{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.8612303290414878, "eval_steps": 500, "global_step": 4000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.988078206962327e-05, "loss": 1.7515, "step": 10 }, { "epoch": 0.01, "learning_rate": 4.976156413924655e-05, "loss": 1.78, "step": 20 }, { "epoch": 0.02, "learning_rate": 4.964234620886982e-05, "loss": 1.7268, "step": 30 }, { "epoch": 0.03, "learning_rate": 4.9523128278493086e-05, "loss": 1.6973, "step": 40 }, { "epoch": 0.04, "learning_rate": 4.940391034811636e-05, "loss": 1.6927, "step": 50 }, { "epoch": 0.04, "learning_rate": 4.928469241773963e-05, "loss": 1.6304, "step": 60 }, { "epoch": 0.05, "learning_rate": 4.91654744873629e-05, "loss": 1.6876, "step": 70 }, { "epoch": 0.06, "learning_rate": 4.904625655698618e-05, "loss": 1.6705, "step": 80 }, { "epoch": 0.06, "learning_rate": 4.8927038626609446e-05, "loss": 1.671, "step": 90 }, { "epoch": 0.07, "learning_rate": 4.8807820696232716e-05, "loss": 1.6873, "step": 100 }, { "epoch": 0.08, "learning_rate": 4.868860276585599e-05, "loss": 1.6374, "step": 110 }, { "epoch": 0.09, "learning_rate": 4.856938483547926e-05, "loss": 1.6345, "step": 120 }, { "epoch": 0.09, "learning_rate": 4.845016690510253e-05, "loss": 1.6681, "step": 130 }, { "epoch": 0.1, "learning_rate": 4.8330948974725806e-05, "loss": 1.6318, "step": 140 }, { "epoch": 0.11, "learning_rate": 4.8211731044349076e-05, "loss": 1.6623, "step": 150 }, { "epoch": 0.11, "learning_rate": 4.8092513113972345e-05, "loss": 1.6638, "step": 160 }, { "epoch": 0.12, "learning_rate": 4.7973295183595614e-05, "loss": 1.5959, "step": 170 }, { "epoch": 0.13, "learning_rate": 4.785407725321889e-05, "loss": 1.6736, "step": 180 }, { "epoch": 0.14, "learning_rate": 4.773485932284216e-05, "loss": 1.6483, "step": 190 }, { "epoch": 0.14, "learning_rate": 4.761564139246543e-05, "loss": 1.6607, "step": 200 }, { "epoch": 0.15, "learning_rate": 4.74964234620887e-05, "loss": 1.6355, "step": 210 }, { "epoch": 0.16, "learning_rate": 4.7377205531711974e-05, "loss": 1.6412, "step": 220 }, { "epoch": 0.16, "learning_rate": 4.7257987601335244e-05, "loss": 1.6416, "step": 230 }, { "epoch": 0.17, "learning_rate": 4.713876967095851e-05, "loss": 1.6822, "step": 240 }, { "epoch": 0.18, "learning_rate": 4.701955174058178e-05, "loss": 1.6344, "step": 250 }, { "epoch": 0.19, "learning_rate": 4.690033381020505e-05, "loss": 1.6217, "step": 260 }, { "epoch": 0.19, "learning_rate": 4.678111587982833e-05, "loss": 1.6628, "step": 270 }, { "epoch": 0.2, "learning_rate": 4.66618979494516e-05, "loss": 1.6067, "step": 280 }, { "epoch": 0.21, "learning_rate": 4.6542680019074866e-05, "loss": 1.6526, "step": 290 }, { "epoch": 0.21, "learning_rate": 4.642346208869814e-05, "loss": 1.637, "step": 300 }, { "epoch": 0.22, "learning_rate": 4.630424415832141e-05, "loss": 1.6491, "step": 310 }, { "epoch": 0.23, "learning_rate": 4.618502622794468e-05, "loss": 1.6213, "step": 320 }, { "epoch": 0.24, "learning_rate": 4.606580829756796e-05, "loss": 1.6675, "step": 330 }, { "epoch": 0.24, "learning_rate": 4.5946590367191226e-05, "loss": 1.5946, "step": 340 }, { "epoch": 0.25, "learning_rate": 4.5827372436814496e-05, "loss": 1.6309, "step": 350 }, { "epoch": 0.26, "learning_rate": 4.570815450643777e-05, "loss": 1.6093, "step": 360 }, { "epoch": 0.26, "learning_rate": 4.558893657606104e-05, "loss": 1.6171, "step": 370 }, { "epoch": 0.27, "learning_rate": 4.546971864568431e-05, "loss": 1.6124, "step": 380 }, { "epoch": 0.28, "learning_rate": 4.5350500715307586e-05, "loss": 1.6322, "step": 390 }, { "epoch": 0.29, "learning_rate": 4.5231282784930856e-05, "loss": 1.6261, "step": 400 }, { "epoch": 0.29, "learning_rate": 4.5112064854554125e-05, "loss": 1.5778, "step": 410 }, { "epoch": 0.3, "learning_rate": 4.49928469241774e-05, "loss": 1.6442, "step": 420 }, { "epoch": 0.31, "learning_rate": 4.487362899380067e-05, "loss": 1.6189, "step": 430 }, { "epoch": 0.31, "learning_rate": 4.475441106342394e-05, "loss": 1.6357, "step": 440 }, { "epoch": 0.32, "learning_rate": 4.4635193133047216e-05, "loss": 1.6001, "step": 450 }, { "epoch": 0.33, "learning_rate": 4.4515975202670485e-05, "loss": 1.6227, "step": 460 }, { "epoch": 0.34, "learning_rate": 4.4396757272293754e-05, "loss": 1.6108, "step": 470 }, { "epoch": 0.34, "learning_rate": 4.4277539341917024e-05, "loss": 1.6559, "step": 480 }, { "epoch": 0.35, "learning_rate": 4.41583214115403e-05, "loss": 1.6107, "step": 490 }, { "epoch": 0.36, "learning_rate": 4.403910348116357e-05, "loss": 1.6137, "step": 500 }, { "epoch": 0.36, "learning_rate": 4.391988555078684e-05, "loss": 1.6333, "step": 510 }, { "epoch": 0.37, "learning_rate": 4.3800667620410114e-05, "loss": 1.6256, "step": 520 }, { "epoch": 0.38, "learning_rate": 4.3681449690033384e-05, "loss": 1.652, "step": 530 }, { "epoch": 0.39, "learning_rate": 4.356223175965665e-05, "loss": 1.6325, "step": 540 }, { "epoch": 0.39, "learning_rate": 4.344301382927993e-05, "loss": 1.6319, "step": 550 }, { "epoch": 0.4, "learning_rate": 4.33237958989032e-05, "loss": 1.6378, "step": 560 }, { "epoch": 0.41, "learning_rate": 4.320457796852647e-05, "loss": 1.6113, "step": 570 }, { "epoch": 0.41, "learning_rate": 4.3085360038149744e-05, "loss": 1.5908, "step": 580 }, { "epoch": 0.42, "learning_rate": 4.296614210777301e-05, "loss": 1.6292, "step": 590 }, { "epoch": 0.43, "learning_rate": 4.284692417739628e-05, "loss": 1.6608, "step": 600 }, { "epoch": 0.44, "learning_rate": 4.272770624701956e-05, "loss": 1.6125, "step": 610 }, { "epoch": 0.44, "learning_rate": 4.260848831664283e-05, "loss": 1.597, "step": 620 }, { "epoch": 0.45, "learning_rate": 4.24892703862661e-05, "loss": 1.6496, "step": 630 }, { "epoch": 0.46, "learning_rate": 4.237005245588937e-05, "loss": 1.6096, "step": 640 }, { "epoch": 0.46, "learning_rate": 4.225083452551264e-05, "loss": 1.634, "step": 650 }, { "epoch": 0.47, "learning_rate": 4.213161659513591e-05, "loss": 1.6243, "step": 660 }, { "epoch": 0.48, "learning_rate": 4.201239866475918e-05, "loss": 1.6428, "step": 670 }, { "epoch": 0.49, "learning_rate": 4.189318073438245e-05, "loss": 1.6434, "step": 680 }, { "epoch": 0.49, "learning_rate": 4.1773962804005726e-05, "loss": 1.6316, "step": 690 }, { "epoch": 0.5, "learning_rate": 4.1654744873628996e-05, "loss": 1.627, "step": 700 }, { "epoch": 0.51, "learning_rate": 4.1535526943252265e-05, "loss": 1.6344, "step": 710 }, { "epoch": 0.52, "learning_rate": 4.1416309012875534e-05, "loss": 1.6445, "step": 720 }, { "epoch": 0.52, "learning_rate": 4.129709108249881e-05, "loss": 1.637, "step": 730 }, { "epoch": 0.53, "learning_rate": 4.117787315212208e-05, "loss": 1.6025, "step": 740 }, { "epoch": 0.54, "learning_rate": 4.105865522174535e-05, "loss": 1.6254, "step": 750 }, { "epoch": 0.54, "learning_rate": 4.0939437291368625e-05, "loss": 1.6274, "step": 760 }, { "epoch": 0.55, "learning_rate": 4.0820219360991894e-05, "loss": 1.6329, "step": 770 }, { "epoch": 0.56, "learning_rate": 4.0701001430615164e-05, "loss": 1.6436, "step": 780 }, { "epoch": 0.57, "learning_rate": 4.058178350023844e-05, "loss": 1.6511, "step": 790 }, { "epoch": 0.57, "learning_rate": 4.046256556986171e-05, "loss": 1.6011, "step": 800 }, { "epoch": 0.58, "learning_rate": 4.034334763948498e-05, "loss": 1.6596, "step": 810 }, { "epoch": 0.59, "learning_rate": 4.022412970910825e-05, "loss": 1.6009, "step": 820 }, { "epoch": 0.59, "learning_rate": 4.0104911778731524e-05, "loss": 1.5909, "step": 830 }, { "epoch": 0.6, "learning_rate": 3.998569384835479e-05, "loss": 1.6371, "step": 840 }, { "epoch": 0.61, "learning_rate": 3.986647591797806e-05, "loss": 1.5722, "step": 850 }, { "epoch": 0.62, "learning_rate": 3.974725798760134e-05, "loss": 1.6408, "step": 860 }, { "epoch": 0.62, "learning_rate": 3.962804005722461e-05, "loss": 1.6413, "step": 870 }, { "epoch": 0.63, "learning_rate": 3.950882212684788e-05, "loss": 1.6372, "step": 880 }, { "epoch": 0.64, "learning_rate": 3.938960419647115e-05, "loss": 1.6492, "step": 890 }, { "epoch": 0.64, "learning_rate": 3.927038626609442e-05, "loss": 1.667, "step": 900 }, { "epoch": 0.65, "learning_rate": 3.915116833571769e-05, "loss": 1.626, "step": 910 }, { "epoch": 0.66, "learning_rate": 3.903195040534097e-05, "loss": 1.5959, "step": 920 }, { "epoch": 0.67, "learning_rate": 3.891273247496424e-05, "loss": 1.6026, "step": 930 }, { "epoch": 0.67, "learning_rate": 3.8793514544587506e-05, "loss": 1.6449, "step": 940 }, { "epoch": 0.68, "learning_rate": 3.867429661421078e-05, "loss": 1.6275, "step": 950 }, { "epoch": 0.69, "learning_rate": 3.855507868383405e-05, "loss": 1.6155, "step": 960 }, { "epoch": 0.69, "learning_rate": 3.843586075345732e-05, "loss": 1.6324, "step": 970 }, { "epoch": 0.7, "learning_rate": 3.83166428230806e-05, "loss": 1.6119, "step": 980 }, { "epoch": 0.71, "learning_rate": 3.8197424892703866e-05, "loss": 1.6156, "step": 990 }, { "epoch": 0.72, "learning_rate": 3.8078206962327136e-05, "loss": 1.5996, "step": 1000 }, { "epoch": 0.72, "learning_rate": 3.795898903195041e-05, "loss": 1.6431, "step": 1010 }, { "epoch": 0.73, "learning_rate": 3.783977110157368e-05, "loss": 1.6383, "step": 1020 }, { "epoch": 0.74, "learning_rate": 3.772055317119695e-05, "loss": 1.6192, "step": 1030 }, { "epoch": 0.74, "learning_rate": 3.7601335240820226e-05, "loss": 1.5839, "step": 1040 }, { "epoch": 0.75, "learning_rate": 3.7482117310443496e-05, "loss": 1.5957, "step": 1050 }, { "epoch": 0.76, "learning_rate": 3.7362899380066765e-05, "loss": 1.6518, "step": 1060 }, { "epoch": 0.77, "learning_rate": 3.724368144969004e-05, "loss": 1.6311, "step": 1070 }, { "epoch": 0.77, "learning_rate": 3.712446351931331e-05, "loss": 1.6616, "step": 1080 }, { "epoch": 0.78, "learning_rate": 3.700524558893658e-05, "loss": 1.6469, "step": 1090 }, { "epoch": 0.79, "learning_rate": 3.688602765855985e-05, "loss": 1.6166, "step": 1100 }, { "epoch": 0.79, "learning_rate": 3.676680972818312e-05, "loss": 1.6427, "step": 1110 }, { "epoch": 0.8, "learning_rate": 3.6647591797806394e-05, "loss": 1.6341, "step": 1120 }, { "epoch": 0.81, "learning_rate": 3.6528373867429664e-05, "loss": 1.628, "step": 1130 }, { "epoch": 0.82, "learning_rate": 3.640915593705293e-05, "loss": 1.6182, "step": 1140 }, { "epoch": 0.82, "learning_rate": 3.62899380066762e-05, "loss": 1.6392, "step": 1150 }, { "epoch": 0.83, "learning_rate": 3.617072007629947e-05, "loss": 1.6185, "step": 1160 }, { "epoch": 0.84, "learning_rate": 3.605150214592275e-05, "loss": 1.6146, "step": 1170 }, { "epoch": 0.84, "learning_rate": 3.593228421554602e-05, "loss": 1.6151, "step": 1180 }, { "epoch": 0.85, "learning_rate": 3.5813066285169286e-05, "loss": 1.6696, "step": 1190 }, { "epoch": 0.86, "learning_rate": 3.569384835479256e-05, "loss": 1.6416, "step": 1200 }, { "epoch": 0.87, "learning_rate": 3.557463042441583e-05, "loss": 1.6127, "step": 1210 }, { "epoch": 0.87, "learning_rate": 3.54554124940391e-05, "loss": 1.6247, "step": 1220 }, { "epoch": 0.88, "learning_rate": 3.533619456366238e-05, "loss": 1.6297, "step": 1230 }, { "epoch": 0.89, "learning_rate": 3.5216976633285646e-05, "loss": 1.6354, "step": 1240 }, { "epoch": 0.89, "learning_rate": 3.5097758702908915e-05, "loss": 1.6057, "step": 1250 }, { "epoch": 0.9, "learning_rate": 3.497854077253219e-05, "loss": 1.6314, "step": 1260 }, { "epoch": 0.91, "learning_rate": 3.485932284215546e-05, "loss": 1.6576, "step": 1270 }, { "epoch": 0.92, "learning_rate": 3.474010491177873e-05, "loss": 1.6059, "step": 1280 }, { "epoch": 0.92, "learning_rate": 3.4620886981402006e-05, "loss": 1.6689, "step": 1290 }, { "epoch": 0.93, "learning_rate": 3.4501669051025275e-05, "loss": 1.6505, "step": 1300 }, { "epoch": 0.94, "learning_rate": 3.4382451120648545e-05, "loss": 1.5906, "step": 1310 }, { "epoch": 0.94, "learning_rate": 3.426323319027182e-05, "loss": 1.6134, "step": 1320 }, { "epoch": 0.95, "learning_rate": 3.414401525989509e-05, "loss": 1.6182, "step": 1330 }, { "epoch": 0.96, "learning_rate": 3.402479732951836e-05, "loss": 1.6337, "step": 1340 }, { "epoch": 0.97, "learning_rate": 3.3905579399141636e-05, "loss": 1.6436, "step": 1350 }, { "epoch": 0.97, "learning_rate": 3.3786361468764905e-05, "loss": 1.6666, "step": 1360 }, { "epoch": 0.98, "learning_rate": 3.3667143538388174e-05, "loss": 1.626, "step": 1370 }, { "epoch": 0.99, "learning_rate": 3.354792560801145e-05, "loss": 1.5996, "step": 1380 }, { "epoch": 0.99, "learning_rate": 3.342870767763472e-05, "loss": 1.6522, "step": 1390 }, { "epoch": 1.0, "learning_rate": 3.330948974725799e-05, "loss": 1.6198, "step": 1400 }, { "epoch": 1.01, "learning_rate": 3.3190271816881265e-05, "loss": 1.6077, "step": 1410 }, { "epoch": 1.02, "learning_rate": 3.3071053886504534e-05, "loss": 1.6341, "step": 1420 }, { "epoch": 1.02, "learning_rate": 3.2951835956127803e-05, "loss": 1.5617, "step": 1430 }, { "epoch": 1.03, "learning_rate": 3.283261802575107e-05, "loss": 1.661, "step": 1440 }, { "epoch": 1.04, "learning_rate": 3.271340009537435e-05, "loss": 1.601, "step": 1450 }, { "epoch": 1.04, "learning_rate": 3.259418216499762e-05, "loss": 1.607, "step": 1460 }, { "epoch": 1.05, "learning_rate": 3.247496423462089e-05, "loss": 1.642, "step": 1470 }, { "epoch": 1.06, "learning_rate": 3.2355746304244164e-05, "loss": 1.6506, "step": 1480 }, { "epoch": 1.07, "learning_rate": 3.223652837386743e-05, "loss": 1.6046, "step": 1490 }, { "epoch": 1.07, "learning_rate": 3.21173104434907e-05, "loss": 1.6273, "step": 1500 }, { "epoch": 1.08, "learning_rate": 3.199809251311398e-05, "loss": 1.6266, "step": 1510 }, { "epoch": 1.09, "learning_rate": 3.187887458273725e-05, "loss": 1.6132, "step": 1520 }, { "epoch": 1.09, "learning_rate": 3.175965665236052e-05, "loss": 1.6257, "step": 1530 }, { "epoch": 1.1, "learning_rate": 3.1640438721983786e-05, "loss": 1.5969, "step": 1540 }, { "epoch": 1.11, "learning_rate": 3.152122079160706e-05, "loss": 1.6094, "step": 1550 }, { "epoch": 1.12, "learning_rate": 3.140200286123033e-05, "loss": 1.5999, "step": 1560 }, { "epoch": 1.12, "learning_rate": 3.12827849308536e-05, "loss": 1.5904, "step": 1570 }, { "epoch": 1.13, "learning_rate": 3.116356700047687e-05, "loss": 1.5829, "step": 1580 }, { "epoch": 1.14, "learning_rate": 3.104434907010014e-05, "loss": 1.6265, "step": 1590 }, { "epoch": 1.14, "learning_rate": 3.0925131139723415e-05, "loss": 1.5791, "step": 1600 }, { "epoch": 1.15, "learning_rate": 3.0805913209346685e-05, "loss": 1.6229, "step": 1610 }, { "epoch": 1.16, "learning_rate": 3.0686695278969954e-05, "loss": 1.6038, "step": 1620 }, { "epoch": 1.17, "learning_rate": 3.056747734859323e-05, "loss": 1.6362, "step": 1630 }, { "epoch": 1.17, "learning_rate": 3.0448259418216503e-05, "loss": 1.6267, "step": 1640 }, { "epoch": 1.18, "learning_rate": 3.0329041487839772e-05, "loss": 1.6535, "step": 1650 }, { "epoch": 1.19, "learning_rate": 3.0209823557463045e-05, "loss": 1.6036, "step": 1660 }, { "epoch": 1.19, "learning_rate": 3.0090605627086314e-05, "loss": 1.5961, "step": 1670 }, { "epoch": 1.2, "learning_rate": 2.9971387696709587e-05, "loss": 1.6079, "step": 1680 }, { "epoch": 1.21, "learning_rate": 2.985216976633286e-05, "loss": 1.6352, "step": 1690 }, { "epoch": 1.22, "learning_rate": 2.973295183595613e-05, "loss": 1.6107, "step": 1700 }, { "epoch": 1.22, "learning_rate": 2.9613733905579398e-05, "loss": 1.6127, "step": 1710 }, { "epoch": 1.23, "learning_rate": 2.9494515975202674e-05, "loss": 1.6102, "step": 1720 }, { "epoch": 1.24, "learning_rate": 2.9375298044825943e-05, "loss": 1.6223, "step": 1730 }, { "epoch": 1.24, "learning_rate": 2.9256080114449213e-05, "loss": 1.6028, "step": 1740 }, { "epoch": 1.25, "learning_rate": 2.9136862184072482e-05, "loss": 1.6347, "step": 1750 }, { "epoch": 1.26, "learning_rate": 2.9017644253695758e-05, "loss": 1.6589, "step": 1760 }, { "epoch": 1.27, "learning_rate": 2.8898426323319027e-05, "loss": 1.6328, "step": 1770 }, { "epoch": 1.27, "learning_rate": 2.8779208392942297e-05, "loss": 1.6306, "step": 1780 }, { "epoch": 1.28, "learning_rate": 2.8659990462565573e-05, "loss": 1.6307, "step": 1790 }, { "epoch": 1.29, "learning_rate": 2.8540772532188842e-05, "loss": 1.6448, "step": 1800 }, { "epoch": 1.29, "learning_rate": 2.842155460181211e-05, "loss": 1.6233, "step": 1810 }, { "epoch": 1.3, "learning_rate": 2.8302336671435387e-05, "loss": 1.6665, "step": 1820 }, { "epoch": 1.31, "learning_rate": 2.8183118741058657e-05, "loss": 1.5952, "step": 1830 }, { "epoch": 1.32, "learning_rate": 2.8063900810681926e-05, "loss": 1.6203, "step": 1840 }, { "epoch": 1.32, "learning_rate": 2.7944682880305202e-05, "loss": 1.6101, "step": 1850 }, { "epoch": 1.33, "learning_rate": 2.782546494992847e-05, "loss": 1.6163, "step": 1860 }, { "epoch": 1.34, "learning_rate": 2.770624701955174e-05, "loss": 1.6024, "step": 1870 }, { "epoch": 1.34, "learning_rate": 2.7587029089175013e-05, "loss": 1.6017, "step": 1880 }, { "epoch": 1.35, "learning_rate": 2.7467811158798286e-05, "loss": 1.6389, "step": 1890 }, { "epoch": 1.36, "learning_rate": 2.7348593228421555e-05, "loss": 1.6092, "step": 1900 }, { "epoch": 1.37, "learning_rate": 2.7229375298044828e-05, "loss": 1.6114, "step": 1910 }, { "epoch": 1.37, "learning_rate": 2.7110157367668097e-05, "loss": 1.6598, "step": 1920 }, { "epoch": 1.38, "learning_rate": 2.6990939437291367e-05, "loss": 1.6292, "step": 1930 }, { "epoch": 1.39, "learning_rate": 2.6871721506914643e-05, "loss": 1.5928, "step": 1940 }, { "epoch": 1.39, "learning_rate": 2.6752503576537912e-05, "loss": 1.5785, "step": 1950 }, { "epoch": 1.4, "learning_rate": 2.663328564616118e-05, "loss": 1.6141, "step": 1960 }, { "epoch": 1.41, "learning_rate": 2.6514067715784457e-05, "loss": 1.5837, "step": 1970 }, { "epoch": 1.42, "learning_rate": 2.6394849785407727e-05, "loss": 1.6534, "step": 1980 }, { "epoch": 1.42, "learning_rate": 2.6275631855030996e-05, "loss": 1.6262, "step": 1990 }, { "epoch": 1.43, "learning_rate": 2.6156413924654272e-05, "loss": 1.5702, "step": 2000 }, { "epoch": 1.44, "learning_rate": 2.603719599427754e-05, "loss": 1.6014, "step": 2010 }, { "epoch": 1.44, "learning_rate": 2.591797806390081e-05, "loss": 1.6303, "step": 2020 }, { "epoch": 1.45, "learning_rate": 2.5798760133524087e-05, "loss": 1.5714, "step": 2030 }, { "epoch": 1.46, "learning_rate": 2.5679542203147356e-05, "loss": 1.6155, "step": 2040 }, { "epoch": 1.47, "learning_rate": 2.5560324272770625e-05, "loss": 1.6266, "step": 2050 }, { "epoch": 1.47, "learning_rate": 2.54411063423939e-05, "loss": 1.5943, "step": 2060 }, { "epoch": 1.48, "learning_rate": 2.532188841201717e-05, "loss": 1.5944, "step": 2070 }, { "epoch": 1.49, "learning_rate": 2.520267048164044e-05, "loss": 1.6377, "step": 2080 }, { "epoch": 1.49, "learning_rate": 2.508345255126371e-05, "loss": 1.5661, "step": 2090 }, { "epoch": 1.5, "learning_rate": 2.4964234620886985e-05, "loss": 1.6748, "step": 2100 }, { "epoch": 1.51, "learning_rate": 2.4845016690510255e-05, "loss": 1.6237, "step": 2110 }, { "epoch": 1.52, "learning_rate": 2.4725798760133524e-05, "loss": 1.6482, "step": 2120 }, { "epoch": 1.52, "learning_rate": 2.4606580829756797e-05, "loss": 1.6219, "step": 2130 }, { "epoch": 1.53, "learning_rate": 2.4487362899380066e-05, "loss": 1.6477, "step": 2140 }, { "epoch": 1.54, "learning_rate": 2.436814496900334e-05, "loss": 1.6199, "step": 2150 }, { "epoch": 1.55, "learning_rate": 2.4248927038626608e-05, "loss": 1.6036, "step": 2160 }, { "epoch": 1.55, "learning_rate": 2.412970910824988e-05, "loss": 1.5806, "step": 2170 }, { "epoch": 1.56, "learning_rate": 2.4010491177873153e-05, "loss": 1.6445, "step": 2180 }, { "epoch": 1.57, "learning_rate": 2.3891273247496423e-05, "loss": 1.6283, "step": 2190 }, { "epoch": 1.57, "learning_rate": 2.3772055317119695e-05, "loss": 1.5914, "step": 2200 }, { "epoch": 1.58, "learning_rate": 2.3652837386742968e-05, "loss": 1.6306, "step": 2210 }, { "epoch": 1.59, "learning_rate": 2.3533619456366237e-05, "loss": 1.6427, "step": 2220 }, { "epoch": 1.6, "learning_rate": 2.341440152598951e-05, "loss": 1.6507, "step": 2230 }, { "epoch": 1.6, "learning_rate": 2.3295183595612783e-05, "loss": 1.6106, "step": 2240 }, { "epoch": 1.61, "learning_rate": 2.3175965665236052e-05, "loss": 1.6115, "step": 2250 }, { "epoch": 1.62, "learning_rate": 2.3056747734859325e-05, "loss": 1.6542, "step": 2260 }, { "epoch": 1.62, "learning_rate": 2.2937529804482597e-05, "loss": 1.6038, "step": 2270 }, { "epoch": 1.63, "learning_rate": 2.2818311874105867e-05, "loss": 1.6208, "step": 2280 }, { "epoch": 1.64, "learning_rate": 2.269909394372914e-05, "loss": 1.6451, "step": 2290 }, { "epoch": 1.65, "learning_rate": 2.2579876013352412e-05, "loss": 1.639, "step": 2300 }, { "epoch": 1.65, "learning_rate": 2.246065808297568e-05, "loss": 1.6411, "step": 2310 }, { "epoch": 1.66, "learning_rate": 2.2341440152598954e-05, "loss": 1.5903, "step": 2320 }, { "epoch": 1.67, "learning_rate": 2.2222222222222223e-05, "loss": 1.6466, "step": 2330 }, { "epoch": 1.67, "learning_rate": 2.2103004291845496e-05, "loss": 1.6011, "step": 2340 }, { "epoch": 1.68, "learning_rate": 2.1983786361468765e-05, "loss": 1.6188, "step": 2350 }, { "epoch": 1.69, "learning_rate": 2.1864568431092035e-05, "loss": 1.6109, "step": 2360 }, { "epoch": 1.7, "learning_rate": 2.1745350500715307e-05, "loss": 1.5914, "step": 2370 }, { "epoch": 1.7, "learning_rate": 2.162613257033858e-05, "loss": 1.6252, "step": 2380 }, { "epoch": 1.71, "learning_rate": 2.150691463996185e-05, "loss": 1.6336, "step": 2390 }, { "epoch": 1.72, "learning_rate": 2.1387696709585122e-05, "loss": 1.6197, "step": 2400 }, { "epoch": 1.72, "learning_rate": 2.1268478779208395e-05, "loss": 1.6296, "step": 2410 }, { "epoch": 1.73, "learning_rate": 2.1149260848831664e-05, "loss": 1.6153, "step": 2420 }, { "epoch": 1.74, "learning_rate": 2.1030042918454937e-05, "loss": 1.628, "step": 2430 }, { "epoch": 1.75, "learning_rate": 2.091082498807821e-05, "loss": 1.6003, "step": 2440 }, { "epoch": 1.75, "learning_rate": 2.079160705770148e-05, "loss": 1.619, "step": 2450 }, { "epoch": 1.76, "learning_rate": 2.067238912732475e-05, "loss": 1.6032, "step": 2460 }, { "epoch": 1.77, "learning_rate": 2.055317119694802e-05, "loss": 1.6484, "step": 2470 }, { "epoch": 1.77, "learning_rate": 2.0433953266571293e-05, "loss": 1.5987, "step": 2480 }, { "epoch": 1.78, "learning_rate": 2.0314735336194566e-05, "loss": 1.6301, "step": 2490 }, { "epoch": 1.79, "learning_rate": 2.0195517405817835e-05, "loss": 1.579, "step": 2500 }, { "epoch": 1.8, "learning_rate": 2.0076299475441108e-05, "loss": 1.5987, "step": 2510 }, { "epoch": 1.8, "learning_rate": 1.995708154506438e-05, "loss": 1.6182, "step": 2520 }, { "epoch": 1.81, "learning_rate": 1.983786361468765e-05, "loss": 1.6147, "step": 2530 }, { "epoch": 1.82, "learning_rate": 1.9718645684310923e-05, "loss": 1.6207, "step": 2540 }, { "epoch": 1.82, "learning_rate": 1.9599427753934195e-05, "loss": 1.5982, "step": 2550 }, { "epoch": 1.83, "learning_rate": 1.9480209823557465e-05, "loss": 1.6267, "step": 2560 }, { "epoch": 1.84, "learning_rate": 1.9360991893180734e-05, "loss": 1.6316, "step": 2570 }, { "epoch": 1.85, "learning_rate": 1.9241773962804007e-05, "loss": 1.6095, "step": 2580 }, { "epoch": 1.85, "learning_rate": 1.9122556032427276e-05, "loss": 1.6576, "step": 2590 }, { "epoch": 1.86, "learning_rate": 1.900333810205055e-05, "loss": 1.6177, "step": 2600 }, { "epoch": 1.87, "learning_rate": 1.888412017167382e-05, "loss": 1.5909, "step": 2610 }, { "epoch": 1.87, "learning_rate": 1.876490224129709e-05, "loss": 1.6152, "step": 2620 }, { "epoch": 1.88, "learning_rate": 1.8645684310920363e-05, "loss": 1.6222, "step": 2630 }, { "epoch": 1.89, "learning_rate": 1.8526466380543633e-05, "loss": 1.631, "step": 2640 }, { "epoch": 1.9, "learning_rate": 1.8407248450166905e-05, "loss": 1.6383, "step": 2650 }, { "epoch": 1.9, "learning_rate": 1.8288030519790178e-05, "loss": 1.568, "step": 2660 }, { "epoch": 1.91, "learning_rate": 1.8168812589413447e-05, "loss": 1.6138, "step": 2670 }, { "epoch": 1.92, "learning_rate": 1.804959465903672e-05, "loss": 1.6173, "step": 2680 }, { "epoch": 1.92, "learning_rate": 1.7930376728659993e-05, "loss": 1.6435, "step": 2690 }, { "epoch": 1.93, "learning_rate": 1.7811158798283262e-05, "loss": 1.6352, "step": 2700 }, { "epoch": 1.94, "learning_rate": 1.7691940867906535e-05, "loss": 1.628, "step": 2710 }, { "epoch": 1.95, "learning_rate": 1.7572722937529807e-05, "loss": 1.6211, "step": 2720 }, { "epoch": 1.95, "learning_rate": 1.7453505007153077e-05, "loss": 1.6143, "step": 2730 }, { "epoch": 1.96, "learning_rate": 1.733428707677635e-05, "loss": 1.6096, "step": 2740 }, { "epoch": 1.97, "learning_rate": 1.7215069146399622e-05, "loss": 1.6084, "step": 2750 }, { "epoch": 1.97, "learning_rate": 1.709585121602289e-05, "loss": 1.6353, "step": 2760 }, { "epoch": 1.98, "learning_rate": 1.6976633285646164e-05, "loss": 1.6074, "step": 2770 }, { "epoch": 1.99, "learning_rate": 1.6857415355269433e-05, "loss": 1.6284, "step": 2780 }, { "epoch": 2.0, "learning_rate": 1.6738197424892706e-05, "loss": 1.6177, "step": 2790 }, { "epoch": 2.0, "learning_rate": 1.6618979494515975e-05, "loss": 1.6046, "step": 2800 }, { "epoch": 2.01, "learning_rate": 1.6499761564139244e-05, "loss": 1.571, "step": 2810 }, { "epoch": 2.02, "learning_rate": 1.6380543633762517e-05, "loss": 1.5751, "step": 2820 }, { "epoch": 2.02, "learning_rate": 1.626132570338579e-05, "loss": 1.6568, "step": 2830 }, { "epoch": 2.03, "learning_rate": 1.614210777300906e-05, "loss": 1.6336, "step": 2840 }, { "epoch": 2.04, "learning_rate": 1.6022889842632332e-05, "loss": 1.5798, "step": 2850 }, { "epoch": 2.05, "learning_rate": 1.5903671912255605e-05, "loss": 1.5965, "step": 2860 }, { "epoch": 2.05, "learning_rate": 1.5784453981878874e-05, "loss": 1.6014, "step": 2870 }, { "epoch": 2.06, "learning_rate": 1.5665236051502147e-05, "loss": 1.6362, "step": 2880 }, { "epoch": 2.07, "learning_rate": 1.554601812112542e-05, "loss": 1.6305, "step": 2890 }, { "epoch": 2.07, "learning_rate": 1.542680019074869e-05, "loss": 1.6313, "step": 2900 }, { "epoch": 2.08, "learning_rate": 1.530758226037196e-05, "loss": 1.6038, "step": 2910 }, { "epoch": 2.09, "learning_rate": 1.5188364329995234e-05, "loss": 1.6064, "step": 2920 }, { "epoch": 2.1, "learning_rate": 1.5069146399618503e-05, "loss": 1.6093, "step": 2930 }, { "epoch": 2.1, "learning_rate": 1.4949928469241776e-05, "loss": 1.5881, "step": 2940 }, { "epoch": 2.11, "learning_rate": 1.4830710538865045e-05, "loss": 1.6171, "step": 2950 }, { "epoch": 2.12, "learning_rate": 1.4711492608488318e-05, "loss": 1.6684, "step": 2960 }, { "epoch": 2.12, "learning_rate": 1.4592274678111589e-05, "loss": 1.6055, "step": 2970 }, { "epoch": 2.13, "learning_rate": 1.4473056747734858e-05, "loss": 1.6273, "step": 2980 }, { "epoch": 2.14, "learning_rate": 1.435383881735813e-05, "loss": 1.5818, "step": 2990 }, { "epoch": 2.15, "learning_rate": 1.4234620886981404e-05, "loss": 1.6099, "step": 3000 }, { "epoch": 2.15, "learning_rate": 1.4115402956604673e-05, "loss": 1.6234, "step": 3010 }, { "epoch": 2.16, "learning_rate": 1.3996185026227945e-05, "loss": 1.55, "step": 3020 }, { "epoch": 2.17, "learning_rate": 1.3876967095851218e-05, "loss": 1.6718, "step": 3030 }, { "epoch": 2.17, "learning_rate": 1.3757749165474487e-05, "loss": 1.6226, "step": 3040 }, { "epoch": 2.18, "learning_rate": 1.363853123509776e-05, "loss": 1.5971, "step": 3050 }, { "epoch": 2.19, "learning_rate": 1.3519313304721031e-05, "loss": 1.6403, "step": 3060 }, { "epoch": 2.2, "learning_rate": 1.3400095374344302e-05, "loss": 1.614, "step": 3070 }, { "epoch": 2.2, "learning_rate": 1.3280877443967573e-05, "loss": 1.6011, "step": 3080 }, { "epoch": 2.21, "learning_rate": 1.3161659513590846e-05, "loss": 1.6229, "step": 3090 }, { "epoch": 2.22, "learning_rate": 1.3042441583214115e-05, "loss": 1.5777, "step": 3100 }, { "epoch": 2.22, "learning_rate": 1.2923223652837388e-05, "loss": 1.6099, "step": 3110 }, { "epoch": 2.23, "learning_rate": 1.2804005722460657e-05, "loss": 1.5801, "step": 3120 }, { "epoch": 2.24, "learning_rate": 1.268478779208393e-05, "loss": 1.5914, "step": 3130 }, { "epoch": 2.25, "learning_rate": 1.2565569861707202e-05, "loss": 1.6024, "step": 3140 }, { "epoch": 2.25, "learning_rate": 1.2446351931330473e-05, "loss": 1.6074, "step": 3150 }, { "epoch": 2.26, "learning_rate": 1.2327134000953744e-05, "loss": 1.5698, "step": 3160 }, { "epoch": 2.27, "learning_rate": 1.2207916070577015e-05, "loss": 1.6145, "step": 3170 }, { "epoch": 2.27, "learning_rate": 1.2088698140200286e-05, "loss": 1.5883, "step": 3180 }, { "epoch": 2.28, "learning_rate": 1.1969480209823557e-05, "loss": 1.6314, "step": 3190 }, { "epoch": 2.29, "learning_rate": 1.1850262279446828e-05, "loss": 1.6169, "step": 3200 }, { "epoch": 2.3, "learning_rate": 1.1731044349070101e-05, "loss": 1.627, "step": 3210 }, { "epoch": 2.3, "learning_rate": 1.1611826418693372e-05, "loss": 1.6505, "step": 3220 }, { "epoch": 2.31, "learning_rate": 1.1492608488316643e-05, "loss": 1.5854, "step": 3230 }, { "epoch": 2.32, "learning_rate": 1.1373390557939914e-05, "loss": 1.6387, "step": 3240 }, { "epoch": 2.32, "learning_rate": 1.1254172627563187e-05, "loss": 1.587, "step": 3250 }, { "epoch": 2.33, "learning_rate": 1.1134954697186458e-05, "loss": 1.604, "step": 3260 }, { "epoch": 2.34, "learning_rate": 1.1015736766809729e-05, "loss": 1.609, "step": 3270 }, { "epoch": 2.35, "learning_rate": 1.0896518836433001e-05, "loss": 1.5899, "step": 3280 }, { "epoch": 2.35, "learning_rate": 1.077730090605627e-05, "loss": 1.5935, "step": 3290 }, { "epoch": 2.36, "learning_rate": 1.0658082975679542e-05, "loss": 1.6361, "step": 3300 }, { "epoch": 2.37, "learning_rate": 1.0538865045302813e-05, "loss": 1.5745, "step": 3310 }, { "epoch": 2.37, "learning_rate": 1.0419647114926085e-05, "loss": 1.6116, "step": 3320 }, { "epoch": 2.38, "learning_rate": 1.0300429184549356e-05, "loss": 1.6053, "step": 3330 }, { "epoch": 2.39, "learning_rate": 1.0181211254172627e-05, "loss": 1.6389, "step": 3340 }, { "epoch": 2.4, "learning_rate": 1.00619933237959e-05, "loss": 1.5935, "step": 3350 }, { "epoch": 2.4, "learning_rate": 9.942775393419171e-06, "loss": 1.6453, "step": 3360 }, { "epoch": 2.41, "learning_rate": 9.823557463042442e-06, "loss": 1.6121, "step": 3370 }, { "epoch": 2.42, "learning_rate": 9.704339532665713e-06, "loss": 1.5903, "step": 3380 }, { "epoch": 2.42, "learning_rate": 9.585121602288986e-06, "loss": 1.6416, "step": 3390 }, { "epoch": 2.43, "learning_rate": 9.465903671912257e-06, "loss": 1.6385, "step": 3400 }, { "epoch": 2.44, "learning_rate": 9.346685741535526e-06, "loss": 1.5784, "step": 3410 }, { "epoch": 2.45, "learning_rate": 9.227467811158799e-06, "loss": 1.6277, "step": 3420 }, { "epoch": 2.45, "learning_rate": 9.10824988078207e-06, "loss": 1.5928, "step": 3430 }, { "epoch": 2.46, "learning_rate": 8.98903195040534e-06, "loss": 1.595, "step": 3440 }, { "epoch": 2.47, "learning_rate": 8.869814020028613e-06, "loss": 1.6532, "step": 3450 }, { "epoch": 2.47, "learning_rate": 8.750596089651884e-06, "loss": 1.6233, "step": 3460 }, { "epoch": 2.48, "learning_rate": 8.631378159275155e-06, "loss": 1.6202, "step": 3470 }, { "epoch": 2.49, "learning_rate": 8.512160228898426e-06, "loss": 1.5735, "step": 3480 }, { "epoch": 2.5, "learning_rate": 8.392942298521699e-06, "loss": 1.6395, "step": 3490 }, { "epoch": 2.5, "learning_rate": 8.27372436814497e-06, "loss": 1.6077, "step": 3500 }, { "epoch": 2.51, "learning_rate": 8.154506437768241e-06, "loss": 1.5644, "step": 3510 }, { "epoch": 2.52, "learning_rate": 8.035288507391512e-06, "loss": 1.6114, "step": 3520 }, { "epoch": 2.53, "learning_rate": 7.916070577014783e-06, "loss": 1.5856, "step": 3530 }, { "epoch": 2.53, "learning_rate": 7.796852646638054e-06, "loss": 1.6417, "step": 3540 }, { "epoch": 2.54, "learning_rate": 7.677634716261325e-06, "loss": 1.5687, "step": 3550 }, { "epoch": 2.55, "learning_rate": 7.558416785884598e-06, "loss": 1.5817, "step": 3560 }, { "epoch": 2.55, "learning_rate": 7.439198855507869e-06, "loss": 1.6244, "step": 3570 }, { "epoch": 2.56, "learning_rate": 7.31998092513114e-06, "loss": 1.6223, "step": 3580 }, { "epoch": 2.57, "learning_rate": 7.2007629947544116e-06, "loss": 1.6277, "step": 3590 }, { "epoch": 2.58, "learning_rate": 7.0815450643776825e-06, "loss": 1.6102, "step": 3600 }, { "epoch": 2.58, "learning_rate": 6.9623271340009535e-06, "loss": 1.5911, "step": 3610 }, { "epoch": 2.59, "learning_rate": 6.8431092036242245e-06, "loss": 1.6144, "step": 3620 }, { "epoch": 2.6, "learning_rate": 6.723891273247497e-06, "loss": 1.6146, "step": 3630 }, { "epoch": 2.6, "learning_rate": 6.604673342870768e-06, "loss": 1.5961, "step": 3640 }, { "epoch": 2.61, "learning_rate": 6.485455412494039e-06, "loss": 1.6164, "step": 3650 }, { "epoch": 2.62, "learning_rate": 6.366237482117311e-06, "loss": 1.6583, "step": 3660 }, { "epoch": 2.63, "learning_rate": 6.247019551740582e-06, "loss": 1.6354, "step": 3670 }, { "epoch": 2.63, "learning_rate": 6.127801621363853e-06, "loss": 1.6257, "step": 3680 }, { "epoch": 2.64, "learning_rate": 6.008583690987125e-06, "loss": 1.5901, "step": 3690 }, { "epoch": 2.65, "learning_rate": 5.889365760610397e-06, "loss": 1.6279, "step": 3700 }, { "epoch": 2.65, "learning_rate": 5.770147830233668e-06, "loss": 1.6207, "step": 3710 }, { "epoch": 2.66, "learning_rate": 5.650929899856939e-06, "loss": 1.5817, "step": 3720 }, { "epoch": 2.67, "learning_rate": 5.53171196948021e-06, "loss": 1.6184, "step": 3730 }, { "epoch": 2.68, "learning_rate": 5.4124940391034815e-06, "loss": 1.6104, "step": 3740 }, { "epoch": 2.68, "learning_rate": 5.293276108726753e-06, "loss": 1.6178, "step": 3750 }, { "epoch": 2.69, "learning_rate": 5.174058178350024e-06, "loss": 1.5805, "step": 3760 }, { "epoch": 2.7, "learning_rate": 5.054840247973295e-06, "loss": 1.673, "step": 3770 }, { "epoch": 2.7, "learning_rate": 4.935622317596566e-06, "loss": 1.6019, "step": 3780 }, { "epoch": 2.71, "learning_rate": 4.816404387219838e-06, "loss": 1.5988, "step": 3790 }, { "epoch": 2.72, "learning_rate": 4.697186456843109e-06, "loss": 1.6067, "step": 3800 }, { "epoch": 2.73, "learning_rate": 4.577968526466381e-06, "loss": 1.607, "step": 3810 }, { "epoch": 2.73, "learning_rate": 4.458750596089652e-06, "loss": 1.593, "step": 3820 }, { "epoch": 2.74, "learning_rate": 4.339532665712923e-06, "loss": 1.5766, "step": 3830 }, { "epoch": 2.75, "learning_rate": 4.220314735336195e-06, "loss": 1.6005, "step": 3840 }, { "epoch": 2.75, "learning_rate": 4.101096804959466e-06, "loss": 1.6264, "step": 3850 }, { "epoch": 2.76, "learning_rate": 3.981878874582738e-06, "loss": 1.5977, "step": 3860 }, { "epoch": 2.77, "learning_rate": 3.8626609442060095e-06, "loss": 1.6245, "step": 3870 }, { "epoch": 2.78, "learning_rate": 3.74344301382928e-06, "loss": 1.5923, "step": 3880 }, { "epoch": 2.78, "learning_rate": 3.6242250834525515e-06, "loss": 1.6262, "step": 3890 }, { "epoch": 2.79, "learning_rate": 3.5050071530758225e-06, "loss": 1.5885, "step": 3900 }, { "epoch": 2.8, "learning_rate": 3.3857892226990943e-06, "loss": 1.6372, "step": 3910 }, { "epoch": 2.8, "learning_rate": 3.2665712923223653e-06, "loss": 1.637, "step": 3920 }, { "epoch": 2.81, "learning_rate": 3.1473533619456367e-06, "loss": 1.6507, "step": 3930 }, { "epoch": 2.82, "learning_rate": 3.028135431568908e-06, "loss": 1.5973, "step": 3940 }, { "epoch": 2.83, "learning_rate": 2.908917501192179e-06, "loss": 1.6351, "step": 3950 }, { "epoch": 2.83, "learning_rate": 2.789699570815451e-06, "loss": 1.6114, "step": 3960 }, { "epoch": 2.84, "learning_rate": 2.6704816404387224e-06, "loss": 1.6444, "step": 3970 }, { "epoch": 2.85, "learning_rate": 2.5512637100619934e-06, "loss": 1.6145, "step": 3980 }, { "epoch": 2.85, "learning_rate": 2.432045779685265e-06, "loss": 1.6347, "step": 3990 }, { "epoch": 2.86, "learning_rate": 2.3128278493085362e-06, "loss": 1.5958, "step": 4000 } ], "logging_steps": 10, "max_steps": 4194, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "total_flos": 2.527783275284398e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }