": 0.06, "grad_norm": 1.8883190997093964, "learning_rate": 1.9957999324802473e-05, "loss": 1.0428, "step": 303 }, { "epoch": 0.06, "grad_norm": 1.720295899770073, "learning_rate": 1.9957426350572345e-05, "loss": 0.9482, "step": 304 }, { "epoch": 0.06, "grad_norm": 1.9816495220080403, "learning_rate": 1.995684950284781e-05, "loss": 1.0557, "step": 305 }, { "epoch": 0.06, "grad_norm": 1.92187930498817, "learning_rate": 1.9956268781853277e-05, "loss": 1.0582, "step": 306 }, { "epoch": 0.06, "grad_norm": 1.795117789160023, "learning_rate": 1.9955684187814644e-05, "loss": 1.0761, "step": 307 }, { "epoch": 0.06, "grad_norm": 1.9245112528044024, "learning_rate": 1.9955095720959318e-05, "loss": 1.1684, "step": 308 }, { "epoch": 0.06, "grad_norm": 0.9632462029062842, "learning_rate": 1.9954503381516225e-05, "loss": 0.7674, "step": 309 }, { "epoch": 0.06, "grad_norm": 1.9219486581712448, "learning_rate": 1.995390716971578e-05, "loss": 1.0211, "step": 310 }, { "epoch": 0.06, "grad_norm": 1.9147529258042912, "learning_rate": 1.9953307085789916e-05, "loss": 1.0947, "step": 311 }, { "epoch": 0.06, "grad_norm": 1.023656325583728, "learning_rate": 1.995270312997207e-05, "loss": 0.8131, "step": 312 }, { "epoch": 0.06, "grad_norm": 1.7903741102627215, "learning_rate": 1.9952095302497185e-05, "loss": 0.9933, "step": 313 }, { "epoch": 0.06, "grad_norm": 2.02294327217036, "learning_rate": 1.9951483603601703e-05, "loss": 0.9262, "step": 314 }, { "epoch": 0.06, "grad_norm": 1.7932331946119509, "learning_rate": 1.9950868033523584e-05, "loss": 1.0388, "step": 315 }, { "epoch": 0.06, "grad_norm": 1.9016906199071297, "learning_rate": 1.9950248592502286e-05, "loss": 1.0161, "step": 316 }, { "epoch": 0.06, "grad_norm": 1.9496588477478443, "learning_rate": 1.994962528077878e-05, "loss": 1.0056, "step": 317 }, { "epoch": 0.06, "grad_norm": 1.7857218614144716, "learning_rate": 1.9948998098595526e-05, "loss": 1.0717, "step": 318 }, { "epoch": 0.06, "grad_norm": 2.2058906093436734, "learning_rate": 1.9948367046196513e-05, "loss": 1.0229, "step": 319 }, { "epoch": 0.06, "grad_norm": 1.8833597215221982, "learning_rate": 1.9947732123827218e-05, "loss": 1.0789, "step": 320 }, { "epoch": 0.06, "grad_norm": 1.0603717639007564, "learning_rate": 1.994709333173463e-05, "loss": 0.8642, "step": 321 }, { "epoch": 0.06, "grad_norm": 2.033922433865109, "learning_rate": 1.994645067016725e-05, "loss": 1.0365, "step": 322 }, { "epoch": 0.06, "grad_norm": 1.870516832634325, "learning_rate": 1.9945804139375066e-05, "loss": 0.9902, "step": 323 }, { "epoch": 0.06, "grad_norm": 0.9861030358173385, "learning_rate": 1.9945153739609588e-05, "loss": 0.7725, "step": 324 }, { "epoch": 0.06, "grad_norm": 1.9496791073979263, "learning_rate": 1.9944499471123824e-05, "loss": 1.0054, "step": 325 }, { "epoch": 0.06, "grad_norm": 2.0447227654810196, "learning_rate": 1.9943841334172288e-05, "loss": 1.1126, "step": 326 }, { "epoch": 0.06, "grad_norm": 2.24213973693733, "learning_rate": 1.9943179329010997e-05, "loss": 1.0988, "step": 327 }, { "epoch": 0.06, "grad_norm": 1.8596491661660886, "learning_rate": 1.994251345589748e-05, "loss": 1.0312, "step": 328 }, { "epoch": 0.06, "grad_norm": 1.9170393207754506, "learning_rate": 1.9941843715090758e-05, "loss": 1.0078, "step": 329 }, { "epoch": 0.06, "grad_norm": 1.8284329304637323, "learning_rate": 1.994117010685137e-05, "loss": 0.9095, "step": 330 }, { "epoch": 0.06, "grad_norm": 1.9552073759311999, "learning_rate": 1.9940492631441352e-05, "loss": 1.0652, "step": 331 }, { "epoch": 0.06, "grad_norm": 2.0132724055989812, "learning_rate": 1.9939811289124246e-05, "loss": 1.0849, "step": 332 }, { "epoch": 0.06, "grad_norm": 2.087593794800754, "learning_rate": 1.9939126080165093e-05, "loss": 1.0264, "step": 333 }, { "epoch": 0.06, "grad_norm": 1.8617360148956503, "learning_rate": 1.9938437004830453e-05, "loss": 1.0128, "step": 334 }, { "epoch": 0.06, "grad_norm": 1.6487974768481515, "learning_rate": 1.9937744063388365e-05, "loss": 0.924, "step": 335 }, { "epoch": 0.06, "grad_norm": 1.8887708831775187, "learning_rate": 1.9937047256108405e-05, "loss": 0.9823, "step": 336 }, { "epoch": 0.06, "grad_norm": 2.035534616225895, "learning_rate": 1.9936346583261622e-05, "loss": 1.0182, "step": 337 }, { "epoch": 0.07, "grad_norm": 1.969898654916401, "learning_rate": 1.9935642045120585e-05, "loss": 1.0657, "step": 338 }, { "epoch": 0.07, "grad_norm": 2.009217417503386, "learning_rate": 1.9934933641959367e-05, "loss": 0.9853, "step": 339 }, { "epoch": 0.07, "grad_norm": 1.8124399073403066, "learning_rate": 1.9934221374053538e-05, "loss": 0.9696, "step": 340 }, { "epoch": 0.07, "grad_norm": 1.9066949773049553, "learning_rate": 1.9933505241680176e-05, "loss": 1.1261, "step": 341 }, { "epoch": 0.07, "grad_norm": 1.843104252573575, "learning_rate": 1.9932785245117852e-05, "loss": 1.0277, "step": 342 }, { "epoch": 0.07, "grad_norm": 2.0257800926544487, "learning_rate": 1.9932061384646662e-05, "loss": 1.056, "step": 343 }, { "epoch": 0.07, "grad_norm": 1.069660038019677, "learning_rate": 1.993133366054818e-05, "loss": 0.8464, "step": 344 }, { "epoch": 0.07, "grad_norm": 2.047929245583957, "learning_rate": 1.9930602073105503e-05, "loss": 1.0297, "step": 345 }, { "epoch": 0.07, "grad_norm": 1.7804271272628047, "learning_rate": 1.9929866622603217e-05, "loss": 0.9681, "step": 346 }, { "epoch": 0.07, "grad_norm": 1.8036059077290953, "learning_rate": 1.992912730932742e-05, "loss": 1.0982, "step": 347 }, { "epoch": 0.07, "grad_norm": 2.1577273526751513, "learning_rate": 1.992838413356571e-05, "loss": 1.0578, "step": 348 }, { "epoch": 0.07, "grad_norm": 1.9351592416164614, "learning_rate": 1.992763709560718e-05, "loss": 1.0799, "step": 349 }, { "epoch": 0.07, "grad_norm": 1.7613887958883605, "learning_rate": 1.992688619574244e-05, "loss": 1.118, "step": 350 }, { "epoch": 0.07, "grad_norm": 1.7710807310053625, "learning_rate": 1.9926131434263587e-05, "loss": 1.0957, "step": 351 }, { "epoch": 0.07, "grad_norm": 2.1014264167112024, "learning_rate": 1.9925372811464232e-05, "loss": 1.0916, "step": 352 }, { "epoch": 0.07, "grad_norm": 1.695271742923848, "learning_rate": 1.9924610327639482e-05, "loss": 0.9742, "step": 353 }, { "epoch": 0.07, "grad_norm": 1.946395684960528, "learning_rate": 1.992384398308595e-05, "loss": 1.0277, "step": 354 }, { "epoch": 0.07, "grad_norm": 1.020284309819523, "learning_rate": 1.9923073778101743e-05, "loss": 0.8184, "step": 355 }, { "epoch": 0.07, "grad_norm": 1.7877368746091395, "learning_rate": 1.9922299712986478e-05, "loss": 1.0512, "step": 356 }, { "epoch": 0.07, "grad_norm": 1.9511674507474972, "learning_rate": 1.9921521788041273e-05, "loss": 0.9541, "step": 357 }, { "epoch": 0.07, "grad_norm": 1.8548873026796064, "learning_rate": 1.9920740003568743e-05, "loss": 1.0032, "step": 358 }, { "epoch": 0.07, "grad_norm": 2.369642361117581, "learning_rate": 1.9919954359873003e-05, "loss": 1.0463, "step": 359 }, { "epoch": 0.07, "grad_norm": 1.6853151801856843, "learning_rate": 1.991916485725968e-05, "loss": 0.9586, "step": 360 }, { "epoch": 0.07, "grad_norm": 2.121801973394243, "learning_rate": 1.991837149603589e-05, "loss": 1.007, "step": 361 }, { "epoch": 0.07, "grad_norm": 1.8694623317506724, "learning_rate": 1.9917574276510256e-05, "loss": 1.0233, "step": 362 }, { "epoch": 0.07, "grad_norm": 1.9936957782176836, "learning_rate": 1.99167731989929e-05, "loss": 1.11, "step": 363 }, { "epoch": 0.07, "grad_norm": 2.044933129387799, "learning_rate": 1.9915968263795448e-05, "loss": 1.0585, "step": 364 }, { "epoch": 0.07, "grad_norm": 1.9558810730478424, "learning_rate": 1.9915159471231025e-05, "loss": 0.9883, "step": 365 }, { "epoch": 0.07, "grad_norm": 2.0169845204190078, "learning_rate": 1.9914346821614247e-05, "loss": 1.0129, "step": 366 }, { "epoch": 0.07, "grad_norm": 2.0359412772425673, "learning_rate": 1.9913530315261252e-05, "loss": 1.0086, "step": 367 }, { "epoch": 0.07, "grad_norm": 2.018034818878424, "learning_rate": 1.991270995248966e-05, "loss": 1.0717, "step": 368 }, { "epoch": 0.07, "grad_norm": 1.9196933985110856, "learning_rate": 1.9911885733618594e-05, "loss": 1.0193, "step": 369 }, { "epoch": 0.07, "grad_norm": 1.8924726827316862, "learning_rate": 1.9911057658968677e-05, "loss": 1.0684, "step": 370 }, { "epoch": 0.07, "grad_norm": 1.957954173791168, "learning_rate": 1.9910225728862045e-05, "loss": 1.003, "step": 371 }, { "epoch": 0.07, "grad_norm": 1.7327565474786015, "learning_rate": 1.9909389943622316e-05, "loss": 1.0367, "step": 372 }, { "epoch": 0.07, "grad_norm": 2.1352232620719276, "learning_rate": 1.9908550303574617e-05, "loss": 1.1118, "step": 373 }, { "epoch": 0.07, "grad_norm": 2.0787287987087506, "learning_rate": 1.990770680904557e-05, "loss": 1.0894, "step": 374 }, { "epoch": 0.07, "grad_norm": 1.3620095751306678, "learning_rate": 1.9906859460363307e-05, "loss": 0.8552, "step": 375 }, { "epoch": 0.07, "grad_norm": 1.9670341479798041, "learning_rate": 1.9906008257857447e-05, "loss": 0.9371, "step": 376 }, { "epoch": 0.07, "grad_norm": 1.913167874526329, "learning_rate": 1.990515320185911e-05, "loss": 1.0643, "step": 377 }, { "epoch": 0.07, "grad_norm": 1.9217382388951545, "learning_rate": 1.9904294292700917e-05, "loss": 1.0264, "step": 378 }, { "epoch": 0.07, "grad_norm": 1.9352416915935249, "learning_rate": 1.9903431530716992e-05, "loss": 1.0726, "step": 379 }, { "epoch": 0.07, "grad_norm": 2.032603191233027, "learning_rate": 1.9902564916242952e-05, "loss": 1.0659, "step": 380 }, { "epoch": 0.07, "grad_norm": 1.9618668169033733, "learning_rate": 1.9901694449615917e-05, "loss": 1.0239, "step": 381 }, { "epoch": 0.07, "grad_norm": 2.09195688744226, "learning_rate": 1.9900820131174503e-05, "loss": 1.0984, "step": 382 }, { "epoch": 0.07, "grad_norm": 1.9234946021972024, "learning_rate": 1.989994196125882e-05, "loss": 1.0506, "step": 383 }, { "epoch": 0.07, "grad_norm": 1.0991909496265084, "learning_rate": 1.989905994021049e-05, "loss": 0.8034, "step": 384 }, { "epoch": 0.07, "grad_norm": 1.81014889387723, "learning_rate": 1.989817406837262e-05, "loss": 1.0006, "step": 385 }, { "epoch": 0.07, "grad_norm": 0.993529462114099, "learning_rate": 1.989728434608981e-05, "loss": 0.8089, "step": 386 }, { "epoch": 0.07, "grad_norm": 1.882727487143848, "learning_rate": 1.9896390773708182e-05, "loss": 1.0693, "step": 387 }, { "epoch": 0.07, "grad_norm": 1.7729876511972384, "learning_rate": 1.9895493351575333e-05, "loss": 1.1044, "step": 388 }, { "epoch": 0.07, "grad_norm": 1.8930447196671079, "learning_rate": 1.9894592080040364e-05, "loss": 1.0936, "step": 389 }, { "epoch": 0.08, "grad_norm": 1.7141797791734572, "learning_rate": 1.9893686959453875e-05, "loss": 0.9307, "step": 390 }, { "epoch": 0.08, "grad_norm": 2.0206681281369794, "learning_rate": 1.9892777990167967e-05, "loss": 1.0052, "step": 391 }, { "epoch": 0.08, "grad_norm": 1.9601360739455025, "learning_rate": 1.9891865172536233e-05, "loss": 1.0426, "step": 392 }, { "epoch": 0.08, "grad_norm": 1.6936067659027334, "learning_rate": 1.989094850691376e-05, "loss": 0.9326, "step": 393 }, { "epoch": 0.08, "grad_norm": 1.856166304153269, "learning_rate": 1.989002799365714e-05, "loss": 0.9852, "step": 394 }, { "epoch": 0.08, "grad_norm": 1.8367907200949016, "learning_rate": 1.9889103633124457e-05, "loss": 0.9592, "step": 395 }, { "epoch": 0.08, "grad_norm": 2.007355585475035, "learning_rate": 1.9888175425675288e-05, "loss": 1.0117, "step": 396 }, { "epoch": 0.08, "grad_norm": 1.8516073622878386, "learning_rate": 1.988724337167072e-05, "loss": 1.0603, "step": 397 }, { "epoch": 0.08, "grad_norm": 1.216372170317351, "learning_rate": 1.9886307471473323e-05, "loss": 0.7921, "step": 398 }, { "epoch": 0.08, "grad_norm": 1.9320279482943123, "learning_rate": 1.9885367725447162e-05, "loss": 1.0564, "step": 399 }, { "epoch": 0.08, "grad_norm": 1.8561275651991433, "learning_rate": 1.9884424133957808e-05, "loss": 1.0022, "step": 400 }, { "epoch": 0.08, "grad_norm": 1.912677537686615, "learning_rate": 1.9883476697372327e-05, "loss": 0.9387, "step": 401 }, { "epoch": 0.08, "grad_norm": 1.0297626339996624, "learning_rate": 1.9882525416059273e-05, "loss": 0.8481, "step": 402 }, { "epoch": 0.08, "grad_norm": 2.0247451338678344, "learning_rate": 1.98815702903887e-05, "loss": 0.9894, "step": 403 }, { "epoch": 0.08, "grad_norm": 1.9871374845980427, "learning_rate": 1.9880611320732154e-05, "loss": 1.0576, "step": 404 }, { "epoch": 0.08, "grad_norm": 1.9930155207385365, "learning_rate": 1.9879648507462687e-05, "loss": 0.9972, "step": 405 }, { "epoch": 0.08, "grad_norm": 2.0646801640749652, "learning_rate": 1.9878681850954833e-05, "loss": 1.0854, "step": 406 }, { "epoch": 0.08, "grad_norm": 1.8818333915154013, "learning_rate": 1.9877711351584628e-05, "loss": 1.0383, "step": 407 }, { "epoch": 0.08, "grad_norm": 1.9722438634458774, "learning_rate": 1.98767370097296e-05, "loss": 1.0116, "step": 408 }, { "epoch": 0.08, "grad_norm": 1.7066244506847275, "learning_rate": 1.987575882576878e-05, "loss": 1.0032, "step": 409 }, { "epoch": 0.08, "grad_norm": 1.902672174295704, "learning_rate": 1.987477680008268e-05, "loss": 1.1152, "step": 410 }, { "epoch": 0.08, "grad_norm": 1.7623694577336437, "learning_rate": 1.9873790933053316e-05, "loss": 0.9807, "step": 411 }, { "epoch": 0.08, "grad_norm": 1.9894455403137112, "learning_rate": 1.9872801225064196e-05, "loss": 1.0516, "step": 412 }, { "epoch": 0.08, "grad_norm": 2.1739518583820248, "learning_rate": 1.987180767650032e-05, "loss": 1.0914, "step": 413 }, { "epoch": 0.08, "grad_norm": 1.7886753698199753, "learning_rate": 1.987081028774819e-05, "loss": 0.9163, "step": 414 }, { "epoch": 0.08, "grad_norm": 1.1521609517012579, "learning_rate": 1.9869809059195787e-05, "loss": 0.8685, "step": 415 }, { "epoch": 0.08, "grad_norm": 1.8376642390611246, "learning_rate": 1.9868803991232602e-05, "loss": 0.9614, "step": 416 }, { "epoch": 0.08, "grad_norm": 1.8501436743338675, "learning_rate": 1.986779508424961e-05, "loss": 1.0526, "step": 417 }, { "epoch": 0.08, "grad_norm": 1.6869946424617572, "learning_rate": 1.9866782338639278e-05, "loss": 1.0524, "step": 418 }, { "epoch": 0.08, "grad_norm": 1.8153293231608487, "learning_rate": 1.986576575479557e-05, "loss": 1.0178, "step": 419 }, { "epoch": 0.08, "grad_norm": 1.7274306454495725, "learning_rate": 1.9864745333113948e-05, "loss": 0.9729, "step": 420 }, { "epoch": 0.08, "grad_norm": 1.939912973493156, "learning_rate": 1.986372107399136e-05, "loss": 1.0441, "step": 421 }, { "epoch": 0.08, "grad_norm": 1.7856564272695379, "learning_rate": 1.9862692977826242e-05, "loss": 1.1091, "step": 422 }, { "epoch": 0.08, "grad_norm": 1.8341112574380691, "learning_rate": 1.9861661045018537e-05, "loss": 0.8888, "step": 423 }, { "epoch": 0.08, "grad_norm": 1.8561948420468832, "learning_rate": 1.9860625275969673e-05, "loss": 1.039, "step": 424 }, { "epoch": 0.08, "grad_norm": 1.7934335505219023, "learning_rate": 1.9859585671082562e-05, "loss": 1.0336, "step": 425 }, { "epoch": 0.08, "grad_norm": 1.8360599761712861, "learning_rate": 1.9858542230761622e-05, "loss": 1.0813, "step": 426 }, { "epoch": 0.08, "grad_norm": 1.9867816840398522, "learning_rate": 1.985749495541276e-05, "loss": 1.0322, "step": 427 }, { "epoch": 0.08, "grad_norm": 1.9480167546900247, "learning_rate": 1.9856443845443364e-05, "loss": 1.0453, "step": 428 }, { "epoch": 0.08, "grad_norm": 2.1140835883562086, "learning_rate": 1.9855388901262324e-05, "loss": 1.0198, "step": 429 }, { "epoch": 0.08, "grad_norm": 2.064005705298389, "learning_rate": 1.9854330123280027e-05, "loss": 1.0869, "step": 430 }, { "epoch": 0.08, "grad_norm": 1.6915389255562758, "learning_rate": 1.985326751190833e-05, "loss": 1.0063, "step": 431 }, { "epoch": 0.08, "grad_norm": 1.8715414211034649, "learning_rate": 1.9852201067560607e-05, "loss": 0.9858, "step": 432 }, { "epoch": 0.08, "grad_norm": 1.9636600893192735, "learning_rate": 1.9851130790651706e-05, "loss": 1.0528, "step": 433 }, { "epoch": 0.08, "grad_norm": 1.966849427909118, "learning_rate": 1.9850056681597968e-05, "loss": 1.0915, "step": 434 }, { "epoch": 0.08, "grad_norm": 1.9070631155194202, "learning_rate": 1.9848978740817234e-05, "loss": 1.0174, "step": 435 }, { "epoch": 0.08, "grad_norm": 1.225217117866621, "learning_rate": 1.984789696872882e-05, "loss": 0.8672, "step": 436 }, { "epoch": 0.08, "grad_norm": 2.038760319545761, "learning_rate": 1.9846811365753548e-05, "loss": 1.0013, "step": 437 }, { "epoch": 0.08, "grad_norm": 2.022940013987618, "learning_rate": 1.9845721932313725e-05, "loss": 0.9708, "step": 438 }, { "epoch": 0.08, "grad_norm": 1.7647463910730028, "learning_rate": 1.984462866883314e-05, "loss": 0.9222, "step": 439 }, { "epoch": 0.08, "grad_norm": 1.866488318733101, "learning_rate": 1.9843531575737085e-05, "loss": 1.043, "step": 440 }, { "epoch": 0.08, "grad_norm": 1.8603090234733615, "learning_rate": 1.9842430653452333e-05, "loss": 0.9491, "step": 441 }, { "epoch": 0.09, "grad_norm": 1.8875785862623655, "learning_rate": 1.9841325902407144e-05, "loss": 0.9926, "step": 442 }, { "epoch": 0.09, "grad_norm": 1.942175598283091, "learning_rate": 1.9840217323031278e-05, "loss": 0.9455, "step": 443 }, { "epoch": 0.09, "grad_norm": 1.985476015117722, "learning_rate": 1.983910491575598e-05, "loss": 1.0879, "step": 444 }, { "epoch": 0.09, "grad_norm": 1.7275782937334652, "learning_rate": 1.9837988681013977e-05, "loss": 1.0377, "step": 445 }, { "epoch": 0.09, "grad_norm": 2.0112594657447027, "learning_rate": 1.9836868619239498e-05, "loss": 0.9808, "step": 446 }, { "epoch": 0.09, "grad_norm": 1.839058814041238, "learning_rate": 1.9835744730868244e-05, "loss": 0.8538, "step": 447 }, { "epoch": 0.09, "grad_norm": 2.157369191952226, "learning_rate": 1.9834617016337424e-05, "loss": 1.0736, "step": 448 }, { "epoch": 0.09, "grad_norm": 2.15228050930449, "learning_rate": 1.9833485476085715e-05, "loss": 1.019, "step": 449 }, { "epoch": 0.09, "grad_norm": 1.91857747393063, "learning_rate": 1.98323501105533e-05, "loss": 1.0517, "step": 450 }, { "epoch": 0.09, "grad_norm": 1.027868590912365, "learning_rate": 1.983121092018184e-05, "loss": 0.793, "step": 451 }, { "epoch": 0.09, "grad_norm": 1.773990990913634, "learning_rate": 1.9830067905414485e-05, "loss": 1.0535, "step": 452 }, { "epoch": 0.09, "grad_norm": 1.7448900958278026, "learning_rate": 1.9828921066695876e-05, "loss": 1.0646, "step": 453 }, { "epoch": 0.09, "grad_norm": 1.8842052222344852, "learning_rate": 1.982777040447214e-05, "loss": 0.9916, "step": 454 }, { "epoch": 0.09, "grad_norm": 1.965498295082324, "learning_rate": 1.9826615919190886e-05, "loss": 1.0308, "step": 455 }, { "epoch": 0.09, "grad_norm": 1.8825201063090378, "learning_rate": 1.9825457611301226e-05, "loss": 1.0029, "step": 456 }, { "epoch": 0.09, "grad_norm": 2.0328819583947006, "learning_rate": 1.9824295481253735e-05, "loss": 1.07, "step": 457 }, { "epoch": 0.09, "grad_norm": 1.0825105072372898, "learning_rate": 1.98231295295005e-05, "loss": 0.7738, "step": 458 }, { "epoch": 0.09, "grad_norm": 1.8165626539270863, "learning_rate": 1.9821959756495075e-05, "loss": 1.0831, "step": 459 }, { "epoch": 0.09, "grad_norm": 1.9422401630853525, "learning_rate": 1.982078616269251e-05, "loss": 1.0181, "step": 460 }, { "epoch": 0.09, "grad_norm": 1.7945631288777881, "learning_rate": 1.981960874854934e-05, "loss": 0.946, "step": 461 }, { "epoch": 0.09, "grad_norm": 1.997337758639312, "learning_rate": 1.9818427514523584e-05, "loss": 1.0037, "step": 462 }, { "epoch": 0.09, "grad_norm": 1.9193241141993849, "learning_rate": 1.9817242461074757e-05, "loss": 1.0171, "step": 463 }, { "epoch": 0.09, "grad_norm": 1.9978405533297976, "learning_rate": 1.981605358866384e-05, "loss": 1.0468, "step": 464 }, { "epoch": 0.09, "grad_norm": 1.8804833385106348, "learning_rate": 1.9814860897753317e-05, "loss": 0.916, "step": 465 }, { "epoch": 0.09, "grad_norm": 1.8028266192668139, "learning_rate": 1.981366438880715e-05, "loss": 1.0217, "step": 466 }, { "epoch": 0.09, "grad_norm": 1.7132667749630526, "learning_rate": 1.9812464062290788e-05, "loss": 1.0445, "step": 467 }, { "epoch": 0.09, "grad_norm": 1.9219672750165928, "learning_rate": 1.9811259918671168e-05, "loss": 1.031, "step": 468 }, { "epoch": 0.09, "grad_norm": 1.8280416256736887, "learning_rate": 1.9810051958416697e-05, "loss": 1.0184, "step": 469 }, { "epoch": 0.09, "grad_norm": 1.6689592882194266, "learning_rate": 1.9808840181997292e-05, "loss": 1.0227, "step": 470 }, { "epoch": 0.09, "grad_norm": 1.900220242233606, "learning_rate": 1.9807624589884335e-05, "loss": 1.0608, "step": 471 }, { "epoch": 0.09, "grad_norm": 1.6929314568440184, "learning_rate": 1.98064051825507e-05, "loss": 0.9899, "step": 472 }, { "epoch": 0.09, "grad_norm": 1.651258459418155, "learning_rate": 1.980518196047074e-05, "loss": 0.9661, "step": 473 }, { "epoch": 0.09, "grad_norm": 2.1874289610603563, "learning_rate": 1.9803954924120297e-05, "loss": 0.9393, "step": 474 }, { "epoch": 0.09, "grad_norm": 1.8038819153786403, "learning_rate": 1.9802724073976695e-05, "loss": 0.9559, "step": 475 }, { "epoch": 0.09, "grad_norm": 1.770721462261662, "learning_rate": 1.9801489410518736e-05, "loss": 0.9643, "step": 476 }, { "epoch": 0.09, "grad_norm": 1.7367654491312072, "learning_rate": 1.9800250934226723e-05, "loss": 0.9443, "step": 477 }, { "epoch": 0.09, "grad_norm": 1.9591444421711552, "learning_rate": 1.9799008645582424e-05, "loss": 0.9747, "step": 478 }, { "epoch": 0.09, "grad_norm": 1.6828464935006877, "learning_rate": 1.979776254506909e-05, "loss": 0.9754, "step": 479 }, { "epoch": 0.09, "grad_norm": 1.908226452531261, "learning_rate": 1.9796512633171476e-05, "loss": 1.1313, "step": 480 }, { "epoch": 0.09, "grad_norm": 1.306422799793475, "learning_rate": 1.9795258910375787e-05, "loss": 0.8817, "step": 481 }, { "epoch": 0.09, "grad_norm": 1.9053129529215438, "learning_rate": 1.979400137716974e-05, "loss": 1.0261, "step": 482 }, { "epoch": 0.09, "grad_norm": 1.9080635923357674, "learning_rate": 1.979274003404252e-05, "loss": 0.9686, "step": 483 }, { "epoch": 0.09, "grad_norm": 1.8037616024087626, "learning_rate": 1.9791474881484793e-05, "loss": 1.0324, "step": 484 }, { "epoch": 0.09, "grad_norm": 1.8250327442496437, "learning_rate": 1.9790205919988714e-05, "loss": 1.0082, "step": 485 }, { "epoch": 0.09, "grad_norm": 1.8511505666088204, "learning_rate": 1.9788933150047916e-05, "loss": 1.1118, "step": 486 }, { "epoch": 0.09, "grad_norm": 1.8903056078178093, "learning_rate": 1.9787656572157515e-05, "loss": 1.0646, "step": 487 }, { "epoch": 0.09, "grad_norm": 1.9195313614337501, "learning_rate": 1.97863761868141e-05, "loss": 1.0412, "step": 488 }, { "epoch": 0.09, "grad_norm": 1.9799264468742026, "learning_rate": 1.9785091994515756e-05, "loss": 1.0861, "step": 489 }, { "epoch": 0.09, "grad_norm": 1.6755241928671092, "learning_rate": 1.9783803995762033e-05, "loss": 0.9611, "step": 490 }, { "epoch": 0.09, "grad_norm": 1.961898488303003, "learning_rate": 1.9782512191053982e-05, "loss": 1.0589, "step": 491 }, { "epoch": 0.09, "grad_norm": 1.775413845673962, "learning_rate": 1.9781216580894108e-05, "loss": 1.0354, "step": 492 }, { "epoch": 0.09, "grad_norm": 1.7928396588919673, "learning_rate": 1.977991716578642e-05, "loss": 1.0508, "step": 493 }, { "epoch": 0.1, "grad_norm": 1.9412161829079344, "learning_rate": 1.9778613946236395e-05, "loss": 1.0015, "step": 494 }, { "epoch": 0.1, "grad_norm": 1.7096885758847509, "learning_rate": 1.9777306922750995e-05, "loss": 0.9801, "step": 495 }, { "epoch": 0.1, "grad_norm": 1.8191213564062976, "learning_rate": 1.9775996095838655e-05, "loss": 1.0899, "step": 496 }, { "epoch": 0.1, "grad_norm": 1.964813155629249, "learning_rate": 1.9774681466009295e-05, "loss": 1.053, "step": 497 }, { "epoch": 0.1, "grad_norm": 1.8601508656062495, "learning_rate": 1.9773363033774312e-05, "loss": 1.034, "step": 498 }, { "epoch": 0.1, "grad_norm": 1.5995716944146932, "learning_rate": 1.977204079964659e-05, "loss": 0.9518, "step": 499 }, { "epoch": 0.1, "grad_norm": 1.9695321697574193, "learning_rate": 1.977071476414048e-05, "loss": 0.9849, "step": 500 } ], "logging_steps": 1.0, "max_steps": 5193, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "total_flos": 678526663131136.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }