{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 230, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008695652173913044, "grad_norm": 18.15669822692871, "learning_rate": 0.0, "loss": 4.5989, "step": 1 }, { "epoch": 0.017391304347826087, "grad_norm": 19.82965087890625, "learning_rate": 1e-05, "loss": 4.7595, "step": 2 }, { "epoch": 0.02608695652173913, "grad_norm": 18.204021453857422, "learning_rate": 2e-05, "loss": 4.5244, "step": 3 }, { "epoch": 0.034782608695652174, "grad_norm": 29.440780639648438, "learning_rate": 3e-05, "loss": 5.3648, "step": 4 }, { "epoch": 0.043478260869565216, "grad_norm": 16.630733489990234, "learning_rate": 4e-05, "loss": 4.8256, "step": 5 }, { "epoch": 0.05217391304347826, "grad_norm": 14.301246643066406, "learning_rate": 5e-05, "loss": 3.6577, "step": 6 }, { "epoch": 0.06086956521739131, "grad_norm": 15.203990936279297, "learning_rate": 6e-05, "loss": 3.7917, "step": 7 }, { "epoch": 0.06956521739130435, "grad_norm": 15.369929313659668, "learning_rate": 7e-05, "loss": 4.048, "step": 8 }, { "epoch": 0.0782608695652174, "grad_norm": 14.635960578918457, "learning_rate": 8e-05, "loss": 3.9196, "step": 9 }, { "epoch": 0.08695652173913043, "grad_norm": 25.854639053344727, "learning_rate": 9e-05, "loss": 4.3504, "step": 10 }, { "epoch": 0.09565217391304348, "grad_norm": 10.977479934692383, "learning_rate": 0.0001, "loss": 2.5819, "step": 11 }, { "epoch": 0.10434782608695652, "grad_norm": 9.749446868896484, "learning_rate": 9.999490215047167e-05, "loss": 2.165, "step": 12 }, { "epoch": 0.11304347826086956, "grad_norm": 12.812524795532227, "learning_rate": 9.997960964140947e-05, "loss": 2.5085, "step": 13 }, { "epoch": 0.12173913043478261, "grad_norm": 11.711141586303711, "learning_rate": 9.995412559116979e-05, "loss": 2.7094, "step": 14 }, { "epoch": 0.13043478260869565, "grad_norm": 14.878225326538086, "learning_rate": 9.991845519630678e-05, "loss": 3.0107, "step": 15 }, { "epoch": 0.1391304347826087, "grad_norm": 11.596781730651855, "learning_rate": 9.987260573051269e-05, "loss": 1.996, "step": 16 }, { "epoch": 0.14782608695652175, "grad_norm": 10.746283531188965, "learning_rate": 9.981658654313457e-05, "loss": 2.2152, "step": 17 }, { "epoch": 0.1565217391304348, "grad_norm": 10.082755088806152, "learning_rate": 9.975040905726798e-05, "loss": 1.384, "step": 18 }, { "epoch": 0.16521739130434782, "grad_norm": 9.694713592529297, "learning_rate": 9.967408676742751e-05, "loss": 1.8851, "step": 19 }, { "epoch": 0.17391304347826086, "grad_norm": 11.335524559020996, "learning_rate": 9.958763523679514e-05, "loss": 1.9028, "step": 20 }, { "epoch": 0.1826086956521739, "grad_norm": 13.664958953857422, "learning_rate": 9.949107209404665e-05, "loss": 1.4538, "step": 21 }, { "epoch": 0.19130434782608696, "grad_norm": 13.078099250793457, "learning_rate": 9.938441702975689e-05, "loss": 2.5061, "step": 22 }, { "epoch": 0.2, "grad_norm": 8.856505393981934, "learning_rate": 9.926769179238466e-05, "loss": 1.1623, "step": 23 }, { "epoch": 0.20869565217391303, "grad_norm": 10.897032737731934, "learning_rate": 9.914092018383778e-05, "loss": 1.6242, "step": 24 }, { "epoch": 0.21739130434782608, "grad_norm": 10.83500862121582, "learning_rate": 9.900412805461967e-05, "loss": 1.9913, "step": 25 }, { "epoch": 0.22608695652173913, "grad_norm": 8.87816333770752, "learning_rate": 9.885734329855798e-05, "loss": 1.8755, "step": 26 }, { "epoch": 0.23478260869565218, "grad_norm": 14.880556106567383, "learning_rate": 9.870059584711668e-05, "loss": 1.005, "step": 27 }, { "epoch": 0.24347826086956523, "grad_norm": 11.756641387939453, "learning_rate": 9.853391766329263e-05, "loss": 1.9287, "step": 28 }, { "epoch": 0.25217391304347825, "grad_norm": 11.141681671142578, "learning_rate": 9.835734273509786e-05, "loss": 1.7336, "step": 29 }, { "epoch": 0.2608695652173913, "grad_norm": 8.97098159790039, "learning_rate": 9.817090706862895e-05, "loss": 1.1737, "step": 30 }, { "epoch": 0.26956521739130435, "grad_norm": 12.16342544555664, "learning_rate": 9.797464868072488e-05, "loss": 3.3643, "step": 31 }, { "epoch": 0.2782608695652174, "grad_norm": 15.482931137084961, "learning_rate": 9.776860759121484e-05, "loss": 2.0722, "step": 32 }, { "epoch": 0.28695652173913044, "grad_norm": 8.24347972869873, "learning_rate": 9.755282581475769e-05, "loss": 1.2189, "step": 33 }, { "epoch": 0.2956521739130435, "grad_norm": 9.246153831481934, "learning_rate": 9.73273473522745e-05, "loss": 1.295, "step": 34 }, { "epoch": 0.30434782608695654, "grad_norm": 13.356026649475098, "learning_rate": 9.709221818197624e-05, "loss": 1.6265, "step": 35 }, { "epoch": 0.3130434782608696, "grad_norm": 9.574901580810547, "learning_rate": 9.68474862499881e-05, "loss": 1.1326, "step": 36 }, { "epoch": 0.3217391304347826, "grad_norm": 15.934743881225586, "learning_rate": 9.659320146057262e-05, "loss": 1.5065, "step": 37 }, { "epoch": 0.33043478260869563, "grad_norm": 9.842390060424805, "learning_rate": 9.632941566595357e-05, "loss": 1.3366, "step": 38 }, { "epoch": 0.3391304347826087, "grad_norm": 12.335067749023438, "learning_rate": 9.60561826557425e-05, "loss": 0.7185, "step": 39 }, { "epoch": 0.34782608695652173, "grad_norm": 12.821420669555664, "learning_rate": 9.577355814597031e-05, "loss": 2.171, "step": 40 }, { "epoch": 0.3565217391304348, "grad_norm": 6.9211745262146, "learning_rate": 9.548159976772592e-05, "loss": 0.4694, "step": 41 }, { "epoch": 0.3652173913043478, "grad_norm": 10.683237075805664, "learning_rate": 9.518036705540458e-05, "loss": 1.688, "step": 42 }, { "epoch": 0.3739130434782609, "grad_norm": 13.161890983581543, "learning_rate": 9.486992143456792e-05, "loss": 0.8145, "step": 43 }, { "epoch": 0.3826086956521739, "grad_norm": 8.92729377746582, "learning_rate": 9.45503262094184e-05, "loss": 1.4569, "step": 44 }, { "epoch": 0.391304347826087, "grad_norm": 7.679493427276611, "learning_rate": 9.422164654989072e-05, "loss": 1.0301, "step": 45 }, { "epoch": 0.4, "grad_norm": 9.197248458862305, "learning_rate": 9.388394947836279e-05, "loss": 1.125, "step": 46 }, { "epoch": 0.40869565217391307, "grad_norm": 8.750134468078613, "learning_rate": 9.353730385598887e-05, "loss": 0.9901, "step": 47 }, { "epoch": 0.41739130434782606, "grad_norm": 8.447084426879883, "learning_rate": 9.318178036865785e-05, "loss": 0.2989, "step": 48 }, { "epoch": 0.4260869565217391, "grad_norm": 6.760093688964844, "learning_rate": 9.281745151257946e-05, "loss": 0.6226, "step": 49 }, { "epoch": 0.43478260869565216, "grad_norm": 12.86007022857666, "learning_rate": 9.244439157950114e-05, "loss": 1.6501, "step": 50 }, { "epoch": 0.4434782608695652, "grad_norm": 7.0637125968933105, "learning_rate": 9.206267664155907e-05, "loss": 0.8073, "step": 51 }, { "epoch": 0.45217391304347826, "grad_norm": 8.347302436828613, "learning_rate": 9.167238453576589e-05, "loss": 0.8773, "step": 52 }, { "epoch": 0.4608695652173913, "grad_norm": 12.007081031799316, "learning_rate": 9.12735948481387e-05, "loss": 1.7717, "step": 53 }, { "epoch": 0.46956521739130436, "grad_norm": 8.299239158630371, "learning_rate": 9.086638889747035e-05, "loss": 1.1201, "step": 54 }, { "epoch": 0.4782608695652174, "grad_norm": 9.381499290466309, "learning_rate": 9.045084971874738e-05, "loss": 0.8098, "step": 55 }, { "epoch": 0.48695652173913045, "grad_norm": 8.82516860961914, "learning_rate": 9.002706204621803e-05, "loss": 1.2713, "step": 56 }, { "epoch": 0.4956521739130435, "grad_norm": 12.698591232299805, "learning_rate": 8.959511229611376e-05, "loss": 1.4672, "step": 57 }, { "epoch": 0.5043478260869565, "grad_norm": 10.124267578125, "learning_rate": 8.915508854902778e-05, "loss": 0.7497, "step": 58 }, { "epoch": 0.5130434782608696, "grad_norm": 10.243094444274902, "learning_rate": 8.870708053195413e-05, "loss": 1.0571, "step": 59 }, { "epoch": 0.5217391304347826, "grad_norm": 15.050994873046875, "learning_rate": 8.825117959999116e-05, "loss": 1.1001, "step": 60 }, { "epoch": 0.5304347826086957, "grad_norm": 15.316854476928711, "learning_rate": 8.778747871771292e-05, "loss": 0.784, "step": 61 }, { "epoch": 0.5391304347826087, "grad_norm": 3.280144214630127, "learning_rate": 8.731607244021236e-05, "loss": 0.0856, "step": 62 }, { "epoch": 0.5478260869565217, "grad_norm": 8.658632278442383, "learning_rate": 8.683705689382024e-05, "loss": 1.2149, "step": 63 }, { "epoch": 0.5565217391304348, "grad_norm": 10.066658020019531, "learning_rate": 8.635052975650369e-05, "loss": 1.4377, "step": 64 }, { "epoch": 0.5652173913043478, "grad_norm": 10.947000503540039, "learning_rate": 8.585659023794818e-05, "loss": 1.6525, "step": 65 }, { "epoch": 0.5739130434782609, "grad_norm": 8.52258586883545, "learning_rate": 8.535533905932738e-05, "loss": 1.1801, "step": 66 }, { "epoch": 0.5826086956521739, "grad_norm": 9.919696807861328, "learning_rate": 8.484687843276469e-05, "loss": 1.176, "step": 67 }, { "epoch": 0.591304347826087, "grad_norm": 9.4547700881958, "learning_rate": 8.433131204049067e-05, "loss": 1.0911, "step": 68 }, { "epoch": 0.6, "grad_norm": 14.620793342590332, "learning_rate": 8.380874501370097e-05, "loss": 0.7491, "step": 69 }, { "epoch": 0.6086956521739131, "grad_norm": 7.218148708343506, "learning_rate": 8.327928391111841e-05, "loss": 0.1841, "step": 70 }, { "epoch": 0.6173913043478261, "grad_norm": 12.315970420837402, "learning_rate": 8.274303669726426e-05, "loss": 1.2871, "step": 71 }, { "epoch": 0.6260869565217392, "grad_norm": 12.200401306152344, "learning_rate": 8.220011272044277e-05, "loss": 0.4186, "step": 72 }, { "epoch": 0.6347826086956522, "grad_norm": 7.502784252166748, "learning_rate": 8.165062269044353e-05, "loss": 0.7866, "step": 73 }, { "epoch": 0.6434782608695652, "grad_norm": 8.83882999420166, "learning_rate": 8.109467865596612e-05, "loss": 1.1315, "step": 74 }, { "epoch": 0.6521739130434783, "grad_norm": 17.456348419189453, "learning_rate": 8.053239398177191e-05, "loss": 2.3548, "step": 75 }, { "epoch": 0.6608695652173913, "grad_norm": 12.876847267150879, "learning_rate": 7.996388332556735e-05, "loss": 1.7174, "step": 76 }, { "epoch": 0.6695652173913044, "grad_norm": 10.776142120361328, "learning_rate": 7.938926261462366e-05, "loss": 0.9081, "step": 77 }, { "epoch": 0.6782608695652174, "grad_norm": 14.020254135131836, "learning_rate": 7.880864902213765e-05, "loss": 1.9042, "step": 78 }, { "epoch": 0.6869565217391305, "grad_norm": 8.45417594909668, "learning_rate": 7.822216094333847e-05, "loss": 0.9913, "step": 79 }, { "epoch": 0.6956521739130435, "grad_norm": 13.904030799865723, "learning_rate": 7.762991797134514e-05, "loss": 2.1202, "step": 80 }, { "epoch": 0.7043478260869566, "grad_norm": 7.09511137008667, "learning_rate": 7.703204087277988e-05, "loss": 0.6924, "step": 81 }, { "epoch": 0.7130434782608696, "grad_norm": 10.574461936950684, "learning_rate": 7.64286515631421e-05, "loss": 0.667, "step": 82 }, { "epoch": 0.7217391304347827, "grad_norm": 17.19155502319336, "learning_rate": 7.58198730819481e-05, "loss": 2.4983, "step": 83 }, { "epoch": 0.7304347826086957, "grad_norm": 11.54223346710205, "learning_rate": 7.52058295676416e-05, "loss": 1.8265, "step": 84 }, { "epoch": 0.7391304347826086, "grad_norm": 7.497072219848633, "learning_rate": 7.45866462322802e-05, "loss": 0.9592, "step": 85 }, { "epoch": 0.7478260869565218, "grad_norm": 18.042118072509766, "learning_rate": 7.396244933600285e-05, "loss": 1.2019, "step": 86 }, { "epoch": 0.7565217391304347, "grad_norm": 8.521622657775879, "learning_rate": 7.333336616128369e-05, "loss": 0.9159, "step": 87 }, { "epoch": 0.7652173913043478, "grad_norm": 6.687935829162598, "learning_rate": 7.269952498697734e-05, "loss": 0.7739, "step": 88 }, { "epoch": 0.7739130434782608, "grad_norm": 11.469585418701172, "learning_rate": 7.206105506216106e-05, "loss": 1.5827, "step": 89 }, { "epoch": 0.782608695652174, "grad_norm": 8.240609169006348, "learning_rate": 7.141808657977907e-05, "loss": 1.0337, "step": 90 }, { "epoch": 0.7913043478260869, "grad_norm": 6.628414630889893, "learning_rate": 7.077075065009433e-05, "loss": 0.8117, "step": 91 }, { "epoch": 0.8, "grad_norm": 9.6090087890625, "learning_rate": 7.01191792739534e-05, "loss": 0.9952, "step": 92 }, { "epoch": 0.808695652173913, "grad_norm": 11.751654624938965, "learning_rate": 6.946350531586959e-05, "loss": 0.999, "step": 93 }, { "epoch": 0.8173913043478261, "grad_norm": 9.336933135986328, "learning_rate": 6.880386247692999e-05, "loss": 0.9874, "step": 94 }, { "epoch": 0.8260869565217391, "grad_norm": 10.022204399108887, "learning_rate": 6.814038526753205e-05, "loss": 1.5146, "step": 95 }, { "epoch": 0.8347826086956521, "grad_norm": 6.776736736297607, "learning_rate": 6.747320897995493e-05, "loss": 0.7498, "step": 96 }, { "epoch": 0.8434782608695652, "grad_norm": 3.5592079162597656, "learning_rate": 6.680246966077151e-05, "loss": 0.3334, "step": 97 }, { "epoch": 0.8521739130434782, "grad_norm": 9.817056655883789, "learning_rate": 6.61283040831067e-05, "loss": 2.1917, "step": 98 }, { "epoch": 0.8608695652173913, "grad_norm": 15.627985954284668, "learning_rate": 6.545084971874738e-05, "loss": 2.424, "step": 99 }, { "epoch": 0.8695652173913043, "grad_norm": 7.368549823760986, "learning_rate": 6.477024471011001e-05, "loss": 0.7012, "step": 100 }, { "epoch": 0.8782608695652174, "grad_norm": 11.648536682128906, "learning_rate": 6.408662784207149e-05, "loss": 2.1049, "step": 101 }, { "epoch": 0.8869565217391304, "grad_norm": 7.728333950042725, "learning_rate": 6.340013851366896e-05, "loss": 1.3175, "step": 102 }, { "epoch": 0.8956521739130435, "grad_norm": 10.55436897277832, "learning_rate": 6.271091670967436e-05, "loss": 1.196, "step": 103 }, { "epoch": 0.9043478260869565, "grad_norm": 8.97383975982666, "learning_rate": 6.201910297204962e-05, "loss": 1.0469, "step": 104 }, { "epoch": 0.9130434782608695, "grad_norm": 10.435872077941895, "learning_rate": 6.132483837128823e-05, "loss": 2.2582, "step": 105 }, { "epoch": 0.9217391304347826, "grad_norm": 5.654266834259033, "learning_rate": 6.062826447764883e-05, "loss": 0.3781, "step": 106 }, { "epoch": 0.9304347826086956, "grad_norm": 8.847671508789062, "learning_rate": 5.992952333228728e-05, "loss": 1.2343, "step": 107 }, { "epoch": 0.9391304347826087, "grad_norm": 6.885233402252197, "learning_rate": 5.9228757418292266e-05, "loss": 0.3779, "step": 108 }, { "epoch": 0.9478260869565217, "grad_norm": 18.239648818969727, "learning_rate": 5.85261096316312e-05, "loss": 2.1069, "step": 109 }, { "epoch": 0.9565217391304348, "grad_norm": 3.1215038299560547, "learning_rate": 5.782172325201155e-05, "loss": 0.1011, "step": 110 }, { "epoch": 0.9652173913043478, "grad_norm": 15.885011672973633, "learning_rate": 5.7115741913664264e-05, "loss": 1.4789, "step": 111 }, { "epoch": 0.9739130434782609, "grad_norm": 7.603321075439453, "learning_rate": 5.640830957605465e-05, "loss": 0.7941, "step": 112 }, { "epoch": 0.9826086956521739, "grad_norm": 11.354793548583984, "learning_rate": 5.569957049452703e-05, "loss": 2.0018, "step": 113 }, { "epoch": 0.991304347826087, "grad_norm": 8.468228340148926, "learning_rate": 5.4989669190889136e-05, "loss": 1.1619, "step": 114 }, { "epoch": 1.0, "grad_norm": 6.8398637771606445, "learning_rate": 5.427875042394199e-05, "loss": 0.7186, "step": 115 }, { "epoch": 1.008695652173913, "grad_norm": 7.124094009399414, "learning_rate": 5.3566959159961615e-05, "loss": 1.1124, "step": 116 }, { "epoch": 1.017391304347826, "grad_norm": 9.615336418151855, "learning_rate": 5.2854440543138406e-05, "loss": 0.8346, "step": 117 }, { "epoch": 1.0260869565217392, "grad_norm": 7.556457042694092, "learning_rate": 5.2141339865980134e-05, "loss": 0.7831, "step": 118 }, { "epoch": 1.0347826086956522, "grad_norm": 7.170627117156982, "learning_rate": 5.142780253968481e-05, "loss": 0.7333, "step": 119 }, { "epoch": 1.0434782608695652, "grad_norm": 8.967455863952637, "learning_rate": 5.0713974064489367e-05, "loss": 2.6066, "step": 120 }, { "epoch": 1.0521739130434782, "grad_norm": 8.012558937072754, "learning_rate": 5e-05, "loss": 0.6936, "step": 121 }, { "epoch": 1.0608695652173914, "grad_norm": 5.820160865783691, "learning_rate": 4.928602593551065e-05, "loss": 0.5577, "step": 122 }, { "epoch": 1.0695652173913044, "grad_norm": 5.0591559410095215, "learning_rate": 4.85721974603152e-05, "loss": 0.3028, "step": 123 }, { "epoch": 1.0782608695652174, "grad_norm": 8.6309814453125, "learning_rate": 4.7858660134019884e-05, "loss": 1.1837, "step": 124 }, { "epoch": 1.0869565217391304, "grad_norm": 11.295366287231445, "learning_rate": 4.71455594568616e-05, "loss": 1.8619, "step": 125 }, { "epoch": 1.0956521739130434, "grad_norm": 7.7538862228393555, "learning_rate": 4.643304084003839e-05, "loss": 0.8074, "step": 126 }, { "epoch": 1.1043478260869566, "grad_norm": 8.09078311920166, "learning_rate": 4.5721249576058027e-05, "loss": 0.6141, "step": 127 }, { "epoch": 1.1130434782608696, "grad_norm": 6.496982574462891, "learning_rate": 4.501033080911086e-05, "loss": 0.6054, "step": 128 }, { "epoch": 1.1217391304347826, "grad_norm": 8.538832664489746, "learning_rate": 4.4300429505472976e-05, "loss": 1.1904, "step": 129 }, { "epoch": 1.1304347826086956, "grad_norm": 9.956181526184082, "learning_rate": 4.359169042394536e-05, "loss": 1.1105, "step": 130 }, { "epoch": 1.1391304347826088, "grad_norm": 5.782883644104004, "learning_rate": 4.288425808633575e-05, "loss": 0.5066, "step": 131 }, { "epoch": 1.1478260869565218, "grad_norm": 7.502802848815918, "learning_rate": 4.2178276747988446e-05, "loss": 1.662, "step": 132 }, { "epoch": 1.1565217391304348, "grad_norm": 5.598113059997559, "learning_rate": 4.147389036836881e-05, "loss": 0.5835, "step": 133 }, { "epoch": 1.1652173913043478, "grad_norm": 4.0234808921813965, "learning_rate": 4.077124258170774e-05, "loss": 0.0897, "step": 134 }, { "epoch": 1.1739130434782608, "grad_norm": 8.106297492980957, "learning_rate": 4.007047666771274e-05, "loss": 0.8356, "step": 135 }, { "epoch": 1.182608695652174, "grad_norm": 6.441939353942871, "learning_rate": 3.937173552235117e-05, "loss": 0.5413, "step": 136 }, { "epoch": 1.191304347826087, "grad_norm": 12.384346961975098, "learning_rate": 3.8675161628711776e-05, "loss": 0.7925, "step": 137 }, { "epoch": 1.2, "grad_norm": 8.959207534790039, "learning_rate": 3.798089702795038e-05, "loss": 0.715, "step": 138 }, { "epoch": 1.208695652173913, "grad_norm": 8.550363540649414, "learning_rate": 3.728908329032567e-05, "loss": 1.0794, "step": 139 }, { "epoch": 1.2173913043478262, "grad_norm": 15.134200096130371, "learning_rate": 3.659986148633107e-05, "loss": 1.3818, "step": 140 }, { "epoch": 1.2260869565217392, "grad_norm": 8.52934741973877, "learning_rate": 3.591337215792852e-05, "loss": 0.316, "step": 141 }, { "epoch": 1.2347826086956522, "grad_norm": 6.627355098724365, "learning_rate": 3.522975528989e-05, "loss": 0.4346, "step": 142 }, { "epoch": 1.2434782608695651, "grad_norm": 10.961922645568848, "learning_rate": 3.4549150281252636e-05, "loss": 1.5048, "step": 143 }, { "epoch": 1.2521739130434781, "grad_norm": 8.977882385253906, "learning_rate": 3.3871695916893314e-05, "loss": 0.9586, "step": 144 }, { "epoch": 1.2608695652173914, "grad_norm": 8.683388710021973, "learning_rate": 3.3197530339228487e-05, "loss": 0.9217, "step": 145 }, { "epoch": 1.2695652173913043, "grad_norm": 14.419705390930176, "learning_rate": 3.2526791020045086e-05, "loss": 1.7538, "step": 146 }, { "epoch": 1.2782608695652173, "grad_norm": 7.970763206481934, "learning_rate": 3.1859614732467954e-05, "loss": 0.4354, "step": 147 }, { "epoch": 1.2869565217391306, "grad_norm": 8.308634757995605, "learning_rate": 3.119613752307002e-05, "loss": 0.8199, "step": 148 }, { "epoch": 1.2956521739130435, "grad_norm": 7.006349563598633, "learning_rate": 3.053649468413043e-05, "loss": 0.5617, "step": 149 }, { "epoch": 1.3043478260869565, "grad_norm": 8.015650749206543, "learning_rate": 2.988082072604661e-05, "loss": 0.7712, "step": 150 }, { "epoch": 1.3130434782608695, "grad_norm": 9.2400541305542, "learning_rate": 2.9229249349905684e-05, "loss": 1.4479, "step": 151 }, { "epoch": 1.3217391304347825, "grad_norm": 5.748171806335449, "learning_rate": 2.858191342022095e-05, "loss": 0.389, "step": 152 }, { "epoch": 1.3304347826086955, "grad_norm": 7.006728649139404, "learning_rate": 2.7938944937838923e-05, "loss": 0.5211, "step": 153 }, { "epoch": 1.3391304347826087, "grad_norm": 7.924238681793213, "learning_rate": 2.7300475013022663e-05, "loss": 0.6353, "step": 154 }, { "epoch": 1.3478260869565217, "grad_norm": 10.750234603881836, "learning_rate": 2.6666633838716314e-05, "loss": 1.1832, "step": 155 }, { "epoch": 1.3565217391304347, "grad_norm": 5.400400161743164, "learning_rate": 2.603755066399718e-05, "loss": 0.1326, "step": 156 }, { "epoch": 1.365217391304348, "grad_norm": 8.878824234008789, "learning_rate": 2.5413353767719805e-05, "loss": 0.9578, "step": 157 }, { "epoch": 1.373913043478261, "grad_norm": 6.241739749908447, "learning_rate": 2.4794170432358415e-05, "loss": 0.4989, "step": 158 }, { "epoch": 1.382608695652174, "grad_norm": 19.65182113647461, "learning_rate": 2.418012691805191e-05, "loss": 2.3024, "step": 159 }, { "epoch": 1.391304347826087, "grad_norm": 10.574295043945312, "learning_rate": 2.3571348436857904e-05, "loss": 0.8163, "step": 160 }, { "epoch": 1.4, "grad_norm": 4.394688606262207, "learning_rate": 2.296795912722014e-05, "loss": 0.1608, "step": 161 }, { "epoch": 1.4086956521739131, "grad_norm": 6.658543109893799, "learning_rate": 2.2370082028654866e-05, "loss": 0.6319, "step": 162 }, { "epoch": 1.4173913043478261, "grad_norm": 3.092381715774536, "learning_rate": 2.1777839056661554e-05, "loss": 0.0609, "step": 163 }, { "epoch": 1.4260869565217391, "grad_norm": 8.153127670288086, "learning_rate": 2.119135097786236e-05, "loss": 0.8792, "step": 164 }, { "epoch": 1.434782608695652, "grad_norm": 3.8503527641296387, "learning_rate": 2.061073738537635e-05, "loss": 0.0882, "step": 165 }, { "epoch": 1.4434782608695653, "grad_norm": 13.175821304321289, "learning_rate": 2.0036116674432654e-05, "loss": 1.2865, "step": 166 }, { "epoch": 1.4521739130434783, "grad_norm": 7.390486717224121, "learning_rate": 1.946760601822809e-05, "loss": 0.5875, "step": 167 }, { "epoch": 1.4608695652173913, "grad_norm": 8.266345024108887, "learning_rate": 1.8905321344033898e-05, "loss": 0.2723, "step": 168 }, { "epoch": 1.4695652173913043, "grad_norm": 8.177164077758789, "learning_rate": 1.8349377309556486e-05, "loss": 0.6457, "step": 169 }, { "epoch": 1.4782608695652173, "grad_norm": 6.325401306152344, "learning_rate": 1.7799887279557237e-05, "loss": 0.6313, "step": 170 }, { "epoch": 1.4869565217391305, "grad_norm": 11.269718170166016, "learning_rate": 1.725696330273575e-05, "loss": 0.8341, "step": 171 }, { "epoch": 1.4956521739130435, "grad_norm": 9.295413970947266, "learning_rate": 1.6720716088881594e-05, "loss": 1.0624, "step": 172 }, { "epoch": 1.5043478260869565, "grad_norm": 10.624412536621094, "learning_rate": 1.619125498629904e-05, "loss": 1.374, "step": 173 }, { "epoch": 1.5130434782608697, "grad_norm": 8.308755874633789, "learning_rate": 1.566868795950932e-05, "loss": 0.2568, "step": 174 }, { "epoch": 1.5217391304347827, "grad_norm": 9.137283325195312, "learning_rate": 1.5153121567235335e-05, "loss": 0.6905, "step": 175 }, { "epoch": 1.5304347826086957, "grad_norm": 8.51821517944336, "learning_rate": 1.4644660940672627e-05, "loss": 0.733, "step": 176 }, { "epoch": 1.5391304347826087, "grad_norm": 8.871479034423828, "learning_rate": 1.414340976205183e-05, "loss": 0.8432, "step": 177 }, { "epoch": 1.5478260869565217, "grad_norm": 7.690972328186035, "learning_rate": 1.3649470243496326e-05, "loss": 0.5685, "step": 178 }, { "epoch": 1.5565217391304347, "grad_norm": 7.664311408996582, "learning_rate": 1.3162943106179749e-05, "loss": 0.6617, "step": 179 }, { "epoch": 1.5652173913043477, "grad_norm": 7.690062999725342, "learning_rate": 1.2683927559787655e-05, "loss": 0.5499, "step": 180 }, { "epoch": 1.5739130434782609, "grad_norm": 2.8447952270507812, "learning_rate": 1.2212521282287092e-05, "loss": 0.0586, "step": 181 }, { "epoch": 1.5826086956521739, "grad_norm": 7.366944313049316, "learning_rate": 1.1748820400008843e-05, "loss": 0.6262, "step": 182 }, { "epoch": 1.591304347826087, "grad_norm": 10.251835823059082, "learning_rate": 1.1292919468045877e-05, "loss": 0.7647, "step": 183 }, { "epoch": 1.6, "grad_norm": 10.744357109069824, "learning_rate": 1.0844911450972229e-05, "loss": 0.4428, "step": 184 }, { "epoch": 1.608695652173913, "grad_norm": 7.546830654144287, "learning_rate": 1.0404887703886251e-05, "loss": 0.7932, "step": 185 }, { "epoch": 1.617391304347826, "grad_norm": 5.92943000793457, "learning_rate": 9.972937953781986e-06, "loss": 0.3523, "step": 186 }, { "epoch": 1.626086956521739, "grad_norm": 8.205349922180176, "learning_rate": 9.549150281252633e-06, "loss": 0.5491, "step": 187 }, { "epoch": 1.634782608695652, "grad_norm": 3.2450342178344727, "learning_rate": 9.133611102529654e-06, "loss": 0.071, "step": 188 }, { "epoch": 1.643478260869565, "grad_norm": 3.5468215942382812, "learning_rate": 8.7264051518613e-06, "loss": 0.0861, "step": 189 }, { "epoch": 1.6521739130434783, "grad_norm": 7.733258247375488, "learning_rate": 8.327615464234129e-06, "loss": 0.6044, "step": 190 }, { "epoch": 1.6608695652173913, "grad_norm": 9.37753963470459, "learning_rate": 7.937323358440935e-06, "loss": 0.9109, "step": 191 }, { "epoch": 1.6695652173913045, "grad_norm": 5.947280406951904, "learning_rate": 7.555608420498872e-06, "loss": 0.5775, "step": 192 }, { "epoch": 1.6782608695652175, "grad_norm": 17.63241195678711, "learning_rate": 7.182548487420554e-06, "loss": 1.5021, "step": 193 }, { "epoch": 1.6869565217391305, "grad_norm": 5.9392194747924805, "learning_rate": 6.818219631342149e-06, "loss": 0.1202, "step": 194 }, { "epoch": 1.6956521739130435, "grad_norm": 10.098470687866211, "learning_rate": 6.462696144011149e-06, "loss": 0.9951, "step": 195 }, { "epoch": 1.7043478260869565, "grad_norm": 6.320773124694824, "learning_rate": 6.116050521637218e-06, "loss": 0.3461, "step": 196 }, { "epoch": 1.7130434782608694, "grad_norm": 6.652013778686523, "learning_rate": 5.778353450109286e-06, "loss": 0.5867, "step": 197 }, { "epoch": 1.7217391304347827, "grad_norm": 6.05897855758667, "learning_rate": 5.449673790581611e-06, "loss": 0.3891, "step": 198 }, { "epoch": 1.7304347826086957, "grad_norm": 3.006110668182373, "learning_rate": 5.13007856543209e-06, "loss": 0.0702, "step": 199 }, { "epoch": 1.7391304347826086, "grad_norm": 8.747302055358887, "learning_rate": 4.819632944595415e-06, "loss": 0.7109, "step": 200 }, { "epoch": 1.7478260869565219, "grad_norm": 12.901275634765625, "learning_rate": 4.5184002322740785e-06, "loss": 0.6487, "step": 201 }, { "epoch": 1.7565217391304349, "grad_norm": 9.19820499420166, "learning_rate": 4.2264418540297e-06, "loss": 1.3881, "step": 202 }, { "epoch": 1.7652173913043478, "grad_norm": 7.706724166870117, "learning_rate": 3.9438173442575e-06, "loss": 0.7404, "step": 203 }, { "epoch": 1.7739130434782608, "grad_norm": 7.71926736831665, "learning_rate": 3.6705843340464286e-06, "loss": 0.4732, "step": 204 }, { "epoch": 1.7826086956521738, "grad_norm": 5.502258777618408, "learning_rate": 3.406798539427386e-06, "loss": 0.1223, "step": 205 }, { "epoch": 1.7913043478260868, "grad_norm": 7.742398262023926, "learning_rate": 3.1525137500119207e-06, "loss": 0.5115, "step": 206 }, { "epoch": 1.8, "grad_norm": 10.397440910339355, "learning_rate": 2.9077818180237693e-06, "loss": 0.7478, "step": 207 }, { "epoch": 1.808695652173913, "grad_norm": 7.683396339416504, "learning_rate": 2.6726526477254987e-06, "loss": 0.7615, "step": 208 }, { "epoch": 1.8173913043478263, "grad_norm": 6.312471389770508, "learning_rate": 2.4471741852423237e-06, "loss": 0.5505, "step": 209 }, { "epoch": 1.8260869565217392, "grad_norm": 7.305165767669678, "learning_rate": 2.2313924087851656e-06, "loss": 0.5583, "step": 210 }, { "epoch": 1.8347826086956522, "grad_norm": 6.8820929527282715, "learning_rate": 2.0253513192751373e-06, "loss": 0.3772, "step": 211 }, { "epoch": 1.8434782608695652, "grad_norm": 6.177343845367432, "learning_rate": 1.8290929313710513e-06, "loss": 0.3328, "step": 212 }, { "epoch": 1.8521739130434782, "grad_norm": 5.385695457458496, "learning_rate": 1.6426572649021476e-06, "loss": 0.1388, "step": 213 }, { "epoch": 1.8608695652173912, "grad_norm": 8.022261619567871, "learning_rate": 1.4660823367073751e-06, "loss": 0.565, "step": 214 }, { "epoch": 1.8695652173913042, "grad_norm": 9.438583374023438, "learning_rate": 1.2994041528833266e-06, "loss": 0.8478, "step": 215 }, { "epoch": 1.8782608695652174, "grad_norm": 7.929783344268799, "learning_rate": 1.1426567014420297e-06, "loss": 0.5489, "step": 216 }, { "epoch": 1.8869565217391304, "grad_norm": 12.173213958740234, "learning_rate": 9.958719453803278e-07, "loss": 1.9477, "step": 217 }, { "epoch": 1.8956521739130436, "grad_norm": 6.1458740234375, "learning_rate": 8.590798161622227e-07, "loss": 0.4285, "step": 218 }, { "epoch": 1.9043478260869566, "grad_norm": 11.562338829040527, "learning_rate": 7.323082076153509e-07, "loss": 1.2916, "step": 219 }, { "epoch": 1.9130434782608696, "grad_norm": 17.643951416015625, "learning_rate": 6.15582970243117e-07, "loss": 1.6767, "step": 220 }, { "epoch": 1.9217391304347826, "grad_norm": 10.295869827270508, "learning_rate": 5.089279059533658e-07, "loss": 0.8823, "step": 221 }, { "epoch": 1.9304347826086956, "grad_norm": 6.318659782409668, "learning_rate": 4.123647632048644e-07, "loss": 0.525, "step": 222 }, { "epoch": 1.9391304347826086, "grad_norm": 5.823322772979736, "learning_rate": 3.2591323257248893e-07, "loss": 0.1522, "step": 223 }, { "epoch": 1.9478260869565216, "grad_norm": 7.684267520904541, "learning_rate": 2.4959094273201977e-07, "loss": 0.4218, "step": 224 }, { "epoch": 1.9565217391304348, "grad_norm": 7.761279582977295, "learning_rate": 1.8341345686543332e-07, "loss": 0.4741, "step": 225 }, { "epoch": 1.9652173913043478, "grad_norm": 9.738239288330078, "learning_rate": 1.2739426948732424e-07, "loss": 1.1119, "step": 226 }, { "epoch": 1.973913043478261, "grad_norm": 8.011734962463379, "learning_rate": 8.15448036932176e-08, "loss": 0.8768, "step": 227 }, { "epoch": 1.982608695652174, "grad_norm": 3.6634368896484375, "learning_rate": 4.5874408830215434e-08, "loss": 0.0662, "step": 228 }, { "epoch": 1.991304347826087, "grad_norm": 9.118965148925781, "learning_rate": 2.0390358590538504e-08, "loss": 0.7163, "step": 229 }, { "epoch": 2.0, "grad_norm": 7.614067554473877, "learning_rate": 5.097849528334919e-09, "loss": 0.6342, "step": 230 } ], "logging_steps": 1.0, "max_steps": 230, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 33878645932032.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }