{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.32, "eval_steps": 500, "global_step": 200, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0016, "grad_norm": 18.498022079467773, "learning_rate": 0.0, "loss": 11.9034, "step": 1 }, { "epoch": 0.0032, "grad_norm": 19.59610366821289, "learning_rate": 7.142857142857143e-07, "loss": 12.361, "step": 2 }, { "epoch": 0.0048, "grad_norm": 19.05824089050293, "learning_rate": 1.4285714285714286e-06, "loss": 12.3027, "step": 3 }, { "epoch": 0.0064, "grad_norm": 18.656831741333008, "learning_rate": 2.1428571428571427e-06, "loss": 11.9369, "step": 4 }, { "epoch": 0.008, "grad_norm": 19.260093688964844, "learning_rate": 2.8571428571428573e-06, "loss": 12.0124, "step": 5 }, { "epoch": 0.0096, "grad_norm": 18.27457046508789, "learning_rate": 3.5714285714285718e-06, "loss": 11.8957, "step": 6 }, { "epoch": 0.0112, "grad_norm": 18.090967178344727, "learning_rate": 4.2857142857142855e-06, "loss": 12.0549, "step": 7 }, { "epoch": 0.0128, "grad_norm": 18.144412994384766, "learning_rate": 5e-06, "loss": 12.0455, "step": 8 }, { "epoch": 0.0144, "grad_norm": 17.77107048034668, "learning_rate": 4.999967697817016e-06, "loss": 12.0381, "step": 9 }, { "epoch": 0.016, "grad_norm": 19.326251983642578, "learning_rate": 4.9998707921028104e-06, "loss": 12.2511, "step": 10 }, { "epoch": 0.0176, "grad_norm": 20.007396697998047, "learning_rate": 4.999709285361594e-06, "loss": 12.5214, "step": 11 }, { "epoch": 0.0192, "grad_norm": 18.9156551361084, "learning_rate": 4.999483181766986e-06, "loss": 12.226, "step": 12 }, { "epoch": 0.0208, "grad_norm": 16.71934700012207, "learning_rate": 4.999192487161895e-06, "loss": 11.63, "step": 13 }, { "epoch": 0.0224, "grad_norm": 16.819419860839844, "learning_rate": 4.998837209058379e-06, "loss": 11.8643, "step": 14 }, { "epoch": 0.024, "grad_norm": 17.38993263244629, "learning_rate": 4.998417356637445e-06, "loss": 12.0876, "step": 15 }, { "epoch": 0.0256, "grad_norm": 17.411874771118164, "learning_rate": 4.997932940748811e-06, "loss": 11.9954, "step": 16 }, { "epoch": 0.0272, "grad_norm": 17.002464294433594, "learning_rate": 4.997383973910631e-06, "loss": 12.0872, "step": 17 }, { "epoch": 0.0288, "grad_norm": 16.964523315429688, "learning_rate": 4.996770470309167e-06, "loss": 11.9659, "step": 18 }, { "epoch": 0.0304, "grad_norm": 17.12218475341797, "learning_rate": 4.9960924457984225e-06, "loss": 11.9041, "step": 19 }, { "epoch": 0.032, "grad_norm": 15.89167308807373, "learning_rate": 4.995349917899735e-06, "loss": 11.5677, "step": 20 }, { "epoch": 0.0336, "grad_norm": 17.404312133789062, "learning_rate": 4.994542905801323e-06, "loss": 12.0405, "step": 21 }, { "epoch": 0.0352, "grad_norm": 17.553056716918945, "learning_rate": 4.993671430357788e-06, "loss": 11.9337, "step": 22 }, { "epoch": 0.0368, "grad_norm": 17.339885711669922, "learning_rate": 4.9927355140895775e-06, "loss": 11.9247, "step": 23 }, { "epoch": 0.0384, "grad_norm": 16.14508056640625, "learning_rate": 4.991735181182401e-06, "loss": 11.5418, "step": 24 }, { "epoch": 0.04, "grad_norm": 14.626124382019043, "learning_rate": 4.9906704574866105e-06, "loss": 11.4515, "step": 25 }, { "epoch": 0.0416, "grad_norm": 17.168630599975586, "learning_rate": 4.989541370516523e-06, "loss": 11.9094, "step": 26 }, { "epoch": 0.0432, "grad_norm": 15.818598747253418, "learning_rate": 4.98834794944972e-06, "loss": 11.7249, "step": 27 }, { "epoch": 0.0448, "grad_norm": 15.550960540771484, "learning_rate": 4.987090225126285e-06, "loss": 11.3948, "step": 28 }, { "epoch": 0.0464, "grad_norm": 15.328129768371582, "learning_rate": 4.985768230048011e-06, "loss": 11.3551, "step": 29 }, { "epoch": 0.048, "grad_norm": 13.792865753173828, "learning_rate": 4.9843819983775575e-06, "loss": 11.1959, "step": 30 }, { "epoch": 0.0496, "grad_norm": 15.154494285583496, "learning_rate": 4.982931565937575e-06, "loss": 11.7186, "step": 31 }, { "epoch": 0.0512, "grad_norm": 14.210274696350098, "learning_rate": 4.98141697020977e-06, "loss": 11.3324, "step": 32 }, { "epoch": 0.0528, "grad_norm": 14.419412612915039, "learning_rate": 4.979838250333941e-06, "loss": 11.0964, "step": 33 }, { "epoch": 0.0544, "grad_norm": 14.476765632629395, "learning_rate": 4.978195447106965e-06, "loss": 11.4052, "step": 34 }, { "epoch": 0.056, "grad_norm": 13.166458129882812, "learning_rate": 4.976488602981748e-06, "loss": 11.1172, "step": 35 }, { "epoch": 0.0576, "grad_norm": 13.77320384979248, "learning_rate": 4.974717762066123e-06, "loss": 11.2174, "step": 36 }, { "epoch": 0.0592, "grad_norm": 13.610458374023438, "learning_rate": 4.972882970121711e-06, "loss": 11.0993, "step": 37 }, { "epoch": 0.0608, "grad_norm": 13.38510513305664, "learning_rate": 4.970984274562741e-06, "loss": 11.0244, "step": 38 }, { "epoch": 0.0624, "grad_norm": 13.513715744018555, "learning_rate": 4.969021724454821e-06, "loss": 11.0893, "step": 39 }, { "epoch": 0.064, "grad_norm": 12.476004600524902, "learning_rate": 4.966995370513675e-06, "loss": 10.9256, "step": 40 }, { "epoch": 0.0656, "grad_norm": 13.007659912109375, "learning_rate": 4.9649052651038255e-06, "loss": 10.897, "step": 41 }, { "epoch": 0.0672, "grad_norm": 12.74197006225586, "learning_rate": 4.962751462237248e-06, "loss": 10.9702, "step": 42 }, { "epoch": 0.0688, "grad_norm": 11.668892860412598, "learning_rate": 4.9605340175719686e-06, "loss": 10.6871, "step": 43 }, { "epoch": 0.0704, "grad_norm": 12.722009658813477, "learning_rate": 4.958252988410631e-06, "loss": 10.7933, "step": 44 }, { "epoch": 0.072, "grad_norm": 10.594651222229004, "learning_rate": 4.955908433699013e-06, "loss": 10.2903, "step": 45 }, { "epoch": 0.0736, "grad_norm": 12.946322441101074, "learning_rate": 4.9535004140245005e-06, "loss": 11.141, "step": 46 }, { "epoch": 0.0752, "grad_norm": 12.783811569213867, "learning_rate": 4.9510289916145295e-06, "loss": 10.779, "step": 47 }, { "epoch": 0.0768, "grad_norm": 11.354564666748047, "learning_rate": 4.94849423033497e-06, "loss": 10.5837, "step": 48 }, { "epoch": 0.0784, "grad_norm": 11.848569869995117, "learning_rate": 4.94589619568848e-06, "loss": 10.5706, "step": 49 }, { "epoch": 0.08, "grad_norm": 9.897051811218262, "learning_rate": 4.943234954812812e-06, "loss": 10.2364, "step": 50 }, { "epoch": 0.0816, "grad_norm": 11.316352844238281, "learning_rate": 4.940510576479079e-06, "loss": 10.6149, "step": 51 }, { "epoch": 0.0832, "grad_norm": 11.829602241516113, "learning_rate": 4.937723131089974e-06, "loss": 10.5496, "step": 52 }, { "epoch": 0.0848, "grad_norm": 10.069260597229004, "learning_rate": 4.934872690677953e-06, "loss": 10.0925, "step": 53 }, { "epoch": 0.0864, "grad_norm": 11.005655288696289, "learning_rate": 4.931959328903376e-06, "loss": 10.3874, "step": 54 }, { "epoch": 0.088, "grad_norm": 10.913771629333496, "learning_rate": 4.928983121052597e-06, "loss": 10.3699, "step": 55 }, { "epoch": 0.0896, "grad_norm": 10.943140983581543, "learning_rate": 4.925944144036027e-06, "loss": 10.3604, "step": 56 }, { "epoch": 0.0912, "grad_norm": 11.520155906677246, "learning_rate": 4.922842476386137e-06, "loss": 10.45, "step": 57 }, { "epoch": 0.0928, "grad_norm": 11.597639083862305, "learning_rate": 4.919678198255438e-06, "loss": 10.6551, "step": 58 }, { "epoch": 0.0944, "grad_norm": 11.26528549194336, "learning_rate": 4.9164513914144005e-06, "loss": 10.3729, "step": 59 }, { "epoch": 0.096, "grad_norm": 11.043292045593262, "learning_rate": 4.91316213924935e-06, "loss": 10.2723, "step": 60 }, { "epoch": 0.0976, "grad_norm": 10.670892715454102, "learning_rate": 4.909810526760307e-06, "loss": 10.3842, "step": 61 }, { "epoch": 0.0992, "grad_norm": 12.231328010559082, "learning_rate": 4.90639664055879e-06, "loss": 10.4897, "step": 62 }, { "epoch": 0.1008, "grad_norm": 10.968878746032715, "learning_rate": 4.902920568865582e-06, "loss": 10.225, "step": 63 }, { "epoch": 0.1024, "grad_norm": 10.761625289916992, "learning_rate": 4.899382401508446e-06, "loss": 10.0817, "step": 64 }, { "epoch": 0.104, "grad_norm": 9.868699073791504, "learning_rate": 4.8957822299198045e-06, "loss": 9.9514, "step": 65 }, { "epoch": 0.1056, "grad_norm": 10.76175308227539, "learning_rate": 4.892120147134378e-06, "loss": 10.2281, "step": 66 }, { "epoch": 0.1072, "grad_norm": 10.531647682189941, "learning_rate": 4.888396247786784e-06, "loss": 10.0424, "step": 67 }, { "epoch": 0.1088, "grad_norm": 9.720768928527832, "learning_rate": 4.884610628109082e-06, "loss": 9.8735, "step": 68 }, { "epoch": 0.1104, "grad_norm": 10.765035629272461, "learning_rate": 4.880763385928298e-06, "loss": 10.1977, "step": 69 }, { "epoch": 0.112, "grad_norm": 10.57542896270752, "learning_rate": 4.876854620663887e-06, "loss": 9.9432, "step": 70 }, { "epoch": 0.1136, "grad_norm": 10.321698188781738, "learning_rate": 4.872884433325169e-06, "loss": 9.9563, "step": 71 }, { "epoch": 0.1152, "grad_norm": 10.044979095458984, "learning_rate": 4.868852926508721e-06, "loss": 9.9412, "step": 72 }, { "epoch": 0.1168, "grad_norm": 10.604913711547852, "learning_rate": 4.864760204395717e-06, "loss": 10.0144, "step": 73 }, { "epoch": 0.1184, "grad_norm": 9.378023147583008, "learning_rate": 4.860606372749247e-06, "loss": 9.8055, "step": 74 }, { "epoch": 0.12, "grad_norm": 9.08212947845459, "learning_rate": 4.856391538911572e-06, "loss": 9.7179, "step": 75 }, { "epoch": 0.1216, "grad_norm": 10.120437622070312, "learning_rate": 4.8521158118013605e-06, "loss": 9.7055, "step": 76 }, { "epoch": 0.1232, "grad_norm": 9.448174476623535, "learning_rate": 4.847779301910868e-06, "loss": 9.7753, "step": 77 }, { "epoch": 0.1248, "grad_norm": 9.994352340698242, "learning_rate": 4.843382121303082e-06, "loss": 9.8005, "step": 78 }, { "epoch": 0.1264, "grad_norm": 10.175590515136719, "learning_rate": 4.83892438360883e-06, "loss": 9.7149, "step": 79 }, { "epoch": 0.128, "grad_norm": 9.187248229980469, "learning_rate": 4.83440620402384e-06, "loss": 9.5077, "step": 80 }, { "epoch": 0.1296, "grad_norm": 8.287508964538574, "learning_rate": 4.829827699305759e-06, "loss": 9.2745, "step": 81 }, { "epoch": 0.1312, "grad_norm": 9.502992630004883, "learning_rate": 4.825188987771149e-06, "loss": 9.7212, "step": 82 }, { "epoch": 0.1328, "grad_norm": 9.398665428161621, "learning_rate": 4.820490189292415e-06, "loss": 9.4711, "step": 83 }, { "epoch": 0.1344, "grad_norm": 9.67027473449707, "learning_rate": 4.815731425294716e-06, "loss": 9.6444, "step": 84 }, { "epoch": 0.136, "grad_norm": 9.999480247497559, "learning_rate": 4.810912818752825e-06, "loss": 9.6473, "step": 85 }, { "epoch": 0.1376, "grad_norm": 10.192490577697754, "learning_rate": 4.806034494187949e-06, "loss": 9.5, "step": 86 }, { "epoch": 0.1392, "grad_norm": 10.132280349731445, "learning_rate": 4.8010965776645145e-06, "loss": 9.5879, "step": 87 }, { "epoch": 0.1408, "grad_norm": 10.07225227355957, "learning_rate": 4.796099196786908e-06, "loss": 9.4842, "step": 88 }, { "epoch": 0.1424, "grad_norm": 9.903701782226562, "learning_rate": 4.791042480696179e-06, "loss": 9.5136, "step": 89 }, { "epoch": 0.144, "grad_norm": 9.270772933959961, "learning_rate": 4.785926560066703e-06, "loss": 9.367, "step": 90 }, { "epoch": 0.1456, "grad_norm": 8.604142189025879, "learning_rate": 4.780751567102801e-06, "loss": 9.1618, "step": 91 }, { "epoch": 0.1472, "grad_norm": 9.69423770904541, "learning_rate": 4.775517635535332e-06, "loss": 9.2597, "step": 92 }, { "epoch": 0.1488, "grad_norm": 10.679227828979492, "learning_rate": 4.770224900618226e-06, "loss": 9.3722, "step": 93 }, { "epoch": 0.1504, "grad_norm": 9.498805046081543, "learning_rate": 4.764873499124997e-06, "loss": 9.2149, "step": 94 }, { "epoch": 0.152, "grad_norm": 10.133721351623535, "learning_rate": 4.759463569345205e-06, "loss": 9.211, "step": 95 }, { "epoch": 0.1536, "grad_norm": 10.703787803649902, "learning_rate": 4.753995251080884e-06, "loss": 9.2456, "step": 96 }, { "epoch": 0.1552, "grad_norm": 9.839086532592773, "learning_rate": 4.748468685642926e-06, "loss": 9.0973, "step": 97 }, { "epoch": 0.1568, "grad_norm": 8.186079978942871, "learning_rate": 4.742884015847436e-06, "loss": 8.9378, "step": 98 }, { "epoch": 0.1584, "grad_norm": 9.491665840148926, "learning_rate": 4.737241386012032e-06, "loss": 9.0209, "step": 99 }, { "epoch": 0.16, "grad_norm": 9.313272476196289, "learning_rate": 4.731540941952126e-06, "loss": 9.0591, "step": 100 }, { "epoch": 0.1616, "grad_norm": 9.365504264831543, "learning_rate": 4.725782830977145e-06, "loss": 9.0187, "step": 101 }, { "epoch": 0.1632, "grad_norm": 9.761168479919434, "learning_rate": 4.719967201886734e-06, "loss": 8.9663, "step": 102 }, { "epoch": 0.1648, "grad_norm": 10.886737823486328, "learning_rate": 4.714094204966903e-06, "loss": 9.0523, "step": 103 }, { "epoch": 0.1664, "grad_norm": 11.529026985168457, "learning_rate": 4.708163991986152e-06, "loss": 8.9862, "step": 104 }, { "epoch": 0.168, "grad_norm": 11.003949165344238, "learning_rate": 4.702176716191539e-06, "loss": 8.9944, "step": 105 }, { "epoch": 0.1696, "grad_norm": 10.637957572937012, "learning_rate": 4.696132532304727e-06, "loss": 8.7661, "step": 106 }, { "epoch": 0.1712, "grad_norm": 10.600850105285645, "learning_rate": 4.690031596517984e-06, "loss": 8.6939, "step": 107 }, { "epoch": 0.1728, "grad_norm": 10.38036823272705, "learning_rate": 4.683874066490143e-06, "loss": 8.8789, "step": 108 }, { "epoch": 0.1744, "grad_norm": 10.32800006866455, "learning_rate": 4.677660101342536e-06, "loss": 8.7128, "step": 109 }, { "epoch": 0.176, "grad_norm": 9.01140022277832, "learning_rate": 4.671389861654873e-06, "loss": 8.5539, "step": 110 }, { "epoch": 0.1776, "grad_norm": 10.66911792755127, "learning_rate": 4.665063509461098e-06, "loss": 8.6381, "step": 111 }, { "epoch": 0.1792, "grad_norm": 12.453883171081543, "learning_rate": 4.658681208245198e-06, "loss": 8.744, "step": 112 }, { "epoch": 0.1808, "grad_norm": 10.25079345703125, "learning_rate": 4.652243122936987e-06, "loss": 8.4376, "step": 113 }, { "epoch": 0.1824, "grad_norm": 13.820728302001953, "learning_rate": 4.645749419907829e-06, "loss": 8.7434, "step": 114 }, { "epoch": 0.184, "grad_norm": 9.763056755065918, "learning_rate": 4.639200266966351e-06, "loss": 8.5522, "step": 115 }, { "epoch": 0.1856, "grad_norm": 12.80479907989502, "learning_rate": 4.632595833354105e-06, "loss": 8.5777, "step": 116 }, { "epoch": 0.1872, "grad_norm": 11.518301963806152, "learning_rate": 4.625936289741187e-06, "loss": 8.2751, "step": 117 }, { "epoch": 0.1888, "grad_norm": 13.24626350402832, "learning_rate": 4.619221808221833e-06, "loss": 8.4951, "step": 118 }, { "epoch": 0.1904, "grad_norm": 14.117487907409668, "learning_rate": 4.612452562309975e-06, "loss": 8.3492, "step": 119 }, { "epoch": 0.192, "grad_norm": 12.98033618927002, "learning_rate": 4.605628726934747e-06, "loss": 8.2238, "step": 120 }, { "epoch": 0.1936, "grad_norm": 11.61721420288086, "learning_rate": 4.598750478435973e-06, "loss": 8.2197, "step": 121 }, { "epoch": 0.1952, "grad_norm": 12.619826316833496, "learning_rate": 4.5918179945596055e-06, "loss": 8.2005, "step": 122 }, { "epoch": 0.1968, "grad_norm": 11.586774826049805, "learning_rate": 4.584831454453135e-06, "loss": 8.0181, "step": 123 }, { "epoch": 0.1984, "grad_norm": 11.792032241821289, "learning_rate": 4.577791038660959e-06, "loss": 8.1414, "step": 124 }, { "epoch": 0.2, "grad_norm": 14.116670608520508, "learning_rate": 4.570696929119717e-06, "loss": 7.9288, "step": 125 }, { "epoch": 0.2016, "grad_norm": 13.249540328979492, "learning_rate": 4.563549309153589e-06, "loss": 7.8991, "step": 126 }, { "epoch": 0.2032, "grad_norm": 13.10855770111084, "learning_rate": 4.556348363469556e-06, "loss": 7.7997, "step": 127 }, { "epoch": 0.2048, "grad_norm": 13.13003921508789, "learning_rate": 4.549094278152631e-06, "loss": 7.7856, "step": 128 }, { "epoch": 0.2064, "grad_norm": 11.22130012512207, "learning_rate": 4.541787240661049e-06, "loss": 7.8092, "step": 129 }, { "epoch": 0.208, "grad_norm": 12.641518592834473, "learning_rate": 4.534427439821416e-06, "loss": 7.6641, "step": 130 }, { "epoch": 0.2096, "grad_norm": 12.413702964782715, "learning_rate": 4.527015065823841e-06, "loss": 7.6125, "step": 131 }, { "epoch": 0.2112, "grad_norm": 12.156352043151855, "learning_rate": 4.519550310217013e-06, "loss": 7.5519, "step": 132 }, { "epoch": 0.2128, "grad_norm": 11.665326118469238, "learning_rate": 4.512033365903251e-06, "loss": 7.5902, "step": 133 }, { "epoch": 0.2144, "grad_norm": 12.924529075622559, "learning_rate": 4.504464427133527e-06, "loss": 7.5706, "step": 134 }, { "epoch": 0.216, "grad_norm": 15.648908615112305, "learning_rate": 4.496843689502435e-06, "loss": 7.3488, "step": 135 }, { "epoch": 0.2176, "grad_norm": 13.633544921875, "learning_rate": 4.489171349943144e-06, "loss": 7.2841, "step": 136 }, { "epoch": 0.2192, "grad_norm": 14.129197120666504, "learning_rate": 4.481447606722309e-06, "loss": 7.2605, "step": 137 }, { "epoch": 0.2208, "grad_norm": 15.414569854736328, "learning_rate": 4.473672659434941e-06, "loss": 7.1375, "step": 138 }, { "epoch": 0.2224, "grad_norm": 15.15605640411377, "learning_rate": 4.465846708999258e-06, "loss": 7.3157, "step": 139 }, { "epoch": 0.224, "grad_norm": 13.083776473999023, "learning_rate": 4.457969957651485e-06, "loss": 7.1391, "step": 140 }, { "epoch": 0.2256, "grad_norm": 14.658546447753906, "learning_rate": 4.450042608940632e-06, "loss": 6.8354, "step": 141 }, { "epoch": 0.2272, "grad_norm": 13.068192481994629, "learning_rate": 4.442064867723236e-06, "loss": 6.9534, "step": 142 }, { "epoch": 0.2288, "grad_norm": 13.683319091796875, "learning_rate": 4.434036940158062e-06, "loss": 6.7263, "step": 143 }, { "epoch": 0.2304, "grad_norm": 12.352782249450684, "learning_rate": 4.425959033700776e-06, "loss": 6.9508, "step": 144 }, { "epoch": 0.232, "grad_norm": 12.934060096740723, "learning_rate": 4.417831357098591e-06, "loss": 6.7608, "step": 145 }, { "epoch": 0.2336, "grad_norm": 10.694926261901855, "learning_rate": 4.409654120384863e-06, "loss": 6.9133, "step": 146 }, { "epoch": 0.2352, "grad_norm": 13.42801570892334, "learning_rate": 4.401427534873669e-06, "loss": 6.2184, "step": 147 }, { "epoch": 0.2368, "grad_norm": 12.629581451416016, "learning_rate": 4.393151813154345e-06, "loss": 6.1405, "step": 148 }, { "epoch": 0.2384, "grad_norm": 9.909472465515137, "learning_rate": 4.384827169085993e-06, "loss": 6.376, "step": 149 }, { "epoch": 0.24, "grad_norm": 9.083218574523926, "learning_rate": 4.3764538177919555e-06, "loss": 6.387, "step": 150 }, { "epoch": 0.2416, "grad_norm": 8.383381843566895, "learning_rate": 4.3680319756542525e-06, "loss": 6.7282, "step": 151 }, { "epoch": 0.2432, "grad_norm": 8.961660385131836, "learning_rate": 4.35956186030799e-06, "loss": 6.2623, "step": 152 }, { "epoch": 0.2448, "grad_norm": 9.286286354064941, "learning_rate": 4.351043690635744e-06, "loss": 6.0499, "step": 153 }, { "epoch": 0.2464, "grad_norm": 9.719377517700195, "learning_rate": 4.3424776867618935e-06, "loss": 6.4369, "step": 154 }, { "epoch": 0.248, "grad_norm": 7.7872700691223145, "learning_rate": 4.333864070046938e-06, "loss": 6.0176, "step": 155 }, { "epoch": 0.2496, "grad_norm": 8.78665828704834, "learning_rate": 4.325203063081776e-06, "loss": 6.0201, "step": 156 }, { "epoch": 0.2512, "grad_norm": 7.898557186126709, "learning_rate": 4.3164948896819535e-06, "loss": 6.1595, "step": 157 }, { "epoch": 0.2528, "grad_norm": 9.21320629119873, "learning_rate": 4.307739774881878e-06, "loss": 6.3917, "step": 158 }, { "epoch": 0.2544, "grad_norm": 6.031705379486084, "learning_rate": 4.298937944929007e-06, "loss": 5.6134, "step": 159 }, { "epoch": 0.256, "grad_norm": 7.0851006507873535, "learning_rate": 4.290089627277998e-06, "loss": 5.4909, "step": 160 }, { "epoch": 0.2576, "grad_norm": 7.172662258148193, "learning_rate": 4.28119505058483e-06, "loss": 6.1213, "step": 161 }, { "epoch": 0.2592, "grad_norm": 7.241125583648682, "learning_rate": 4.2722544447008995e-06, "loss": 5.9029, "step": 162 }, { "epoch": 0.2608, "grad_norm": 6.174571514129639, "learning_rate": 4.263268040667075e-06, "loss": 5.9515, "step": 163 }, { "epoch": 0.2624, "grad_norm": 5.6988935470581055, "learning_rate": 4.254236070707734e-06, "loss": 5.8603, "step": 164 }, { "epoch": 0.264, "grad_norm": 5.242663383483887, "learning_rate": 4.245158768224748e-06, "loss": 5.6214, "step": 165 }, { "epoch": 0.2656, "grad_norm": 5.694828987121582, "learning_rate": 4.236036367791471e-06, "loss": 6.3081, "step": 166 }, { "epoch": 0.2672, "grad_norm": 7.1838788986206055, "learning_rate": 4.226869105146658e-06, "loss": 5.4577, "step": 167 }, { "epoch": 0.2688, "grad_norm": 8.755837440490723, "learning_rate": 4.2176572171883865e-06, "loss": 5.5286, "step": 168 }, { "epoch": 0.2704, "grad_norm": 4.821361064910889, "learning_rate": 4.208400941967928e-06, "loss": 5.8776, "step": 169 }, { "epoch": 0.272, "grad_norm": 5.043092250823975, "learning_rate": 4.199100518683601e-06, "loss": 5.6913, "step": 170 }, { "epoch": 0.2736, "grad_norm": 5.266634941101074, "learning_rate": 4.189756187674584e-06, "loss": 5.8228, "step": 171 }, { "epoch": 0.2752, "grad_norm": 5.798868179321289, "learning_rate": 4.18036819041471e-06, "loss": 5.6908, "step": 172 }, { "epoch": 0.2768, "grad_norm": 5.337583065032959, "learning_rate": 4.170936769506222e-06, "loss": 6.0907, "step": 173 }, { "epoch": 0.2784, "grad_norm": 4.3411102294921875, "learning_rate": 4.161462168673508e-06, "loss": 5.8087, "step": 174 }, { "epoch": 0.28, "grad_norm": 6.649768829345703, "learning_rate": 4.1519446327567995e-06, "loss": 5.2901, "step": 175 }, { "epoch": 0.2816, "grad_norm": 6.4602556228637695, "learning_rate": 4.142384407705846e-06, "loss": 5.274, "step": 176 }, { "epoch": 0.2832, "grad_norm": 5.464128017425537, "learning_rate": 4.132781740573559e-06, "loss": 6.0373, "step": 177 }, { "epoch": 0.2848, "grad_norm": 6.308886528015137, "learning_rate": 4.123136879509626e-06, "loss": 5.2471, "step": 178 }, { "epoch": 0.2864, "grad_norm": 4.4718828201293945, "learning_rate": 4.1134500737541026e-06, "loss": 5.3702, "step": 179 }, { "epoch": 0.288, "grad_norm": 3.863276958465576, "learning_rate": 4.103721573630965e-06, "loss": 5.3922, "step": 180 }, { "epoch": 0.2896, "grad_norm": 4.226170063018799, "learning_rate": 4.093951630541646e-06, "loss": 5.4302, "step": 181 }, { "epoch": 0.2912, "grad_norm": 3.5398764610290527, "learning_rate": 4.084140496958539e-06, "loss": 5.3444, "step": 182 }, { "epoch": 0.2928, "grad_norm": 3.5163183212280273, "learning_rate": 4.074288426418467e-06, "loss": 5.3247, "step": 183 }, { "epoch": 0.2944, "grad_norm": 5.308356761932373, "learning_rate": 4.06439567351614e-06, "loss": 5.6837, "step": 184 }, { "epoch": 0.296, "grad_norm": 3.6820993423461914, "learning_rate": 4.054462493897569e-06, "loss": 5.1638, "step": 185 }, { "epoch": 0.2976, "grad_norm": 3.9401638507843018, "learning_rate": 4.0444891442534615e-06, "loss": 5.498, "step": 186 }, { "epoch": 0.2992, "grad_norm": 5.141748428344727, "learning_rate": 4.034475882312593e-06, "loss": 5.1034, "step": 187 }, { "epoch": 0.3008, "grad_norm": 3.4670636653900146, "learning_rate": 4.024422966835137e-06, "loss": 5.2071, "step": 188 }, { "epoch": 0.3024, "grad_norm": 3.7121994495391846, "learning_rate": 4.014330657605984e-06, "loss": 5.3885, "step": 189 }, { "epoch": 0.304, "grad_norm": 5.863914489746094, "learning_rate": 4.004199215428032e-06, "loss": 5.5361, "step": 190 }, { "epoch": 0.3056, "grad_norm": 3.343780517578125, "learning_rate": 3.994028902115439e-06, "loss": 5.4439, "step": 191 }, { "epoch": 0.3072, "grad_norm": 4.041346073150635, "learning_rate": 3.9838199804868635e-06, "loss": 5.6031, "step": 192 }, { "epoch": 0.3088, "grad_norm": 2.9033005237579346, "learning_rate": 3.973572714358668e-06, "loss": 5.3807, "step": 193 }, { "epoch": 0.3104, "grad_norm": 3.026655435562134, "learning_rate": 3.963287368538105e-06, "loss": 5.6681, "step": 194 }, { "epoch": 0.312, "grad_norm": 5.9403862953186035, "learning_rate": 3.9529642088164736e-06, "loss": 5.1567, "step": 195 }, { "epoch": 0.3136, "grad_norm": 4.5110883712768555, "learning_rate": 3.942603501962249e-06, "loss": 5.3055, "step": 196 }, { "epoch": 0.3152, "grad_norm": 4.24874210357666, "learning_rate": 3.932205515714189e-06, "loss": 5.3806, "step": 197 }, { "epoch": 0.3168, "grad_norm": 4.06620979309082, "learning_rate": 3.92177051877442e-06, "loss": 5.5074, "step": 198 }, { "epoch": 0.3184, "grad_norm": 3.4436845779418945, "learning_rate": 3.9112987808014824e-06, "loss": 5.3936, "step": 199 }, { "epoch": 0.32, "grad_norm": 3.5736324787139893, "learning_rate": 3.900790572403376e-06, "loss": 5.3905, "step": 200 } ], "logging_steps": 1, "max_steps": 625, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.40264337309696e+16, "train_batch_size": 16, "trial_name": null, "trial_params": null }