{ "best_metric": null, "best_model_checkpoint": null, "epoch": 8.69236977711554, "global_step": 70000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1e-08, "loss": 0.1844, "step": 1 }, { "epoch": 0.0, "learning_rate": 1.0000000000000001e-07, "loss": 1.4965, "step": 10 }, { "epoch": 0.0, "learning_rate": 2.0000000000000002e-07, "loss": 0.5472, "step": 20 }, { "epoch": 0.0, "learning_rate": 3.0000000000000004e-07, "loss": 0.8209, "step": 30 }, { "epoch": 0.0, "learning_rate": 4.0000000000000003e-07, "loss": 1.1288, "step": 40 }, { "epoch": 0.01, "learning_rate": 5.000000000000001e-07, "loss": 0.7633, "step": 50 }, { "epoch": 0.01, "learning_rate": 6.000000000000001e-07, "loss": 1.047, "step": 60 }, { "epoch": 0.01, "learning_rate": 7.000000000000001e-07, "loss": 0.4947, "step": 70 }, { "epoch": 0.01, "learning_rate": 8.000000000000001e-07, "loss": 0.6869, "step": 80 }, { "epoch": 0.01, "learning_rate": 9.000000000000001e-07, "loss": 1.2198, "step": 90 }, { "epoch": 0.01, "learning_rate": 1.0000000000000002e-06, "loss": 0.6901, "step": 100 }, { "epoch": 0.01, "learning_rate": 1.1e-06, "loss": 0.7621, "step": 110 }, { "epoch": 0.01, "learning_rate": 1.2000000000000002e-06, "loss": 0.5725, "step": 120 }, { "epoch": 0.02, "learning_rate": 1.3e-06, "loss": 1.2147, "step": 130 }, { "epoch": 0.02, "learning_rate": 1.4000000000000001e-06, "loss": 0.4613, "step": 140 }, { "epoch": 0.02, "learning_rate": 1.5e-06, "loss": 0.944, "step": 150 }, { "epoch": 0.02, "learning_rate": 1.6000000000000001e-06, "loss": 0.6005, "step": 160 }, { "epoch": 0.02, "learning_rate": 1.7000000000000002e-06, "loss": 0.6064, "step": 170 }, { "epoch": 0.02, "learning_rate": 1.8000000000000001e-06, "loss": 0.4727, "step": 180 }, { "epoch": 0.02, "learning_rate": 1.9000000000000002e-06, "loss": 0.2754, "step": 190 }, { "epoch": 0.02, "learning_rate": 2.0000000000000003e-06, "loss": 0.4337, "step": 200 }, { "epoch": 0.03, "learning_rate": 2.1000000000000002e-06, "loss": 0.4906, "step": 210 }, { "epoch": 0.03, "learning_rate": 2.2e-06, "loss": 0.1348, "step": 220 }, { "epoch": 0.03, "learning_rate": 2.3000000000000004e-06, "loss": 0.4349, "step": 230 }, { "epoch": 0.03, "learning_rate": 2.4000000000000003e-06, "loss": 0.8058, "step": 240 }, { "epoch": 0.03, "learning_rate": 2.5e-06, "loss": 0.3247, "step": 250 }, { "epoch": 0.03, "learning_rate": 2.6e-06, "loss": 0.399, "step": 260 }, { "epoch": 0.03, "learning_rate": 2.7000000000000004e-06, "loss": 0.3975, "step": 270 }, { "epoch": 0.03, "learning_rate": 2.8000000000000003e-06, "loss": 0.4027, "step": 280 }, { "epoch": 0.04, "learning_rate": 2.9e-06, "loss": 0.2064, "step": 290 }, { "epoch": 0.04, "learning_rate": 3e-06, "loss": 0.2209, "step": 300 }, { "epoch": 0.04, "learning_rate": 3.1000000000000004e-06, "loss": 0.1088, "step": 310 }, { "epoch": 0.04, "learning_rate": 3.2000000000000003e-06, "loss": 0.2345, "step": 320 }, { "epoch": 0.04, "learning_rate": 3.3000000000000006e-06, "loss": 0.3387, "step": 330 }, { "epoch": 0.04, "learning_rate": 3.4000000000000005e-06, "loss": 0.1842, "step": 340 }, { "epoch": 0.04, "learning_rate": 3.5e-06, "loss": 0.2169, "step": 350 }, { "epoch": 0.04, "learning_rate": 3.6000000000000003e-06, "loss": 0.2198, "step": 360 }, { "epoch": 0.05, "learning_rate": 3.7e-06, "loss": 0.1585, "step": 370 }, { "epoch": 0.05, "learning_rate": 3.8000000000000005e-06, "loss": 0.1382, "step": 380 }, { "epoch": 0.05, "learning_rate": 3.900000000000001e-06, "loss": 0.1164, "step": 390 }, { "epoch": 0.05, "learning_rate": 4.000000000000001e-06, "loss": 0.1546, "step": 400 }, { "epoch": 0.05, "learning_rate": 4.1e-06, "loss": 0.1591, "step": 410 }, { "epoch": 0.05, "learning_rate": 4.2000000000000004e-06, "loss": 0.1014, "step": 420 }, { "epoch": 0.05, "learning_rate": 4.3e-06, "loss": 0.1148, "step": 430 }, { "epoch": 0.05, "learning_rate": 4.4e-06, "loss": 0.1151, "step": 440 }, { "epoch": 0.06, "learning_rate": 4.5e-06, "loss": 0.1201, "step": 450 }, { "epoch": 0.06, "learning_rate": 4.600000000000001e-06, "loss": 0.1472, "step": 460 }, { "epoch": 0.06, "learning_rate": 4.7e-06, "loss": 0.0882, "step": 470 }, { "epoch": 0.06, "learning_rate": 4.800000000000001e-06, "loss": 0.0992, "step": 480 }, { "epoch": 0.06, "learning_rate": 4.9000000000000005e-06, "loss": 0.098, "step": 490 }, { "epoch": 0.06, "learning_rate": 5e-06, "loss": 0.1552, "step": 500 }, { "epoch": 0.06, "learning_rate": 5.1e-06, "loss": 0.141, "step": 510 }, { "epoch": 0.06, "learning_rate": 5.2e-06, "loss": 0.1287, "step": 520 }, { "epoch": 0.07, "learning_rate": 5.300000000000001e-06, "loss": 0.1217, "step": 530 }, { "epoch": 0.07, "learning_rate": 5.400000000000001e-06, "loss": 0.1046, "step": 540 }, { "epoch": 0.07, "learning_rate": 5.500000000000001e-06, "loss": 0.1615, "step": 550 }, { "epoch": 0.07, "learning_rate": 5.600000000000001e-06, "loss": 0.1122, "step": 560 }, { "epoch": 0.07, "learning_rate": 5.7e-06, "loss": 0.0708, "step": 570 }, { "epoch": 0.07, "learning_rate": 5.8e-06, "loss": 0.0521, "step": 580 }, { "epoch": 0.07, "learning_rate": 5.9e-06, "loss": 0.0772, "step": 590 }, { "epoch": 0.07, "learning_rate": 6e-06, "loss": 0.1037, "step": 600 }, { "epoch": 0.08, "learning_rate": 6.1e-06, "loss": 0.124, "step": 610 }, { "epoch": 0.08, "learning_rate": 6.200000000000001e-06, "loss": 0.0747, "step": 620 }, { "epoch": 0.08, "learning_rate": 6.300000000000001e-06, "loss": 0.0807, "step": 630 }, { "epoch": 0.08, "learning_rate": 6.4000000000000006e-06, "loss": 0.1114, "step": 640 }, { "epoch": 0.08, "learning_rate": 6.5000000000000004e-06, "loss": 0.0802, "step": 650 }, { "epoch": 0.08, "learning_rate": 6.600000000000001e-06, "loss": 0.109, "step": 660 }, { "epoch": 0.08, "learning_rate": 6.700000000000001e-06, "loss": 0.0774, "step": 670 }, { "epoch": 0.08, "learning_rate": 6.800000000000001e-06, "loss": 0.107, "step": 680 }, { "epoch": 0.09, "learning_rate": 6.9e-06, "loss": 0.1066, "step": 690 }, { "epoch": 0.09, "learning_rate": 7e-06, "loss": 0.1199, "step": 700 }, { "epoch": 0.09, "learning_rate": 7.100000000000001e-06, "loss": 0.1, "step": 710 }, { "epoch": 0.09, "learning_rate": 7.2000000000000005e-06, "loss": 0.0808, "step": 720 }, { "epoch": 0.09, "learning_rate": 7.3e-06, "loss": 0.0936, "step": 730 }, { "epoch": 0.09, "learning_rate": 7.4e-06, "loss": 0.0845, "step": 740 }, { "epoch": 0.09, "learning_rate": 7.500000000000001e-06, "loss": 0.1185, "step": 750 }, { "epoch": 0.09, "learning_rate": 7.600000000000001e-06, "loss": 0.1293, "step": 760 }, { "epoch": 0.1, "learning_rate": 7.7e-06, "loss": 0.0857, "step": 770 }, { "epoch": 0.1, "learning_rate": 7.800000000000002e-06, "loss": 0.0872, "step": 780 }, { "epoch": 0.1, "learning_rate": 7.9e-06, "loss": 0.1004, "step": 790 }, { "epoch": 0.1, "learning_rate": 8.000000000000001e-06, "loss": 0.0882, "step": 800 }, { "epoch": 0.1, "learning_rate": 8.1e-06, "loss": 0.0828, "step": 810 }, { "epoch": 0.1, "learning_rate": 8.2e-06, "loss": 0.1178, "step": 820 }, { "epoch": 0.1, "learning_rate": 8.3e-06, "loss": 0.1224, "step": 830 }, { "epoch": 0.1, "learning_rate": 8.400000000000001e-06, "loss": 0.1025, "step": 840 }, { "epoch": 0.11, "learning_rate": 8.5e-06, "loss": 0.0946, "step": 850 }, { "epoch": 0.11, "learning_rate": 8.6e-06, "loss": 0.1112, "step": 860 }, { "epoch": 0.11, "learning_rate": 8.700000000000001e-06, "loss": 0.1013, "step": 870 }, { "epoch": 0.11, "learning_rate": 8.8e-06, "loss": 0.1327, "step": 880 }, { "epoch": 0.11, "learning_rate": 8.900000000000001e-06, "loss": 0.0924, "step": 890 }, { "epoch": 0.11, "learning_rate": 9e-06, "loss": 0.1043, "step": 900 }, { "epoch": 0.11, "learning_rate": 9.100000000000001e-06, "loss": 0.1013, "step": 910 }, { "epoch": 0.11, "learning_rate": 9.200000000000002e-06, "loss": 0.1242, "step": 920 }, { "epoch": 0.12, "learning_rate": 9.3e-06, "loss": 0.1043, "step": 930 }, { "epoch": 0.12, "learning_rate": 9.4e-06, "loss": 0.1119, "step": 940 }, { "epoch": 0.12, "learning_rate": 9.5e-06, "loss": 0.1408, "step": 950 }, { "epoch": 0.12, "learning_rate": 9.600000000000001e-06, "loss": 0.0795, "step": 960 }, { "epoch": 0.12, "learning_rate": 9.7e-06, "loss": 0.1247, "step": 970 }, { "epoch": 0.12, "learning_rate": 9.800000000000001e-06, "loss": 0.097, "step": 980 }, { "epoch": 0.12, "learning_rate": 9.9e-06, "loss": 0.077, "step": 990 }, { "epoch": 0.12, "learning_rate": 1e-05, "loss": 0.1128, "step": 1000 }, { "epoch": 0.13, "learning_rate": 9.99975102701357e-06, "loss": 0.0988, "step": 1010 }, { "epoch": 0.13, "learning_rate": 9.99950205402714e-06, "loss": 0.1041, "step": 1020 }, { "epoch": 0.13, "learning_rate": 9.999253081040708e-06, "loss": 0.1176, "step": 1030 }, { "epoch": 0.13, "learning_rate": 9.999004108054277e-06, "loss": 0.09, "step": 1040 }, { "epoch": 0.13, "learning_rate": 9.998755135067845e-06, "loss": 0.0978, "step": 1050 }, { "epoch": 0.13, "learning_rate": 9.998506162081415e-06, "loss": 0.0998, "step": 1060 }, { "epoch": 0.13, "learning_rate": 9.998257189094984e-06, "loss": 0.0851, "step": 1070 }, { "epoch": 0.13, "learning_rate": 9.998008216108554e-06, "loss": 0.0822, "step": 1080 }, { "epoch": 0.14, "learning_rate": 9.997759243122121e-06, "loss": 0.0594, "step": 1090 }, { "epoch": 0.14, "learning_rate": 9.997510270135691e-06, "loss": 0.0897, "step": 1100 }, { "epoch": 0.14, "learning_rate": 9.99726129714926e-06, "loss": 0.1325, "step": 1110 }, { "epoch": 0.14, "learning_rate": 9.99701232416283e-06, "loss": 0.1176, "step": 1120 }, { "epoch": 0.14, "learning_rate": 9.996763351176398e-06, "loss": 0.0848, "step": 1130 }, { "epoch": 0.14, "learning_rate": 9.996514378189967e-06, "loss": 0.0748, "step": 1140 }, { "epoch": 0.14, "learning_rate": 9.996265405203535e-06, "loss": 0.0996, "step": 1150 }, { "epoch": 0.14, "learning_rate": 9.996016432217106e-06, "loss": 0.0881, "step": 1160 }, { "epoch": 0.15, "learning_rate": 9.995767459230674e-06, "loss": 0.1272, "step": 1170 }, { "epoch": 0.15, "learning_rate": 9.995518486244243e-06, "loss": 0.0893, "step": 1180 }, { "epoch": 0.15, "learning_rate": 9.995269513257813e-06, "loss": 0.1009, "step": 1190 }, { "epoch": 0.15, "learning_rate": 9.995020540271381e-06, "loss": 0.0835, "step": 1200 }, { "epoch": 0.15, "learning_rate": 9.99477156728495e-06, "loss": 0.0926, "step": 1210 }, { "epoch": 0.15, "learning_rate": 9.994522594298518e-06, "loss": 0.0817, "step": 1220 }, { "epoch": 0.15, "learning_rate": 9.994273621312089e-06, "loss": 0.0989, "step": 1230 }, { "epoch": 0.15, "learning_rate": 9.994024648325657e-06, "loss": 0.0762, "step": 1240 }, { "epoch": 0.16, "learning_rate": 9.993775675339227e-06, "loss": 0.1233, "step": 1250 }, { "epoch": 0.16, "learning_rate": 9.993526702352796e-06, "loss": 0.1046, "step": 1260 }, { "epoch": 0.16, "learning_rate": 9.993277729366364e-06, "loss": 0.0976, "step": 1270 }, { "epoch": 0.16, "learning_rate": 9.993028756379933e-06, "loss": 0.0634, "step": 1280 }, { "epoch": 0.16, "learning_rate": 9.992779783393503e-06, "loss": 0.0734, "step": 1290 }, { "epoch": 0.16, "learning_rate": 9.992530810407072e-06, "loss": 0.0786, "step": 1300 }, { "epoch": 0.16, "learning_rate": 9.992281837420642e-06, "loss": 0.0805, "step": 1310 }, { "epoch": 0.16, "learning_rate": 9.99203286443421e-06, "loss": 0.1464, "step": 1320 }, { "epoch": 0.17, "learning_rate": 9.991783891447779e-06, "loss": 0.0979, "step": 1330 }, { "epoch": 0.17, "learning_rate": 9.991534918461347e-06, "loss": 0.0944, "step": 1340 }, { "epoch": 0.17, "learning_rate": 9.991285945474918e-06, "loss": 0.0997, "step": 1350 }, { "epoch": 0.17, "learning_rate": 9.991036972488486e-06, "loss": 0.0832, "step": 1360 }, { "epoch": 0.17, "learning_rate": 9.990787999502055e-06, "loss": 0.0854, "step": 1370 }, { "epoch": 0.17, "learning_rate": 9.990539026515625e-06, "loss": 0.0731, "step": 1380 }, { "epoch": 0.17, "learning_rate": 9.990290053529193e-06, "loss": 0.0893, "step": 1390 }, { "epoch": 0.17, "learning_rate": 9.990041080542762e-06, "loss": 0.0771, "step": 1400 }, { "epoch": 0.18, "learning_rate": 9.98979210755633e-06, "loss": 0.0844, "step": 1410 }, { "epoch": 0.18, "learning_rate": 9.9895431345699e-06, "loss": 0.1121, "step": 1420 }, { "epoch": 0.18, "learning_rate": 9.989294161583469e-06, "loss": 0.0703, "step": 1430 }, { "epoch": 0.18, "learning_rate": 9.98904518859704e-06, "loss": 0.0954, "step": 1440 }, { "epoch": 0.18, "learning_rate": 9.988796215610606e-06, "loss": 0.1017, "step": 1450 }, { "epoch": 0.18, "learning_rate": 9.988547242624176e-06, "loss": 0.1074, "step": 1460 }, { "epoch": 0.18, "learning_rate": 9.988298269637745e-06, "loss": 0.1197, "step": 1470 }, { "epoch": 0.18, "learning_rate": 9.988049296651315e-06, "loss": 0.0892, "step": 1480 }, { "epoch": 0.19, "learning_rate": 9.987800323664884e-06, "loss": 0.0941, "step": 1490 }, { "epoch": 0.19, "learning_rate": 9.987551350678452e-06, "loss": 0.0967, "step": 1500 }, { "epoch": 0.19, "learning_rate": 9.98730237769202e-06, "loss": 0.0879, "step": 1510 }, { "epoch": 0.19, "learning_rate": 9.98705340470559e-06, "loss": 0.0829, "step": 1520 }, { "epoch": 0.19, "learning_rate": 9.98680443171916e-06, "loss": 0.0768, "step": 1530 }, { "epoch": 0.19, "learning_rate": 9.986555458732728e-06, "loss": 0.0551, "step": 1540 }, { "epoch": 0.19, "learning_rate": 9.986306485746298e-06, "loss": 0.1073, "step": 1550 }, { "epoch": 0.19, "learning_rate": 9.986057512759867e-06, "loss": 0.0995, "step": 1560 }, { "epoch": 0.19, "learning_rate": 9.985808539773435e-06, "loss": 0.0581, "step": 1570 }, { "epoch": 0.2, "learning_rate": 9.985559566787004e-06, "loss": 0.0924, "step": 1580 }, { "epoch": 0.2, "learning_rate": 9.985310593800574e-06, "loss": 0.1197, "step": 1590 }, { "epoch": 0.2, "learning_rate": 9.985061620814142e-06, "loss": 0.0728, "step": 1600 }, { "epoch": 0.2, "learning_rate": 9.984812647827712e-06, "loss": 0.0755, "step": 1610 }, { "epoch": 0.2, "learning_rate": 9.984563674841281e-06, "loss": 0.0718, "step": 1620 }, { "epoch": 0.2, "learning_rate": 9.98431470185485e-06, "loss": 0.1069, "step": 1630 }, { "epoch": 0.2, "learning_rate": 9.984065728868418e-06, "loss": 0.0532, "step": 1640 }, { "epoch": 0.2, "learning_rate": 9.983816755881988e-06, "loss": 0.0623, "step": 1650 }, { "epoch": 0.21, "learning_rate": 9.983567782895557e-06, "loss": 0.1065, "step": 1660 }, { "epoch": 0.21, "learning_rate": 9.983318809909125e-06, "loss": 0.0851, "step": 1670 }, { "epoch": 0.21, "learning_rate": 9.983069836922694e-06, "loss": 0.1054, "step": 1680 }, { "epoch": 0.21, "learning_rate": 9.982820863936264e-06, "loss": 0.1159, "step": 1690 }, { "epoch": 0.21, "learning_rate": 9.982571890949832e-06, "loss": 0.1161, "step": 1700 }, { "epoch": 0.21, "learning_rate": 9.982322917963401e-06, "loss": 0.0613, "step": 1710 }, { "epoch": 0.21, "learning_rate": 9.982073944976971e-06, "loss": 0.0834, "step": 1720 }, { "epoch": 0.21, "learning_rate": 9.98182497199054e-06, "loss": 0.0752, "step": 1730 }, { "epoch": 0.22, "learning_rate": 9.981575999004108e-06, "loss": 0.0569, "step": 1740 }, { "epoch": 0.22, "learning_rate": 9.981327026017677e-06, "loss": 0.1056, "step": 1750 }, { "epoch": 0.22, "learning_rate": 9.981078053031247e-06, "loss": 0.0955, "step": 1760 }, { "epoch": 0.22, "learning_rate": 9.980829080044815e-06, "loss": 0.0884, "step": 1770 }, { "epoch": 0.22, "learning_rate": 9.980580107058386e-06, "loss": 0.0752, "step": 1780 }, { "epoch": 0.22, "learning_rate": 9.980331134071954e-06, "loss": 0.086, "step": 1790 }, { "epoch": 0.22, "learning_rate": 9.980082161085523e-06, "loss": 0.0928, "step": 1800 }, { "epoch": 0.22, "learning_rate": 9.979833188099091e-06, "loss": 0.0981, "step": 1810 }, { "epoch": 0.23, "learning_rate": 9.979584215112661e-06, "loss": 0.0618, "step": 1820 }, { "epoch": 0.23, "learning_rate": 9.97933524212623e-06, "loss": 0.0803, "step": 1830 }, { "epoch": 0.23, "learning_rate": 9.9790862691398e-06, "loss": 0.1008, "step": 1840 }, { "epoch": 0.23, "learning_rate": 9.978837296153369e-06, "loss": 0.1377, "step": 1850 }, { "epoch": 0.23, "learning_rate": 9.978588323166937e-06, "loss": 0.0998, "step": 1860 }, { "epoch": 0.23, "learning_rate": 9.978339350180506e-06, "loss": 0.0717, "step": 1870 }, { "epoch": 0.23, "learning_rate": 9.978090377194076e-06, "loss": 0.0944, "step": 1880 }, { "epoch": 0.23, "learning_rate": 9.977841404207644e-06, "loss": 0.0693, "step": 1890 }, { "epoch": 0.24, "learning_rate": 9.977592431221213e-06, "loss": 0.1001, "step": 1900 }, { "epoch": 0.24, "learning_rate": 9.977343458234783e-06, "loss": 0.0875, "step": 1910 }, { "epoch": 0.24, "learning_rate": 9.977094485248352e-06, "loss": 0.0841, "step": 1920 }, { "epoch": 0.24, "learning_rate": 9.97684551226192e-06, "loss": 0.0792, "step": 1930 }, { "epoch": 0.24, "learning_rate": 9.976596539275489e-06, "loss": 0.0824, "step": 1940 }, { "epoch": 0.24, "learning_rate": 9.976347566289059e-06, "loss": 0.0702, "step": 1950 }, { "epoch": 0.24, "learning_rate": 9.976098593302627e-06, "loss": 0.0723, "step": 1960 }, { "epoch": 0.24, "learning_rate": 9.975849620316198e-06, "loss": 0.0521, "step": 1970 }, { "epoch": 0.25, "learning_rate": 9.975600647329764e-06, "loss": 0.0713, "step": 1980 }, { "epoch": 0.25, "learning_rate": 9.975351674343335e-06, "loss": 0.0473, "step": 1990 }, { "epoch": 0.25, "learning_rate": 9.975102701356903e-06, "loss": 0.1266, "step": 2000 }, { "epoch": 0.25, "learning_rate": 9.974853728370473e-06, "loss": 0.1002, "step": 2010 }, { "epoch": 0.25, "learning_rate": 9.974604755384042e-06, "loss": 0.0953, "step": 2020 }, { "epoch": 0.25, "learning_rate": 9.97435578239761e-06, "loss": 0.0823, "step": 2030 }, { "epoch": 0.25, "learning_rate": 9.974106809411179e-06, "loss": 0.064, "step": 2040 }, { "epoch": 0.25, "learning_rate": 9.97385783642475e-06, "loss": 0.0613, "step": 2050 }, { "epoch": 0.26, "learning_rate": 9.973608863438318e-06, "loss": 0.0772, "step": 2060 }, { "epoch": 0.26, "learning_rate": 9.973359890451886e-06, "loss": 0.0887, "step": 2070 }, { "epoch": 0.26, "learning_rate": 9.973110917465456e-06, "loss": 0.0851, "step": 2080 }, { "epoch": 0.26, "learning_rate": 9.972861944479025e-06, "loss": 0.0815, "step": 2090 }, { "epoch": 0.26, "learning_rate": 9.972612971492593e-06, "loss": 0.0736, "step": 2100 }, { "epoch": 0.26, "learning_rate": 9.972363998506162e-06, "loss": 0.0607, "step": 2110 }, { "epoch": 0.26, "learning_rate": 9.972115025519732e-06, "loss": 0.0754, "step": 2120 }, { "epoch": 0.26, "learning_rate": 9.9718660525333e-06, "loss": 0.08, "step": 2130 }, { "epoch": 0.27, "learning_rate": 9.971617079546871e-06, "loss": 0.0721, "step": 2140 }, { "epoch": 0.27, "learning_rate": 9.97136810656044e-06, "loss": 0.0665, "step": 2150 }, { "epoch": 0.27, "learning_rate": 9.971119133574008e-06, "loss": 0.0781, "step": 2160 }, { "epoch": 0.27, "learning_rate": 9.970870160587576e-06, "loss": 0.0935, "step": 2170 }, { "epoch": 0.27, "learning_rate": 9.970621187601147e-06, "loss": 0.0674, "step": 2180 }, { "epoch": 0.27, "learning_rate": 9.970372214614715e-06, "loss": 0.0824, "step": 2190 }, { "epoch": 0.27, "learning_rate": 9.970123241628284e-06, "loss": 0.0776, "step": 2200 }, { "epoch": 0.27, "learning_rate": 9.969874268641854e-06, "loss": 0.1202, "step": 2210 }, { "epoch": 0.28, "learning_rate": 9.969625295655422e-06, "loss": 0.0916, "step": 2220 }, { "epoch": 0.28, "learning_rate": 9.969376322668991e-06, "loss": 0.0869, "step": 2230 }, { "epoch": 0.28, "learning_rate": 9.96912734968256e-06, "loss": 0.0901, "step": 2240 }, { "epoch": 0.28, "learning_rate": 9.96887837669613e-06, "loss": 0.0839, "step": 2250 }, { "epoch": 0.28, "learning_rate": 9.968629403709698e-06, "loss": 0.0943, "step": 2260 }, { "epoch": 0.28, "learning_rate": 9.968380430723268e-06, "loss": 0.078, "step": 2270 }, { "epoch": 0.28, "learning_rate": 9.968131457736835e-06, "loss": 0.0757, "step": 2280 }, { "epoch": 0.28, "learning_rate": 9.967882484750405e-06, "loss": 0.0945, "step": 2290 }, { "epoch": 0.29, "learning_rate": 9.967633511763974e-06, "loss": 0.0499, "step": 2300 }, { "epoch": 0.29, "learning_rate": 9.967384538777544e-06, "loss": 0.0729, "step": 2310 }, { "epoch": 0.29, "learning_rate": 9.967135565791113e-06, "loss": 0.0552, "step": 2320 }, { "epoch": 0.29, "learning_rate": 9.966886592804681e-06, "loss": 0.0642, "step": 2330 }, { "epoch": 0.29, "learning_rate": 9.96663761981825e-06, "loss": 0.0683, "step": 2340 }, { "epoch": 0.29, "learning_rate": 9.96638864683182e-06, "loss": 0.0528, "step": 2350 }, { "epoch": 0.29, "learning_rate": 9.966139673845388e-06, "loss": 0.0895, "step": 2360 }, { "epoch": 0.29, "learning_rate": 9.965890700858959e-06, "loss": 0.0718, "step": 2370 }, { "epoch": 0.3, "learning_rate": 9.965641727872527e-06, "loss": 0.0831, "step": 2380 }, { "epoch": 0.3, "learning_rate": 9.965392754886096e-06, "loss": 0.0674, "step": 2390 }, { "epoch": 0.3, "learning_rate": 9.965143781899664e-06, "loss": 0.1059, "step": 2400 }, { "epoch": 0.3, "learning_rate": 9.964894808913234e-06, "loss": 0.0692, "step": 2410 }, { "epoch": 0.3, "learning_rate": 9.964645835926803e-06, "loss": 0.0868, "step": 2420 }, { "epoch": 0.3, "learning_rate": 9.964396862940371e-06, "loss": 0.0931, "step": 2430 }, { "epoch": 0.3, "learning_rate": 9.964147889953942e-06, "loss": 0.0837, "step": 2440 }, { "epoch": 0.3, "learning_rate": 9.96389891696751e-06, "loss": 0.0659, "step": 2450 }, { "epoch": 0.31, "learning_rate": 9.963649943981079e-06, "loss": 0.074, "step": 2460 }, { "epoch": 0.31, "learning_rate": 9.963400970994647e-06, "loss": 0.0821, "step": 2470 }, { "epoch": 0.31, "learning_rate": 9.963151998008217e-06, "loss": 0.0911, "step": 2480 }, { "epoch": 0.31, "learning_rate": 9.962903025021786e-06, "loss": 0.0518, "step": 2490 }, { "epoch": 0.31, "learning_rate": 9.962654052035356e-06, "loss": 0.0936, "step": 2500 }, { "epoch": 0.31, "learning_rate": 9.962405079048923e-06, "loss": 0.0729, "step": 2510 }, { "epoch": 0.31, "learning_rate": 9.962156106062493e-06, "loss": 0.077, "step": 2520 }, { "epoch": 0.31, "learning_rate": 9.961907133076062e-06, "loss": 0.0759, "step": 2530 }, { "epoch": 0.32, "learning_rate": 9.961658160089632e-06, "loss": 0.0741, "step": 2540 }, { "epoch": 0.32, "learning_rate": 9.9614091871032e-06, "loss": 0.0938, "step": 2550 }, { "epoch": 0.32, "learning_rate": 9.961160214116769e-06, "loss": 0.0821, "step": 2560 }, { "epoch": 0.32, "learning_rate": 9.960911241130337e-06, "loss": 0.0863, "step": 2570 }, { "epoch": 0.32, "learning_rate": 9.960662268143908e-06, "loss": 0.0962, "step": 2580 }, { "epoch": 0.32, "learning_rate": 9.960413295157476e-06, "loss": 0.0592, "step": 2590 }, { "epoch": 0.32, "learning_rate": 9.960164322171045e-06, "loss": 0.0883, "step": 2600 }, { "epoch": 0.32, "learning_rate": 9.959915349184615e-06, "loss": 0.0717, "step": 2610 }, { "epoch": 0.33, "learning_rate": 9.959666376198183e-06, "loss": 0.0759, "step": 2620 }, { "epoch": 0.33, "learning_rate": 9.959417403211752e-06, "loss": 0.1081, "step": 2630 }, { "epoch": 0.33, "learning_rate": 9.95916843022532e-06, "loss": 0.0867, "step": 2640 }, { "epoch": 0.33, "learning_rate": 9.95891945723889e-06, "loss": 0.0839, "step": 2650 }, { "epoch": 0.33, "learning_rate": 9.958670484252459e-06, "loss": 0.0685, "step": 2660 }, { "epoch": 0.33, "learning_rate": 9.95842151126603e-06, "loss": 0.0758, "step": 2670 }, { "epoch": 0.33, "learning_rate": 9.958172538279598e-06, "loss": 0.0526, "step": 2680 }, { "epoch": 0.33, "learning_rate": 9.957923565293166e-06, "loss": 0.0904, "step": 2690 }, { "epoch": 0.34, "learning_rate": 9.957674592306735e-06, "loss": 0.0517, "step": 2700 }, { "epoch": 0.34, "learning_rate": 9.957425619320305e-06, "loss": 0.0715, "step": 2710 }, { "epoch": 0.34, "learning_rate": 9.957176646333874e-06, "loss": 0.0769, "step": 2720 }, { "epoch": 0.34, "learning_rate": 9.956927673347442e-06, "loss": 0.088, "step": 2730 }, { "epoch": 0.34, "learning_rate": 9.956678700361012e-06, "loss": 0.0596, "step": 2740 }, { "epoch": 0.34, "learning_rate": 9.956429727374581e-06, "loss": 0.1132, "step": 2750 }, { "epoch": 0.34, "learning_rate": 9.95618075438815e-06, "loss": 0.0608, "step": 2760 }, { "epoch": 0.34, "learning_rate": 9.955931781401718e-06, "loss": 0.0753, "step": 2770 }, { "epoch": 0.35, "learning_rate": 9.955682808415288e-06, "loss": 0.0687, "step": 2780 }, { "epoch": 0.35, "learning_rate": 9.955433835428857e-06, "loss": 0.0564, "step": 2790 }, { "epoch": 0.35, "learning_rate": 9.955184862442427e-06, "loss": 0.1023, "step": 2800 }, { "epoch": 0.35, "learning_rate": 9.954935889455994e-06, "loss": 0.1178, "step": 2810 }, { "epoch": 0.35, "learning_rate": 9.954686916469564e-06, "loss": 0.1052, "step": 2820 }, { "epoch": 0.35, "learning_rate": 9.954437943483132e-06, "loss": 0.0724, "step": 2830 }, { "epoch": 0.35, "learning_rate": 9.954188970496703e-06, "loss": 0.073, "step": 2840 }, { "epoch": 0.35, "learning_rate": 9.953939997510271e-06, "loss": 0.092, "step": 2850 }, { "epoch": 0.36, "learning_rate": 9.953691024523841e-06, "loss": 0.087, "step": 2860 }, { "epoch": 0.36, "learning_rate": 9.953442051537408e-06, "loss": 0.0658, "step": 2870 }, { "epoch": 0.36, "learning_rate": 9.953193078550978e-06, "loss": 0.0913, "step": 2880 }, { "epoch": 0.36, "learning_rate": 9.952944105564547e-06, "loss": 0.0692, "step": 2890 }, { "epoch": 0.36, "learning_rate": 9.952695132578117e-06, "loss": 0.0999, "step": 2900 }, { "epoch": 0.36, "learning_rate": 9.952446159591686e-06, "loss": 0.0745, "step": 2910 }, { "epoch": 0.36, "learning_rate": 9.952197186605254e-06, "loss": 0.0666, "step": 2920 }, { "epoch": 0.36, "learning_rate": 9.951948213618823e-06, "loss": 0.0434, "step": 2930 }, { "epoch": 0.37, "learning_rate": 9.951699240632393e-06, "loss": 0.0773, "step": 2940 }, { "epoch": 0.37, "learning_rate": 9.951450267645961e-06, "loss": 0.0721, "step": 2950 }, { "epoch": 0.37, "learning_rate": 9.95120129465953e-06, "loss": 0.0783, "step": 2960 }, { "epoch": 0.37, "learning_rate": 9.9509523216731e-06, "loss": 0.0856, "step": 2970 }, { "epoch": 0.37, "learning_rate": 9.950703348686669e-06, "loss": 0.0526, "step": 2980 }, { "epoch": 0.37, "learning_rate": 9.950454375700237e-06, "loss": 0.1014, "step": 2990 }, { "epoch": 0.37, "learning_rate": 9.950205402713806e-06, "loss": 0.0603, "step": 3000 }, { "epoch": 0.37, "learning_rate": 9.949956429727376e-06, "loss": 0.0831, "step": 3010 }, { "epoch": 0.37, "learning_rate": 9.949707456740944e-06, "loss": 0.0813, "step": 3020 }, { "epoch": 0.38, "learning_rate": 9.949458483754515e-06, "loss": 0.056, "step": 3030 }, { "epoch": 0.38, "learning_rate": 9.949209510768081e-06, "loss": 0.0843, "step": 3040 }, { "epoch": 0.38, "learning_rate": 9.948960537781652e-06, "loss": 0.1004, "step": 3050 }, { "epoch": 0.38, "learning_rate": 9.94871156479522e-06, "loss": 0.084, "step": 3060 }, { "epoch": 0.38, "learning_rate": 9.94846259180879e-06, "loss": 0.055, "step": 3070 }, { "epoch": 0.38, "learning_rate": 9.948213618822359e-06, "loss": 0.0837, "step": 3080 }, { "epoch": 0.38, "learning_rate": 9.947964645835927e-06, "loss": 0.099, "step": 3090 }, { "epoch": 0.38, "learning_rate": 9.947715672849496e-06, "loss": 0.139, "step": 3100 }, { "epoch": 0.39, "learning_rate": 9.947466699863066e-06, "loss": 0.1115, "step": 3110 }, { "epoch": 0.39, "learning_rate": 9.947217726876635e-06, "loss": 0.0804, "step": 3120 }, { "epoch": 0.39, "learning_rate": 9.946968753890203e-06, "loss": 0.0887, "step": 3130 }, { "epoch": 0.39, "learning_rate": 9.946719780903773e-06, "loss": 0.1001, "step": 3140 }, { "epoch": 0.39, "learning_rate": 9.946470807917342e-06, "loss": 0.093, "step": 3150 }, { "epoch": 0.39, "learning_rate": 9.94622183493091e-06, "loss": 0.1014, "step": 3160 }, { "epoch": 0.39, "learning_rate": 9.945972861944479e-06, "loss": 0.0925, "step": 3170 }, { "epoch": 0.39, "learning_rate": 9.945723888958049e-06, "loss": 0.082, "step": 3180 }, { "epoch": 0.4, "learning_rate": 9.945474915971618e-06, "loss": 0.0749, "step": 3190 }, { "epoch": 0.4, "learning_rate": 9.945225942985188e-06, "loss": 0.0751, "step": 3200 }, { "epoch": 0.4, "learning_rate": 9.944976969998756e-06, "loss": 0.0896, "step": 3210 }, { "epoch": 0.4, "learning_rate": 9.944727997012325e-06, "loss": 0.0791, "step": 3220 }, { "epoch": 0.4, "learning_rate": 9.944479024025893e-06, "loss": 0.096, "step": 3230 }, { "epoch": 0.4, "learning_rate": 9.944230051039464e-06, "loss": 0.0772, "step": 3240 }, { "epoch": 0.4, "learning_rate": 9.943981078053032e-06, "loss": 0.0834, "step": 3250 }, { "epoch": 0.4, "learning_rate": 9.9437321050666e-06, "loss": 0.0886, "step": 3260 }, { "epoch": 0.41, "learning_rate": 9.94348313208017e-06, "loss": 0.1039, "step": 3270 }, { "epoch": 0.41, "learning_rate": 9.94323415909374e-06, "loss": 0.0697, "step": 3280 }, { "epoch": 0.41, "learning_rate": 9.942985186107308e-06, "loss": 0.087, "step": 3290 }, { "epoch": 0.41, "learning_rate": 9.942736213120876e-06, "loss": 0.0396, "step": 3300 }, { "epoch": 0.41, "learning_rate": 9.942487240134447e-06, "loss": 0.0949, "step": 3310 }, { "epoch": 0.41, "learning_rate": 9.942238267148015e-06, "loss": 0.0518, "step": 3320 }, { "epoch": 0.41, "learning_rate": 9.941989294161585e-06, "loss": 0.0837, "step": 3330 }, { "epoch": 0.41, "learning_rate": 9.941740321175152e-06, "loss": 0.0622, "step": 3340 }, { "epoch": 0.42, "learning_rate": 9.941491348188722e-06, "loss": 0.0705, "step": 3350 }, { "epoch": 0.42, "learning_rate": 9.94124237520229e-06, "loss": 0.0874, "step": 3360 }, { "epoch": 0.42, "learning_rate": 9.940993402215861e-06, "loss": 0.1084, "step": 3370 }, { "epoch": 0.42, "learning_rate": 9.94074442922943e-06, "loss": 0.0938, "step": 3380 }, { "epoch": 0.42, "learning_rate": 9.940495456243e-06, "loss": 0.063, "step": 3390 }, { "epoch": 0.42, "learning_rate": 9.940246483256567e-06, "loss": 0.0909, "step": 3400 }, { "epoch": 0.42, "learning_rate": 9.939997510270137e-06, "loss": 0.0531, "step": 3410 }, { "epoch": 0.42, "learning_rate": 9.939748537283705e-06, "loss": 0.1351, "step": 3420 }, { "epoch": 0.43, "learning_rate": 9.939499564297276e-06, "loss": 0.0787, "step": 3430 }, { "epoch": 0.43, "learning_rate": 9.939250591310844e-06, "loss": 0.0791, "step": 3440 }, { "epoch": 0.43, "learning_rate": 9.939001618324413e-06, "loss": 0.0958, "step": 3450 }, { "epoch": 0.43, "learning_rate": 9.938752645337981e-06, "loss": 0.0937, "step": 3460 }, { "epoch": 0.43, "learning_rate": 9.938503672351551e-06, "loss": 0.0713, "step": 3470 }, { "epoch": 0.43, "learning_rate": 9.93825469936512e-06, "loss": 0.0741, "step": 3480 }, { "epoch": 0.43, "learning_rate": 9.938005726378688e-06, "loss": 0.0682, "step": 3490 }, { "epoch": 0.43, "learning_rate": 9.937756753392259e-06, "loss": 0.0788, "step": 3500 }, { "epoch": 0.44, "learning_rate": 9.937507780405827e-06, "loss": 0.1052, "step": 3510 }, { "epoch": 0.44, "learning_rate": 9.937258807419396e-06, "loss": 0.1057, "step": 3520 }, { "epoch": 0.44, "learning_rate": 9.937009834432964e-06, "loss": 0.0843, "step": 3530 }, { "epoch": 0.44, "learning_rate": 9.936760861446534e-06, "loss": 0.0451, "step": 3540 }, { "epoch": 0.44, "learning_rate": 9.936511888460103e-06, "loss": 0.1418, "step": 3550 }, { "epoch": 0.44, "learning_rate": 9.936262915473673e-06, "loss": 0.0869, "step": 3560 }, { "epoch": 0.44, "learning_rate": 9.936013942487242e-06, "loss": 0.0701, "step": 3570 }, { "epoch": 0.44, "learning_rate": 9.93576496950081e-06, "loss": 0.0689, "step": 3580 }, { "epoch": 0.45, "learning_rate": 9.935515996514379e-06, "loss": 0.0792, "step": 3590 }, { "epoch": 0.45, "learning_rate": 9.935267023527949e-06, "loss": 0.1346, "step": 3600 }, { "epoch": 0.45, "learning_rate": 9.935018050541517e-06, "loss": 0.0724, "step": 3610 }, { "epoch": 0.45, "learning_rate": 9.934769077555086e-06, "loss": 0.1245, "step": 3620 }, { "epoch": 0.45, "learning_rate": 9.934520104568654e-06, "loss": 0.0624, "step": 3630 }, { "epoch": 0.45, "learning_rate": 9.934271131582225e-06, "loss": 0.0865, "step": 3640 }, { "epoch": 0.45, "learning_rate": 9.934022158595793e-06, "loss": 0.0891, "step": 3650 }, { "epoch": 0.45, "learning_rate": 9.933773185609362e-06, "loss": 0.068, "step": 3660 }, { "epoch": 0.46, "learning_rate": 9.933524212622932e-06, "loss": 0.0638, "step": 3670 }, { "epoch": 0.46, "learning_rate": 9.9332752396365e-06, "loss": 0.0799, "step": 3680 }, { "epoch": 0.46, "learning_rate": 9.933026266650069e-06, "loss": 0.0638, "step": 3690 }, { "epoch": 0.46, "learning_rate": 9.932777293663637e-06, "loss": 0.0541, "step": 3700 }, { "epoch": 0.46, "learning_rate": 9.932528320677208e-06, "loss": 0.0463, "step": 3710 }, { "epoch": 0.46, "learning_rate": 9.932279347690776e-06, "loss": 0.0941, "step": 3720 }, { "epoch": 0.46, "learning_rate": 9.932030374704346e-06, "loss": 0.0562, "step": 3730 }, { "epoch": 0.46, "learning_rate": 9.931781401717915e-06, "loss": 0.0876, "step": 3740 }, { "epoch": 0.47, "learning_rate": 9.931532428731483e-06, "loss": 0.106, "step": 3750 }, { "epoch": 0.47, "learning_rate": 9.931283455745052e-06, "loss": 0.0698, "step": 3760 }, { "epoch": 0.47, "learning_rate": 9.931034482758622e-06, "loss": 0.0672, "step": 3770 }, { "epoch": 0.47, "learning_rate": 9.93078550977219e-06, "loss": 0.0595, "step": 3780 }, { "epoch": 0.47, "learning_rate": 9.930536536785759e-06, "loss": 0.0903, "step": 3790 }, { "epoch": 0.47, "learning_rate": 9.93028756379933e-06, "loss": 0.0918, "step": 3800 }, { "epoch": 0.47, "learning_rate": 9.930038590812898e-06, "loss": 0.0983, "step": 3810 }, { "epoch": 0.47, "learning_rate": 9.929789617826466e-06, "loss": 0.0667, "step": 3820 }, { "epoch": 0.48, "learning_rate": 9.929540644840035e-06, "loss": 0.0724, "step": 3830 }, { "epoch": 0.48, "learning_rate": 9.929291671853605e-06, "loss": 0.0926, "step": 3840 }, { "epoch": 0.48, "learning_rate": 9.929042698867174e-06, "loss": 0.1086, "step": 3850 }, { "epoch": 0.48, "learning_rate": 9.928793725880744e-06, "loss": 0.0509, "step": 3860 }, { "epoch": 0.48, "learning_rate": 9.92854475289431e-06, "loss": 0.1238, "step": 3870 }, { "epoch": 0.48, "learning_rate": 9.92829577990788e-06, "loss": 0.0769, "step": 3880 }, { "epoch": 0.48, "learning_rate": 9.92804680692145e-06, "loss": 0.0752, "step": 3890 }, { "epoch": 0.48, "learning_rate": 9.92779783393502e-06, "loss": 0.0973, "step": 3900 }, { "epoch": 0.49, "learning_rate": 9.927548860948588e-06, "loss": 0.0808, "step": 3910 }, { "epoch": 0.49, "learning_rate": 9.927299887962158e-06, "loss": 0.0793, "step": 3920 }, { "epoch": 0.49, "learning_rate": 9.927050914975725e-06, "loss": 0.0928, "step": 3930 }, { "epoch": 0.49, "learning_rate": 9.926801941989295e-06, "loss": 0.0648, "step": 3940 }, { "epoch": 0.49, "learning_rate": 9.926552969002864e-06, "loss": 0.0969, "step": 3950 }, { "epoch": 0.49, "learning_rate": 9.926303996016434e-06, "loss": 0.0622, "step": 3960 }, { "epoch": 0.49, "learning_rate": 9.926055023030002e-06, "loss": 0.0965, "step": 3970 }, { "epoch": 0.49, "learning_rate": 9.925806050043571e-06, "loss": 0.0763, "step": 3980 }, { "epoch": 0.5, "learning_rate": 9.92555707705714e-06, "loss": 0.0757, "step": 3990 }, { "epoch": 0.5, "learning_rate": 9.92530810407071e-06, "loss": 0.0725, "step": 4000 }, { "epoch": 0.5, "learning_rate": 9.925059131084278e-06, "loss": 0.087, "step": 4010 }, { "epoch": 0.5, "learning_rate": 9.924810158097847e-06, "loss": 0.1062, "step": 4020 }, { "epoch": 0.5, "learning_rate": 9.924561185111417e-06, "loss": 0.0698, "step": 4030 }, { "epoch": 0.5, "learning_rate": 9.924312212124985e-06, "loss": 0.1008, "step": 4040 }, { "epoch": 0.5, "learning_rate": 9.924063239138554e-06, "loss": 0.068, "step": 4050 }, { "epoch": 0.5, "learning_rate": 9.923814266152123e-06, "loss": 0.0848, "step": 4060 }, { "epoch": 0.51, "learning_rate": 9.923565293165693e-06, "loss": 0.1061, "step": 4070 }, { "epoch": 0.51, "learning_rate": 9.923316320179261e-06, "loss": 0.0671, "step": 4080 }, { "epoch": 0.51, "learning_rate": 9.923067347192831e-06, "loss": 0.0682, "step": 4090 }, { "epoch": 0.51, "learning_rate": 9.9228183742064e-06, "loss": 0.0871, "step": 4100 }, { "epoch": 0.51, "learning_rate": 9.922569401219968e-06, "loss": 0.0753, "step": 4110 }, { "epoch": 0.51, "learning_rate": 9.922320428233537e-06, "loss": 0.0963, "step": 4120 }, { "epoch": 0.51, "learning_rate": 9.922071455247107e-06, "loss": 0.0703, "step": 4130 }, { "epoch": 0.51, "learning_rate": 9.921822482260676e-06, "loss": 0.0479, "step": 4140 }, { "epoch": 0.52, "learning_rate": 9.921573509274244e-06, "loss": 0.0998, "step": 4150 }, { "epoch": 0.52, "learning_rate": 9.921324536287814e-06, "loss": 0.0757, "step": 4160 }, { "epoch": 0.52, "learning_rate": 9.921075563301383e-06, "loss": 0.0721, "step": 4170 }, { "epoch": 0.52, "learning_rate": 9.920826590314951e-06, "loss": 0.0594, "step": 4180 }, { "epoch": 0.52, "learning_rate": 9.92057761732852e-06, "loss": 0.0747, "step": 4190 }, { "epoch": 0.52, "learning_rate": 9.92032864434209e-06, "loss": 0.0732, "step": 4200 }, { "epoch": 0.52, "learning_rate": 9.920079671355659e-06, "loss": 0.0736, "step": 4210 }, { "epoch": 0.52, "learning_rate": 9.919830698369229e-06, "loss": 0.0766, "step": 4220 }, { "epoch": 0.53, "learning_rate": 9.919581725382796e-06, "loss": 0.0976, "step": 4230 }, { "epoch": 0.53, "learning_rate": 9.919332752396366e-06, "loss": 0.0862, "step": 4240 }, { "epoch": 0.53, "learning_rate": 9.919083779409934e-06, "loss": 0.0785, "step": 4250 }, { "epoch": 0.53, "learning_rate": 9.918834806423505e-06, "loss": 0.1088, "step": 4260 }, { "epoch": 0.53, "learning_rate": 9.918585833437073e-06, "loss": 0.0611, "step": 4270 }, { "epoch": 0.53, "learning_rate": 9.918336860450642e-06, "loss": 0.0768, "step": 4280 }, { "epoch": 0.53, "learning_rate": 9.91808788746421e-06, "loss": 0.0688, "step": 4290 }, { "epoch": 0.53, "learning_rate": 9.91783891447778e-06, "loss": 0.0689, "step": 4300 }, { "epoch": 0.54, "learning_rate": 9.917589941491349e-06, "loss": 0.1046, "step": 4310 }, { "epoch": 0.54, "learning_rate": 9.917340968504917e-06, "loss": 0.0851, "step": 4320 }, { "epoch": 0.54, "learning_rate": 9.917091995518488e-06, "loss": 0.0814, "step": 4330 }, { "epoch": 0.54, "learning_rate": 9.916843022532056e-06, "loss": 0.0496, "step": 4340 }, { "epoch": 0.54, "learning_rate": 9.916594049545625e-06, "loss": 0.0678, "step": 4350 }, { "epoch": 0.54, "learning_rate": 9.916345076559193e-06, "loss": 0.0759, "step": 4360 }, { "epoch": 0.54, "learning_rate": 9.916096103572763e-06, "loss": 0.1042, "step": 4370 }, { "epoch": 0.54, "learning_rate": 9.915847130586332e-06, "loss": 0.0471, "step": 4380 }, { "epoch": 0.55, "learning_rate": 9.915598157599902e-06, "loss": 0.0971, "step": 4390 }, { "epoch": 0.55, "learning_rate": 9.915349184613469e-06, "loss": 0.0563, "step": 4400 }, { "epoch": 0.55, "learning_rate": 9.91510021162704e-06, "loss": 0.0755, "step": 4410 }, { "epoch": 0.55, "learning_rate": 9.914851238640608e-06, "loss": 0.0661, "step": 4420 }, { "epoch": 0.55, "learning_rate": 9.914602265654178e-06, "loss": 0.0767, "step": 4430 }, { "epoch": 0.55, "learning_rate": 9.914353292667746e-06, "loss": 0.0614, "step": 4440 }, { "epoch": 0.55, "learning_rate": 9.914104319681317e-06, "loss": 0.0743, "step": 4450 }, { "epoch": 0.55, "learning_rate": 9.913855346694883e-06, "loss": 0.0996, "step": 4460 }, { "epoch": 0.56, "learning_rate": 9.913606373708454e-06, "loss": 0.0848, "step": 4470 }, { "epoch": 0.56, "learning_rate": 9.913357400722022e-06, "loss": 0.0585, "step": 4480 }, { "epoch": 0.56, "learning_rate": 9.913108427735592e-06, "loss": 0.0627, "step": 4490 }, { "epoch": 0.56, "learning_rate": 9.912859454749161e-06, "loss": 0.0913, "step": 4500 }, { "epoch": 0.56, "learning_rate": 9.91261048176273e-06, "loss": 0.0775, "step": 4510 }, { "epoch": 0.56, "learning_rate": 9.912361508776298e-06, "loss": 0.0967, "step": 4520 }, { "epoch": 0.56, "learning_rate": 9.912112535789868e-06, "loss": 0.0838, "step": 4530 }, { "epoch": 0.56, "learning_rate": 9.911863562803437e-06, "loss": 0.0535, "step": 4540 }, { "epoch": 0.56, "learning_rate": 9.911614589817005e-06, "loss": 0.0542, "step": 4550 }, { "epoch": 0.57, "learning_rate": 9.911365616830575e-06, "loss": 0.0762, "step": 4560 }, { "epoch": 0.57, "learning_rate": 9.911116643844144e-06, "loss": 0.0915, "step": 4570 }, { "epoch": 0.57, "learning_rate": 9.910867670857712e-06, "loss": 0.0733, "step": 4580 }, { "epoch": 0.57, "learning_rate": 9.910618697871281e-06, "loss": 0.0725, "step": 4590 }, { "epoch": 0.57, "learning_rate": 9.910369724884851e-06, "loss": 0.0968, "step": 4600 }, { "epoch": 0.57, "learning_rate": 9.91012075189842e-06, "loss": 0.0741, "step": 4610 }, { "epoch": 0.57, "learning_rate": 9.90987177891199e-06, "loss": 0.0638, "step": 4620 }, { "epoch": 0.57, "learning_rate": 9.909622805925558e-06, "loss": 0.0783, "step": 4630 }, { "epoch": 0.58, "learning_rate": 9.909373832939127e-06, "loss": 0.0785, "step": 4640 }, { "epoch": 0.58, "learning_rate": 9.909124859952695e-06, "loss": 0.0743, "step": 4650 }, { "epoch": 0.58, "learning_rate": 9.908875886966266e-06, "loss": 0.0789, "step": 4660 }, { "epoch": 0.58, "learning_rate": 9.908626913979834e-06, "loss": 0.0521, "step": 4670 }, { "epoch": 0.58, "learning_rate": 9.908377940993403e-06, "loss": 0.121, "step": 4680 }, { "epoch": 0.58, "learning_rate": 9.908128968006973e-06, "loss": 0.1044, "step": 4690 }, { "epoch": 0.58, "learning_rate": 9.907879995020541e-06, "loss": 0.0888, "step": 4700 }, { "epoch": 0.58, "learning_rate": 9.90763102203411e-06, "loss": 0.0778, "step": 4710 }, { "epoch": 0.59, "learning_rate": 9.907382049047678e-06, "loss": 0.0686, "step": 4720 }, { "epoch": 0.59, "learning_rate": 9.907133076061249e-06, "loss": 0.0669, "step": 4730 }, { "epoch": 0.59, "learning_rate": 9.906884103074817e-06, "loss": 0.0615, "step": 4740 }, { "epoch": 0.59, "learning_rate": 9.906635130088387e-06, "loss": 0.0876, "step": 4750 }, { "epoch": 0.59, "learning_rate": 9.906386157101954e-06, "loss": 0.1036, "step": 4760 }, { "epoch": 0.59, "learning_rate": 9.906137184115524e-06, "loss": 0.0582, "step": 4770 }, { "epoch": 0.59, "learning_rate": 9.905888211129093e-06, "loss": 0.0563, "step": 4780 }, { "epoch": 0.59, "learning_rate": 9.905639238142663e-06, "loss": 0.0799, "step": 4790 }, { "epoch": 0.6, "learning_rate": 9.905390265156232e-06, "loss": 0.0811, "step": 4800 }, { "epoch": 0.6, "learning_rate": 9.9051412921698e-06, "loss": 0.0876, "step": 4810 }, { "epoch": 0.6, "learning_rate": 9.904892319183369e-06, "loss": 0.06, "step": 4820 }, { "epoch": 0.6, "learning_rate": 9.904643346196939e-06, "loss": 0.0757, "step": 4830 }, { "epoch": 0.6, "learning_rate": 9.904394373210507e-06, "loss": 0.0922, "step": 4840 }, { "epoch": 0.6, "learning_rate": 9.904145400224076e-06, "loss": 0.0478, "step": 4850 }, { "epoch": 0.6, "learning_rate": 9.903896427237646e-06, "loss": 0.0843, "step": 4860 }, { "epoch": 0.6, "learning_rate": 9.903647454251215e-06, "loss": 0.0706, "step": 4870 }, { "epoch": 0.61, "learning_rate": 9.903398481264783e-06, "loss": 0.0425, "step": 4880 }, { "epoch": 0.61, "learning_rate": 9.903149508278352e-06, "loss": 0.066, "step": 4890 }, { "epoch": 0.61, "learning_rate": 9.902900535291922e-06, "loss": 0.0827, "step": 4900 }, { "epoch": 0.61, "learning_rate": 9.90265156230549e-06, "loss": 0.1083, "step": 4910 }, { "epoch": 0.61, "learning_rate": 9.90240258931906e-06, "loss": 0.0703, "step": 4920 }, { "epoch": 0.61, "learning_rate": 9.902153616332627e-06, "loss": 0.0855, "step": 4930 }, { "epoch": 0.61, "learning_rate": 9.901904643346198e-06, "loss": 0.0712, "step": 4940 }, { "epoch": 0.61, "learning_rate": 9.901655670359766e-06, "loss": 0.0711, "step": 4950 }, { "epoch": 0.62, "learning_rate": 9.901406697373336e-06, "loss": 0.0938, "step": 4960 }, { "epoch": 0.62, "learning_rate": 9.901157724386905e-06, "loss": 0.0846, "step": 4970 }, { "epoch": 0.62, "learning_rate": 9.900908751400475e-06, "loss": 0.0809, "step": 4980 }, { "epoch": 0.62, "learning_rate": 9.900659778414042e-06, "loss": 0.0849, "step": 4990 }, { "epoch": 0.62, "learning_rate": 9.900410805427612e-06, "loss": 0.0828, "step": 5000 }, { "epoch": 0.62, "eval_bleu": 88.4616, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.6416, "eval_has_error_f1": 0.3431, "eval_loss": 0.06069768965244293, "eval_runtime": 1415.8849, "eval_samples_per_second": 2.824, "eval_steps_per_second": 0.706, "step": 5000 }, { "epoch": 0.62, "learning_rate": 9.90016183244118e-06, "loss": 0.0852, "step": 5010 }, { "epoch": 0.62, "learning_rate": 9.89991285945475e-06, "loss": 0.0897, "step": 5020 }, { "epoch": 0.62, "learning_rate": 9.89966388646832e-06, "loss": 0.0854, "step": 5030 }, { "epoch": 0.63, "learning_rate": 9.899414913481888e-06, "loss": 0.0776, "step": 5040 }, { "epoch": 0.63, "learning_rate": 9.899165940495456e-06, "loss": 0.0702, "step": 5050 }, { "epoch": 0.63, "learning_rate": 9.898916967509027e-06, "loss": 0.0511, "step": 5060 }, { "epoch": 0.63, "learning_rate": 9.898667994522595e-06, "loss": 0.0781, "step": 5070 }, { "epoch": 0.63, "learning_rate": 9.898419021536164e-06, "loss": 0.0745, "step": 5080 }, { "epoch": 0.63, "learning_rate": 9.898170048549734e-06, "loss": 0.0874, "step": 5090 }, { "epoch": 0.63, "learning_rate": 9.897921075563302e-06, "loss": 0.0882, "step": 5100 }, { "epoch": 0.63, "learning_rate": 9.897672102576871e-06, "loss": 0.0861, "step": 5110 }, { "epoch": 0.64, "learning_rate": 9.89742312959044e-06, "loss": 0.0715, "step": 5120 }, { "epoch": 0.64, "learning_rate": 9.89717415660401e-06, "loss": 0.079, "step": 5130 }, { "epoch": 0.64, "learning_rate": 9.896925183617578e-06, "loss": 0.0827, "step": 5140 }, { "epoch": 0.64, "learning_rate": 9.896676210631148e-06, "loss": 0.0774, "step": 5150 }, { "epoch": 0.64, "learning_rate": 9.896427237644717e-06, "loss": 0.0624, "step": 5160 }, { "epoch": 0.64, "learning_rate": 9.896178264658285e-06, "loss": 0.0708, "step": 5170 }, { "epoch": 0.64, "learning_rate": 9.895929291671854e-06, "loss": 0.0767, "step": 5180 }, { "epoch": 0.64, "learning_rate": 9.895680318685424e-06, "loss": 0.0568, "step": 5190 }, { "epoch": 0.65, "learning_rate": 9.895431345698993e-06, "loss": 0.0834, "step": 5200 }, { "epoch": 0.65, "learning_rate": 9.895182372712561e-06, "loss": 0.0671, "step": 5210 }, { "epoch": 0.65, "learning_rate": 9.894933399726131e-06, "loss": 0.0665, "step": 5220 }, { "epoch": 0.65, "learning_rate": 9.8946844267397e-06, "loss": 0.0615, "step": 5230 }, { "epoch": 0.65, "learning_rate": 9.894435453753268e-06, "loss": 0.0667, "step": 5240 }, { "epoch": 0.65, "learning_rate": 9.894186480766837e-06, "loss": 0.0939, "step": 5250 }, { "epoch": 0.65, "learning_rate": 9.893937507780407e-06, "loss": 0.063, "step": 5260 }, { "epoch": 0.65, "learning_rate": 9.893688534793976e-06, "loss": 0.0537, "step": 5270 }, { "epoch": 0.66, "learning_rate": 9.893439561807546e-06, "loss": 0.0679, "step": 5280 }, { "epoch": 0.66, "learning_rate": 9.893190588821113e-06, "loss": 0.0771, "step": 5290 }, { "epoch": 0.66, "learning_rate": 9.892941615834683e-06, "loss": 0.11, "step": 5300 }, { "epoch": 0.66, "learning_rate": 9.892692642848251e-06, "loss": 0.0943, "step": 5310 }, { "epoch": 0.66, "learning_rate": 9.892443669861822e-06, "loss": 0.0884, "step": 5320 }, { "epoch": 0.66, "learning_rate": 9.89219469687539e-06, "loss": 0.0723, "step": 5330 }, { "epoch": 0.66, "learning_rate": 9.891945723888959e-06, "loss": 0.0842, "step": 5340 }, { "epoch": 0.66, "learning_rate": 9.891696750902527e-06, "loss": 0.1021, "step": 5350 }, { "epoch": 0.67, "learning_rate": 9.891447777916097e-06, "loss": 0.1221, "step": 5360 }, { "epoch": 0.67, "learning_rate": 9.891198804929666e-06, "loss": 0.0907, "step": 5370 }, { "epoch": 0.67, "learning_rate": 9.890949831943234e-06, "loss": 0.0488, "step": 5380 }, { "epoch": 0.67, "learning_rate": 9.890700858956805e-06, "loss": 0.0622, "step": 5390 }, { "epoch": 0.67, "learning_rate": 9.890451885970373e-06, "loss": 0.1039, "step": 5400 }, { "epoch": 0.67, "learning_rate": 9.890202912983942e-06, "loss": 0.0877, "step": 5410 }, { "epoch": 0.67, "learning_rate": 9.88995393999751e-06, "loss": 0.1109, "step": 5420 }, { "epoch": 0.67, "learning_rate": 9.88970496701108e-06, "loss": 0.0615, "step": 5430 }, { "epoch": 0.68, "learning_rate": 9.889455994024649e-06, "loss": 0.0714, "step": 5440 }, { "epoch": 0.68, "learning_rate": 9.889207021038219e-06, "loss": 0.0929, "step": 5450 }, { "epoch": 0.68, "learning_rate": 9.888958048051788e-06, "loss": 0.0759, "step": 5460 }, { "epoch": 0.68, "learning_rate": 9.888709075065356e-06, "loss": 0.0541, "step": 5470 }, { "epoch": 0.68, "learning_rate": 9.888460102078925e-06, "loss": 0.0357, "step": 5480 }, { "epoch": 0.68, "learning_rate": 9.888211129092495e-06, "loss": 0.0874, "step": 5490 }, { "epoch": 0.68, "learning_rate": 9.887962156106063e-06, "loss": 0.0636, "step": 5500 }, { "epoch": 0.68, "learning_rate": 9.887713183119634e-06, "loss": 0.0888, "step": 5510 }, { "epoch": 0.69, "learning_rate": 9.887464210133202e-06, "loss": 0.0647, "step": 5520 }, { "epoch": 0.69, "learning_rate": 9.88721523714677e-06, "loss": 0.0815, "step": 5530 }, { "epoch": 0.69, "learning_rate": 9.886966264160339e-06, "loss": 0.079, "step": 5540 }, { "epoch": 0.69, "learning_rate": 9.88671729117391e-06, "loss": 0.065, "step": 5550 }, { "epoch": 0.69, "learning_rate": 9.886468318187478e-06, "loss": 0.0881, "step": 5560 }, { "epoch": 0.69, "learning_rate": 9.886219345201046e-06, "loss": 0.0759, "step": 5570 }, { "epoch": 0.69, "learning_rate": 9.885970372214615e-06, "loss": 0.0823, "step": 5580 }, { "epoch": 0.69, "learning_rate": 9.885721399228183e-06, "loss": 0.0859, "step": 5590 }, { "epoch": 0.7, "learning_rate": 9.885472426241754e-06, "loss": 0.0761, "step": 5600 }, { "epoch": 0.7, "learning_rate": 9.885223453255322e-06, "loss": 0.0927, "step": 5610 }, { "epoch": 0.7, "learning_rate": 9.884974480268892e-06, "loss": 0.087, "step": 5620 }, { "epoch": 0.7, "learning_rate": 9.88472550728246e-06, "loss": 0.0727, "step": 5630 }, { "epoch": 0.7, "learning_rate": 9.88447653429603e-06, "loss": 0.0641, "step": 5640 }, { "epoch": 0.7, "learning_rate": 9.884227561309598e-06, "loss": 0.0585, "step": 5650 }, { "epoch": 0.7, "learning_rate": 9.883978588323168e-06, "loss": 0.105, "step": 5660 }, { "epoch": 0.7, "learning_rate": 9.883729615336737e-06, "loss": 0.0928, "step": 5670 }, { "epoch": 0.71, "learning_rate": 9.883480642350307e-06, "loss": 0.0641, "step": 5680 }, { "epoch": 0.71, "learning_rate": 9.883231669363875e-06, "loss": 0.0966, "step": 5690 }, { "epoch": 0.71, "learning_rate": 9.882982696377444e-06, "loss": 0.0587, "step": 5700 }, { "epoch": 0.71, "learning_rate": 9.882733723391012e-06, "loss": 0.0924, "step": 5710 }, { "epoch": 0.71, "learning_rate": 9.882484750404583e-06, "loss": 0.0814, "step": 5720 }, { "epoch": 0.71, "learning_rate": 9.882235777418151e-06, "loss": 0.0725, "step": 5730 }, { "epoch": 0.71, "learning_rate": 9.88198680443172e-06, "loss": 0.0804, "step": 5740 }, { "epoch": 0.71, "learning_rate": 9.88173783144529e-06, "loss": 0.1092, "step": 5750 }, { "epoch": 0.72, "learning_rate": 9.881488858458858e-06, "loss": 0.0759, "step": 5760 }, { "epoch": 0.72, "learning_rate": 9.881239885472427e-06, "loss": 0.0424, "step": 5770 }, { "epoch": 0.72, "learning_rate": 9.880990912485995e-06, "loss": 0.1082, "step": 5780 }, { "epoch": 0.72, "learning_rate": 9.880741939499566e-06, "loss": 0.0756, "step": 5790 }, { "epoch": 0.72, "learning_rate": 9.880492966513134e-06, "loss": 0.0752, "step": 5800 }, { "epoch": 0.72, "learning_rate": 9.880243993526704e-06, "loss": 0.0787, "step": 5810 }, { "epoch": 0.72, "learning_rate": 9.879995020540271e-06, "loss": 0.0646, "step": 5820 }, { "epoch": 0.72, "learning_rate": 9.879746047553841e-06, "loss": 0.0563, "step": 5830 }, { "epoch": 0.73, "learning_rate": 9.87949707456741e-06, "loss": 0.0607, "step": 5840 }, { "epoch": 0.73, "learning_rate": 9.87924810158098e-06, "loss": 0.08, "step": 5850 }, { "epoch": 0.73, "learning_rate": 9.878999128594549e-06, "loss": 0.093, "step": 5860 }, { "epoch": 0.73, "learning_rate": 9.878750155608117e-06, "loss": 0.093, "step": 5870 }, { "epoch": 0.73, "learning_rate": 9.878501182621686e-06, "loss": 0.1159, "step": 5880 }, { "epoch": 0.73, "learning_rate": 9.878252209635256e-06, "loss": 0.0726, "step": 5890 }, { "epoch": 0.73, "learning_rate": 9.878003236648824e-06, "loss": 0.0753, "step": 5900 }, { "epoch": 0.73, "learning_rate": 9.877754263662393e-06, "loss": 0.0749, "step": 5910 }, { "epoch": 0.74, "learning_rate": 9.877505290675963e-06, "loss": 0.0676, "step": 5920 }, { "epoch": 0.74, "learning_rate": 9.877256317689532e-06, "loss": 0.0701, "step": 5930 }, { "epoch": 0.74, "learning_rate": 9.8770073447031e-06, "loss": 0.0674, "step": 5940 }, { "epoch": 0.74, "learning_rate": 9.876758371716669e-06, "loss": 0.0645, "step": 5950 }, { "epoch": 0.74, "learning_rate": 9.876509398730239e-06, "loss": 0.0902, "step": 5960 }, { "epoch": 0.74, "learning_rate": 9.876260425743807e-06, "loss": 0.0785, "step": 5970 }, { "epoch": 0.74, "learning_rate": 9.876011452757377e-06, "loss": 0.0766, "step": 5980 }, { "epoch": 0.74, "learning_rate": 9.875762479770946e-06, "loss": 0.0512, "step": 5990 }, { "epoch": 0.75, "learning_rate": 9.875513506784515e-06, "loss": 0.0777, "step": 6000 }, { "epoch": 0.75, "learning_rate": 9.875264533798083e-06, "loss": 0.0655, "step": 6010 }, { "epoch": 0.75, "learning_rate": 9.875015560811653e-06, "loss": 0.0804, "step": 6020 }, { "epoch": 0.75, "learning_rate": 9.874766587825222e-06, "loss": 0.067, "step": 6030 }, { "epoch": 0.75, "learning_rate": 9.874517614838792e-06, "loss": 0.0747, "step": 6040 }, { "epoch": 0.75, "learning_rate": 9.87426864185236e-06, "loss": 0.0783, "step": 6050 }, { "epoch": 0.75, "learning_rate": 9.874019668865929e-06, "loss": 0.086, "step": 6060 }, { "epoch": 0.75, "learning_rate": 9.873770695879498e-06, "loss": 0.0975, "step": 6070 }, { "epoch": 0.75, "learning_rate": 9.873521722893066e-06, "loss": 0.0687, "step": 6080 }, { "epoch": 0.76, "learning_rate": 9.873272749906636e-06, "loss": 0.0795, "step": 6090 }, { "epoch": 0.76, "learning_rate": 9.873023776920205e-06, "loss": 0.055, "step": 6100 }, { "epoch": 0.76, "learning_rate": 9.872774803933775e-06, "loss": 0.097, "step": 6110 }, { "epoch": 0.76, "learning_rate": 9.872525830947342e-06, "loss": 0.0651, "step": 6120 }, { "epoch": 0.76, "learning_rate": 9.872276857960912e-06, "loss": 0.0603, "step": 6130 }, { "epoch": 0.76, "learning_rate": 9.87202788497448e-06, "loss": 0.094, "step": 6140 }, { "epoch": 0.76, "learning_rate": 9.87177891198805e-06, "loss": 0.0935, "step": 6150 }, { "epoch": 0.76, "learning_rate": 9.87152993900162e-06, "loss": 0.0817, "step": 6160 }, { "epoch": 0.77, "learning_rate": 9.87128096601519e-06, "loss": 0.0534, "step": 6170 }, { "epoch": 0.77, "learning_rate": 9.871031993028756e-06, "loss": 0.0645, "step": 6180 }, { "epoch": 0.77, "learning_rate": 9.870783020042326e-06, "loss": 0.0585, "step": 6190 }, { "epoch": 0.77, "learning_rate": 9.870534047055895e-06, "loss": 0.0537, "step": 6200 }, { "epoch": 0.77, "learning_rate": 9.870285074069465e-06, "loss": 0.1018, "step": 6210 }, { "epoch": 0.77, "learning_rate": 9.870036101083034e-06, "loss": 0.0956, "step": 6220 }, { "epoch": 0.77, "learning_rate": 9.869787128096602e-06, "loss": 0.0769, "step": 6230 }, { "epoch": 0.77, "learning_rate": 9.86953815511017e-06, "loss": 0.0801, "step": 6240 }, { "epoch": 0.78, "learning_rate": 9.869289182123741e-06, "loss": 0.0716, "step": 6250 }, { "epoch": 0.78, "learning_rate": 9.86904020913731e-06, "loss": 0.0785, "step": 6260 }, { "epoch": 0.78, "learning_rate": 9.868791236150878e-06, "loss": 0.0826, "step": 6270 }, { "epoch": 0.78, "learning_rate": 9.868542263164448e-06, "loss": 0.0786, "step": 6280 }, { "epoch": 0.78, "learning_rate": 9.868293290178017e-06, "loss": 0.064, "step": 6290 }, { "epoch": 0.78, "learning_rate": 9.868044317191585e-06, "loss": 0.0878, "step": 6300 }, { "epoch": 0.78, "learning_rate": 9.867795344205154e-06, "loss": 0.0836, "step": 6310 }, { "epoch": 0.78, "learning_rate": 9.867546371218724e-06, "loss": 0.0823, "step": 6320 }, { "epoch": 0.79, "learning_rate": 9.867297398232292e-06, "loss": 0.0781, "step": 6330 }, { "epoch": 0.79, "learning_rate": 9.867048425245863e-06, "loss": 0.1134, "step": 6340 }, { "epoch": 0.79, "learning_rate": 9.86679945225943e-06, "loss": 0.1272, "step": 6350 }, { "epoch": 0.79, "learning_rate": 9.866550479273e-06, "loss": 0.0698, "step": 6360 }, { "epoch": 0.79, "learning_rate": 9.866301506286568e-06, "loss": 0.0946, "step": 6370 }, { "epoch": 0.79, "learning_rate": 9.866052533300138e-06, "loss": 0.0511, "step": 6380 }, { "epoch": 0.79, "learning_rate": 9.865803560313707e-06, "loss": 0.0867, "step": 6390 }, { "epoch": 0.79, "learning_rate": 9.865554587327275e-06, "loss": 0.0897, "step": 6400 }, { "epoch": 0.8, "learning_rate": 9.865305614340844e-06, "loss": 0.074, "step": 6410 }, { "epoch": 0.8, "learning_rate": 9.865056641354414e-06, "loss": 0.0675, "step": 6420 }, { "epoch": 0.8, "learning_rate": 9.864807668367983e-06, "loss": 0.0868, "step": 6430 }, { "epoch": 0.8, "learning_rate": 9.864558695381551e-06, "loss": 0.0673, "step": 6440 }, { "epoch": 0.8, "learning_rate": 9.864309722395121e-06, "loss": 0.0521, "step": 6450 }, { "epoch": 0.8, "learning_rate": 9.86406074940869e-06, "loss": 0.107, "step": 6460 }, { "epoch": 0.8, "learning_rate": 9.863811776422258e-06, "loss": 0.0737, "step": 6470 }, { "epoch": 0.8, "learning_rate": 9.863562803435827e-06, "loss": 0.0729, "step": 6480 }, { "epoch": 0.81, "learning_rate": 9.863313830449397e-06, "loss": 0.0579, "step": 6490 }, { "epoch": 0.81, "learning_rate": 9.863064857462966e-06, "loss": 0.0688, "step": 6500 }, { "epoch": 0.81, "learning_rate": 9.862815884476536e-06, "loss": 0.0707, "step": 6510 }, { "epoch": 0.81, "learning_rate": 9.862566911490104e-06, "loss": 0.1067, "step": 6520 }, { "epoch": 0.81, "learning_rate": 9.862317938503673e-06, "loss": 0.0563, "step": 6530 }, { "epoch": 0.81, "learning_rate": 9.862068965517241e-06, "loss": 0.0914, "step": 6540 }, { "epoch": 0.81, "learning_rate": 9.861819992530812e-06, "loss": 0.0561, "step": 6550 }, { "epoch": 0.81, "learning_rate": 9.86157101954438e-06, "loss": 0.0986, "step": 6560 }, { "epoch": 0.82, "learning_rate": 9.861322046557949e-06, "loss": 0.1021, "step": 6570 }, { "epoch": 0.82, "learning_rate": 9.861073073571519e-06, "loss": 0.1305, "step": 6580 }, { "epoch": 0.82, "learning_rate": 9.860824100585087e-06, "loss": 0.0662, "step": 6590 }, { "epoch": 0.82, "learning_rate": 9.860575127598656e-06, "loss": 0.0806, "step": 6600 }, { "epoch": 0.82, "learning_rate": 9.860326154612224e-06, "loss": 0.0819, "step": 6610 }, { "epoch": 0.82, "learning_rate": 9.860077181625795e-06, "loss": 0.0501, "step": 6620 }, { "epoch": 0.82, "learning_rate": 9.859828208639363e-06, "loss": 0.0969, "step": 6630 }, { "epoch": 0.82, "learning_rate": 9.859579235652933e-06, "loss": 0.0766, "step": 6640 }, { "epoch": 0.83, "learning_rate": 9.8593302626665e-06, "loss": 0.0708, "step": 6650 }, { "epoch": 0.83, "learning_rate": 9.85908128968007e-06, "loss": 0.0671, "step": 6660 }, { "epoch": 0.83, "learning_rate": 9.858832316693639e-06, "loss": 0.0716, "step": 6670 }, { "epoch": 0.83, "learning_rate": 9.85858334370721e-06, "loss": 0.0598, "step": 6680 }, { "epoch": 0.83, "learning_rate": 9.858334370720778e-06, "loss": 0.0661, "step": 6690 }, { "epoch": 0.83, "learning_rate": 9.858085397734348e-06, "loss": 0.0857, "step": 6700 }, { "epoch": 0.83, "learning_rate": 9.857836424747915e-06, "loss": 0.0521, "step": 6710 }, { "epoch": 0.83, "learning_rate": 9.857587451761485e-06, "loss": 0.0857, "step": 6720 }, { "epoch": 0.84, "learning_rate": 9.857338478775053e-06, "loss": 0.0553, "step": 6730 }, { "epoch": 0.84, "learning_rate": 9.857089505788624e-06, "loss": 0.0725, "step": 6740 }, { "epoch": 0.84, "learning_rate": 9.856840532802192e-06, "loss": 0.0806, "step": 6750 }, { "epoch": 0.84, "learning_rate": 9.85659155981576e-06, "loss": 0.0742, "step": 6760 }, { "epoch": 0.84, "learning_rate": 9.85634258682933e-06, "loss": 0.0683, "step": 6770 }, { "epoch": 0.84, "learning_rate": 9.8560936138429e-06, "loss": 0.1037, "step": 6780 }, { "epoch": 0.84, "learning_rate": 9.855844640856468e-06, "loss": 0.0829, "step": 6790 }, { "epoch": 0.84, "learning_rate": 9.855595667870036e-06, "loss": 0.092, "step": 6800 }, { "epoch": 0.85, "learning_rate": 9.855346694883607e-06, "loss": 0.0589, "step": 6810 }, { "epoch": 0.85, "learning_rate": 9.855097721897175e-06, "loss": 0.082, "step": 6820 }, { "epoch": 0.85, "learning_rate": 9.854848748910744e-06, "loss": 0.1162, "step": 6830 }, { "epoch": 0.85, "learning_rate": 9.854599775924312e-06, "loss": 0.0791, "step": 6840 }, { "epoch": 0.85, "learning_rate": 9.854350802937882e-06, "loss": 0.086, "step": 6850 }, { "epoch": 0.85, "learning_rate": 9.854101829951451e-06, "loss": 0.0598, "step": 6860 }, { "epoch": 0.85, "learning_rate": 9.853852856965021e-06, "loss": 0.0742, "step": 6870 }, { "epoch": 0.85, "learning_rate": 9.853603883978588e-06, "loss": 0.0603, "step": 6880 }, { "epoch": 0.86, "learning_rate": 9.853354910992158e-06, "loss": 0.0815, "step": 6890 }, { "epoch": 0.86, "learning_rate": 9.853105938005727e-06, "loss": 0.0474, "step": 6900 }, { "epoch": 0.86, "learning_rate": 9.852856965019297e-06, "loss": 0.0641, "step": 6910 }, { "epoch": 0.86, "learning_rate": 9.852607992032865e-06, "loss": 0.0569, "step": 6920 }, { "epoch": 0.86, "learning_rate": 9.852359019046434e-06, "loss": 0.0546, "step": 6930 }, { "epoch": 0.86, "learning_rate": 9.852110046060002e-06, "loss": 0.0893, "step": 6940 }, { "epoch": 0.86, "learning_rate": 9.851861073073573e-06, "loss": 0.0868, "step": 6950 }, { "epoch": 0.86, "learning_rate": 9.851612100087141e-06, "loss": 0.0771, "step": 6960 }, { "epoch": 0.87, "learning_rate": 9.85136312710071e-06, "loss": 0.0694, "step": 6970 }, { "epoch": 0.87, "learning_rate": 9.85111415411428e-06, "loss": 0.0601, "step": 6980 }, { "epoch": 0.87, "learning_rate": 9.850865181127848e-06, "loss": 0.0411, "step": 6990 }, { "epoch": 0.87, "learning_rate": 9.850616208141417e-06, "loss": 0.084, "step": 7000 }, { "epoch": 0.87, "learning_rate": 9.850367235154985e-06, "loss": 0.0633, "step": 7010 }, { "epoch": 0.87, "learning_rate": 9.850118262168556e-06, "loss": 0.0571, "step": 7020 }, { "epoch": 0.87, "learning_rate": 9.849869289182124e-06, "loss": 0.0501, "step": 7030 }, { "epoch": 0.87, "learning_rate": 9.849620316195694e-06, "loss": 0.0449, "step": 7040 }, { "epoch": 0.88, "learning_rate": 9.849371343209263e-06, "loss": 0.0832, "step": 7050 }, { "epoch": 0.88, "learning_rate": 9.849122370222831e-06, "loss": 0.0803, "step": 7060 }, { "epoch": 0.88, "learning_rate": 9.8488733972364e-06, "loss": 0.0679, "step": 7070 }, { "epoch": 0.88, "learning_rate": 9.84862442424997e-06, "loss": 0.0681, "step": 7080 }, { "epoch": 0.88, "learning_rate": 9.848375451263539e-06, "loss": 0.0918, "step": 7090 }, { "epoch": 0.88, "learning_rate": 9.848126478277107e-06, "loss": 0.0592, "step": 7100 }, { "epoch": 0.88, "learning_rate": 9.847877505290677e-06, "loss": 0.1029, "step": 7110 }, { "epoch": 0.88, "learning_rate": 9.847628532304246e-06, "loss": 0.0653, "step": 7120 }, { "epoch": 0.89, "learning_rate": 9.847379559317814e-06, "loss": 0.0955, "step": 7130 }, { "epoch": 0.89, "learning_rate": 9.847130586331383e-06, "loss": 0.0481, "step": 7140 }, { "epoch": 0.89, "learning_rate": 9.846881613344953e-06, "loss": 0.0578, "step": 7150 }, { "epoch": 0.89, "learning_rate": 9.846632640358522e-06, "loss": 0.0679, "step": 7160 }, { "epoch": 0.89, "learning_rate": 9.846383667372092e-06, "loss": 0.0702, "step": 7170 }, { "epoch": 0.89, "learning_rate": 9.846134694385659e-06, "loss": 0.0696, "step": 7180 }, { "epoch": 0.89, "learning_rate": 9.845885721399229e-06, "loss": 0.0966, "step": 7190 }, { "epoch": 0.89, "learning_rate": 9.845636748412797e-06, "loss": 0.0763, "step": 7200 }, { "epoch": 0.9, "learning_rate": 9.845387775426368e-06, "loss": 0.0786, "step": 7210 }, { "epoch": 0.9, "learning_rate": 9.845138802439936e-06, "loss": 0.0792, "step": 7220 }, { "epoch": 0.9, "learning_rate": 9.844889829453506e-06, "loss": 0.0646, "step": 7230 }, { "epoch": 0.9, "learning_rate": 9.844640856467073e-06, "loss": 0.0624, "step": 7240 }, { "epoch": 0.9, "learning_rate": 9.844391883480643e-06, "loss": 0.0838, "step": 7250 }, { "epoch": 0.9, "learning_rate": 9.844142910494212e-06, "loss": 0.0735, "step": 7260 }, { "epoch": 0.9, "learning_rate": 9.843893937507782e-06, "loss": 0.0707, "step": 7270 }, { "epoch": 0.9, "learning_rate": 9.84364496452135e-06, "loss": 0.0909, "step": 7280 }, { "epoch": 0.91, "learning_rate": 9.843395991534919e-06, "loss": 0.0819, "step": 7290 }, { "epoch": 0.91, "learning_rate": 9.843147018548488e-06, "loss": 0.0602, "step": 7300 }, { "epoch": 0.91, "learning_rate": 9.842898045562058e-06, "loss": 0.0753, "step": 7310 }, { "epoch": 0.91, "learning_rate": 9.842649072575626e-06, "loss": 0.0911, "step": 7320 }, { "epoch": 0.91, "learning_rate": 9.842400099589195e-06, "loss": 0.0539, "step": 7330 }, { "epoch": 0.91, "learning_rate": 9.842151126602765e-06, "loss": 0.075, "step": 7340 }, { "epoch": 0.91, "learning_rate": 9.841902153616334e-06, "loss": 0.082, "step": 7350 }, { "epoch": 0.91, "learning_rate": 9.841653180629902e-06, "loss": 0.0667, "step": 7360 }, { "epoch": 0.92, "learning_rate": 9.84140420764347e-06, "loss": 0.0668, "step": 7370 }, { "epoch": 0.92, "learning_rate": 9.84115523465704e-06, "loss": 0.0781, "step": 7380 }, { "epoch": 0.92, "learning_rate": 9.84090626167061e-06, "loss": 0.0874, "step": 7390 }, { "epoch": 0.92, "learning_rate": 9.84065728868418e-06, "loss": 0.0596, "step": 7400 }, { "epoch": 0.92, "learning_rate": 9.840408315697748e-06, "loss": 0.0686, "step": 7410 }, { "epoch": 0.92, "learning_rate": 9.840159342711317e-06, "loss": 0.0763, "step": 7420 }, { "epoch": 0.92, "learning_rate": 9.839910369724885e-06, "loss": 0.0582, "step": 7430 }, { "epoch": 0.92, "learning_rate": 9.839661396738455e-06, "loss": 0.0757, "step": 7440 }, { "epoch": 0.93, "learning_rate": 9.839412423752024e-06, "loss": 0.0353, "step": 7450 }, { "epoch": 0.93, "learning_rate": 9.839163450765592e-06, "loss": 0.088, "step": 7460 }, { "epoch": 0.93, "learning_rate": 9.838914477779163e-06, "loss": 0.0719, "step": 7470 }, { "epoch": 0.93, "learning_rate": 9.838665504792731e-06, "loss": 0.0967, "step": 7480 }, { "epoch": 0.93, "learning_rate": 9.8384165318063e-06, "loss": 0.0617, "step": 7490 }, { "epoch": 0.93, "learning_rate": 9.838167558819868e-06, "loss": 0.0726, "step": 7500 }, { "epoch": 0.93, "learning_rate": 9.837918585833438e-06, "loss": 0.1053, "step": 7510 }, { "epoch": 0.93, "learning_rate": 9.837669612847007e-06, "loss": 0.1011, "step": 7520 }, { "epoch": 0.93, "learning_rate": 9.837420639860575e-06, "loss": 0.093, "step": 7530 }, { "epoch": 0.94, "learning_rate": 9.837171666874144e-06, "loss": 0.0961, "step": 7540 }, { "epoch": 0.94, "learning_rate": 9.836922693887714e-06, "loss": 0.0559, "step": 7550 }, { "epoch": 0.94, "learning_rate": 9.836673720901283e-06, "loss": 0.0714, "step": 7560 }, { "epoch": 0.94, "learning_rate": 9.836424747914853e-06, "loss": 0.0513, "step": 7570 }, { "epoch": 0.94, "learning_rate": 9.836175774928421e-06, "loss": 0.0762, "step": 7580 }, { "epoch": 0.94, "learning_rate": 9.83592680194199e-06, "loss": 0.0481, "step": 7590 }, { "epoch": 0.94, "learning_rate": 9.835677828955558e-06, "loss": 0.0848, "step": 7600 }, { "epoch": 0.94, "learning_rate": 9.835428855969129e-06, "loss": 0.1127, "step": 7610 }, { "epoch": 0.95, "learning_rate": 9.835179882982697e-06, "loss": 0.0858, "step": 7620 }, { "epoch": 0.95, "learning_rate": 9.834930909996266e-06, "loss": 0.092, "step": 7630 }, { "epoch": 0.95, "learning_rate": 9.834681937009836e-06, "loss": 0.0685, "step": 7640 }, { "epoch": 0.95, "learning_rate": 9.834432964023404e-06, "loss": 0.0808, "step": 7650 }, { "epoch": 0.95, "learning_rate": 9.834183991036973e-06, "loss": 0.0975, "step": 7660 }, { "epoch": 0.95, "learning_rate": 9.833935018050541e-06, "loss": 0.089, "step": 7670 }, { "epoch": 0.95, "learning_rate": 9.833686045064112e-06, "loss": 0.0541, "step": 7680 }, { "epoch": 0.95, "learning_rate": 9.83343707207768e-06, "loss": 0.0609, "step": 7690 }, { "epoch": 0.96, "learning_rate": 9.83318809909125e-06, "loss": 0.0921, "step": 7700 }, { "epoch": 0.96, "learning_rate": 9.832939126104817e-06, "loss": 0.0706, "step": 7710 }, { "epoch": 0.96, "learning_rate": 9.832690153118387e-06, "loss": 0.0618, "step": 7720 }, { "epoch": 0.96, "learning_rate": 9.832441180131956e-06, "loss": 0.0484, "step": 7730 }, { "epoch": 0.96, "learning_rate": 9.832192207145526e-06, "loss": 0.0814, "step": 7740 }, { "epoch": 0.96, "learning_rate": 9.831943234159095e-06, "loss": 0.0936, "step": 7750 }, { "epoch": 0.96, "learning_rate": 9.831694261172665e-06, "loss": 0.0766, "step": 7760 }, { "epoch": 0.96, "learning_rate": 9.831445288186232e-06, "loss": 0.0817, "step": 7770 }, { "epoch": 0.97, "learning_rate": 9.831196315199802e-06, "loss": 0.0924, "step": 7780 }, { "epoch": 0.97, "learning_rate": 9.83094734221337e-06, "loss": 0.0533, "step": 7790 }, { "epoch": 0.97, "learning_rate": 9.83069836922694e-06, "loss": 0.0863, "step": 7800 }, { "epoch": 0.97, "learning_rate": 9.830449396240509e-06, "loss": 0.0867, "step": 7810 }, { "epoch": 0.97, "learning_rate": 9.830200423254078e-06, "loss": 0.0557, "step": 7820 }, { "epoch": 0.97, "learning_rate": 9.829951450267646e-06, "loss": 0.0719, "step": 7830 }, { "epoch": 0.97, "learning_rate": 9.829702477281216e-06, "loss": 0.0747, "step": 7840 }, { "epoch": 0.97, "learning_rate": 9.829453504294785e-06, "loss": 0.0774, "step": 7850 }, { "epoch": 0.98, "learning_rate": 9.829204531308353e-06, "loss": 0.0885, "step": 7860 }, { "epoch": 0.98, "learning_rate": 9.828955558321924e-06, "loss": 0.0891, "step": 7870 }, { "epoch": 0.98, "learning_rate": 9.828706585335492e-06, "loss": 0.0601, "step": 7880 }, { "epoch": 0.98, "learning_rate": 9.82845761234906e-06, "loss": 0.0944, "step": 7890 }, { "epoch": 0.98, "learning_rate": 9.828208639362629e-06, "loss": 0.0974, "step": 7900 }, { "epoch": 0.98, "learning_rate": 9.8279596663762e-06, "loss": 0.0896, "step": 7910 }, { "epoch": 0.98, "learning_rate": 9.827710693389768e-06, "loss": 0.073, "step": 7920 }, { "epoch": 0.98, "learning_rate": 9.827461720403338e-06, "loss": 0.0946, "step": 7930 }, { "epoch": 0.99, "learning_rate": 9.827212747416907e-06, "loss": 0.0546, "step": 7940 }, { "epoch": 0.99, "learning_rate": 9.826963774430475e-06, "loss": 0.0807, "step": 7950 }, { "epoch": 0.99, "learning_rate": 9.826714801444044e-06, "loss": 0.07, "step": 7960 }, { "epoch": 0.99, "learning_rate": 9.826465828457614e-06, "loss": 0.0932, "step": 7970 }, { "epoch": 0.99, "learning_rate": 9.826216855471182e-06, "loss": 0.0642, "step": 7980 }, { "epoch": 0.99, "learning_rate": 9.82596788248475e-06, "loss": 0.0567, "step": 7990 }, { "epoch": 0.99, "learning_rate": 9.825718909498321e-06, "loss": 0.0994, "step": 8000 }, { "epoch": 0.99, "learning_rate": 9.82546993651189e-06, "loss": 0.0681, "step": 8010 }, { "epoch": 1.0, "learning_rate": 9.825220963525458e-06, "loss": 0.1029, "step": 8020 }, { "epoch": 1.0, "learning_rate": 9.824971990539027e-06, "loss": 0.084, "step": 8030 }, { "epoch": 1.0, "learning_rate": 9.824723017552597e-06, "loss": 0.0859, "step": 8040 }, { "epoch": 1.0, "learning_rate": 9.824474044566165e-06, "loss": 0.0685, "step": 8050 }, { "epoch": 1.0, "learning_rate": 9.824225071579735e-06, "loss": 0.0815, "step": 8060 }, { "epoch": 1.0, "learning_rate": 9.823976098593302e-06, "loss": 0.1321, "step": 8070 }, { "epoch": 1.0, "learning_rate": 9.823727125606873e-06, "loss": 0.0747, "step": 8080 }, { "epoch": 1.0, "learning_rate": 9.823478152620441e-06, "loss": 0.0967, "step": 8090 }, { "epoch": 1.01, "learning_rate": 9.823229179634011e-06, "loss": 0.064, "step": 8100 }, { "epoch": 1.01, "learning_rate": 9.82298020664758e-06, "loss": 0.1167, "step": 8110 }, { "epoch": 1.01, "learning_rate": 9.822731233661148e-06, "loss": 0.0595, "step": 8120 }, { "epoch": 1.01, "learning_rate": 9.822482260674717e-06, "loss": 0.0709, "step": 8130 }, { "epoch": 1.01, "learning_rate": 9.822233287688287e-06, "loss": 0.061, "step": 8140 }, { "epoch": 1.01, "learning_rate": 9.821984314701856e-06, "loss": 0.0549, "step": 8150 }, { "epoch": 1.01, "learning_rate": 9.821735341715424e-06, "loss": 0.0524, "step": 8160 }, { "epoch": 1.01, "learning_rate": 9.821486368728994e-06, "loss": 0.0665, "step": 8170 }, { "epoch": 1.02, "learning_rate": 9.821237395742563e-06, "loss": 0.0656, "step": 8180 }, { "epoch": 1.02, "learning_rate": 9.820988422756131e-06, "loss": 0.0633, "step": 8190 }, { "epoch": 1.02, "learning_rate": 9.8207394497697e-06, "loss": 0.0626, "step": 8200 }, { "epoch": 1.02, "learning_rate": 9.82049047678327e-06, "loss": 0.0794, "step": 8210 }, { "epoch": 1.02, "learning_rate": 9.820241503796839e-06, "loss": 0.1028, "step": 8220 }, { "epoch": 1.02, "learning_rate": 9.819992530810409e-06, "loss": 0.0931, "step": 8230 }, { "epoch": 1.02, "learning_rate": 9.819743557823976e-06, "loss": 0.0734, "step": 8240 }, { "epoch": 1.02, "learning_rate": 9.819494584837546e-06, "loss": 0.0749, "step": 8250 }, { "epoch": 1.03, "learning_rate": 9.819245611851114e-06, "loss": 0.0655, "step": 8260 }, { "epoch": 1.03, "learning_rate": 9.818996638864684e-06, "loss": 0.1237, "step": 8270 }, { "epoch": 1.03, "learning_rate": 9.818747665878253e-06, "loss": 0.0613, "step": 8280 }, { "epoch": 1.03, "learning_rate": 9.818498692891823e-06, "loss": 0.1092, "step": 8290 }, { "epoch": 1.03, "learning_rate": 9.81824971990539e-06, "loss": 0.0656, "step": 8300 }, { "epoch": 1.03, "learning_rate": 9.81800074691896e-06, "loss": 0.0973, "step": 8310 }, { "epoch": 1.03, "learning_rate": 9.817751773932529e-06, "loss": 0.0655, "step": 8320 }, { "epoch": 1.03, "learning_rate": 9.817502800946099e-06, "loss": 0.0611, "step": 8330 }, { "epoch": 1.04, "learning_rate": 9.817253827959667e-06, "loss": 0.0527, "step": 8340 }, { "epoch": 1.04, "learning_rate": 9.817004854973236e-06, "loss": 0.0409, "step": 8350 }, { "epoch": 1.04, "learning_rate": 9.816755881986805e-06, "loss": 0.0852, "step": 8360 }, { "epoch": 1.04, "learning_rate": 9.816506909000375e-06, "loss": 0.0816, "step": 8370 }, { "epoch": 1.04, "learning_rate": 9.816257936013943e-06, "loss": 0.1015, "step": 8380 }, { "epoch": 1.04, "learning_rate": 9.816008963027512e-06, "loss": 0.0669, "step": 8390 }, { "epoch": 1.04, "learning_rate": 9.815759990041082e-06, "loss": 0.0621, "step": 8400 }, { "epoch": 1.04, "learning_rate": 9.81551101705465e-06, "loss": 0.0422, "step": 8410 }, { "epoch": 1.05, "learning_rate": 9.815262044068219e-06, "loss": 0.0596, "step": 8420 }, { "epoch": 1.05, "learning_rate": 9.815013071081788e-06, "loss": 0.0474, "step": 8430 }, { "epoch": 1.05, "learning_rate": 9.814764098095358e-06, "loss": 0.0631, "step": 8440 }, { "epoch": 1.05, "learning_rate": 9.814515125108926e-06, "loss": 0.0657, "step": 8450 }, { "epoch": 1.05, "learning_rate": 9.814266152122496e-06, "loss": 0.053, "step": 8460 }, { "epoch": 1.05, "learning_rate": 9.814017179136065e-06, "loss": 0.0545, "step": 8470 }, { "epoch": 1.05, "learning_rate": 9.813768206149633e-06, "loss": 0.0569, "step": 8480 }, { "epoch": 1.05, "learning_rate": 9.813519233163202e-06, "loss": 0.0883, "step": 8490 }, { "epoch": 1.06, "learning_rate": 9.813270260176772e-06, "loss": 0.0679, "step": 8500 }, { "epoch": 1.06, "learning_rate": 9.81302128719034e-06, "loss": 0.0593, "step": 8510 }, { "epoch": 1.06, "learning_rate": 9.81277231420391e-06, "loss": 0.0753, "step": 8520 }, { "epoch": 1.06, "learning_rate": 9.81252334121748e-06, "loss": 0.0363, "step": 8530 }, { "epoch": 1.06, "learning_rate": 9.812274368231048e-06, "loss": 0.0706, "step": 8540 }, { "epoch": 1.06, "learning_rate": 9.812025395244616e-06, "loss": 0.0862, "step": 8550 }, { "epoch": 1.06, "learning_rate": 9.811776422258185e-06, "loss": 0.062, "step": 8560 }, { "epoch": 1.06, "learning_rate": 9.811527449271755e-06, "loss": 0.0766, "step": 8570 }, { "epoch": 1.07, "learning_rate": 9.811278476285324e-06, "loss": 0.1094, "step": 8580 }, { "epoch": 1.07, "learning_rate": 9.811029503298894e-06, "loss": 0.0787, "step": 8590 }, { "epoch": 1.07, "learning_rate": 9.81078053031246e-06, "loss": 0.0408, "step": 8600 }, { "epoch": 1.07, "learning_rate": 9.810531557326031e-06, "loss": 0.0936, "step": 8610 }, { "epoch": 1.07, "learning_rate": 9.8102825843396e-06, "loss": 0.065, "step": 8620 }, { "epoch": 1.07, "learning_rate": 9.81003361135317e-06, "loss": 0.0752, "step": 8630 }, { "epoch": 1.07, "learning_rate": 9.809784638366738e-06, "loss": 0.0632, "step": 8640 }, { "epoch": 1.07, "learning_rate": 9.809535665380307e-06, "loss": 0.077, "step": 8650 }, { "epoch": 1.08, "learning_rate": 9.809286692393875e-06, "loss": 0.0668, "step": 8660 }, { "epoch": 1.08, "learning_rate": 9.809037719407445e-06, "loss": 0.0794, "step": 8670 }, { "epoch": 1.08, "learning_rate": 9.808788746421014e-06, "loss": 0.0446, "step": 8680 }, { "epoch": 1.08, "learning_rate": 9.808539773434582e-06, "loss": 0.0944, "step": 8690 }, { "epoch": 1.08, "learning_rate": 9.808290800448153e-06, "loss": 0.054, "step": 8700 }, { "epoch": 1.08, "learning_rate": 9.808041827461721e-06, "loss": 0.0676, "step": 8710 }, { "epoch": 1.08, "learning_rate": 9.80779285447529e-06, "loss": 0.1196, "step": 8720 }, { "epoch": 1.08, "learning_rate": 9.807543881488858e-06, "loss": 0.1013, "step": 8730 }, { "epoch": 1.09, "learning_rate": 9.807294908502428e-06, "loss": 0.0424, "step": 8740 }, { "epoch": 1.09, "learning_rate": 9.807045935515997e-06, "loss": 0.0995, "step": 8750 }, { "epoch": 1.09, "learning_rate": 9.806796962529567e-06, "loss": 0.113, "step": 8760 }, { "epoch": 1.09, "learning_rate": 9.806547989543136e-06, "loss": 0.0751, "step": 8770 }, { "epoch": 1.09, "learning_rate": 9.806299016556704e-06, "loss": 0.1079, "step": 8780 }, { "epoch": 1.09, "learning_rate": 9.806050043570273e-06, "loss": 0.0733, "step": 8790 }, { "epoch": 1.09, "learning_rate": 9.805801070583843e-06, "loss": 0.0794, "step": 8800 }, { "epoch": 1.09, "learning_rate": 9.805552097597411e-06, "loss": 0.0835, "step": 8810 }, { "epoch": 1.1, "learning_rate": 9.805303124610982e-06, "loss": 0.0777, "step": 8820 }, { "epoch": 1.1, "learning_rate": 9.805054151624548e-06, "loss": 0.052, "step": 8830 }, { "epoch": 1.1, "learning_rate": 9.804805178638119e-06, "loss": 0.0597, "step": 8840 }, { "epoch": 1.1, "learning_rate": 9.804556205651687e-06, "loss": 0.072, "step": 8850 }, { "epoch": 1.1, "learning_rate": 9.804307232665257e-06, "loss": 0.0699, "step": 8860 }, { "epoch": 1.1, "learning_rate": 9.804058259678826e-06, "loss": 0.0745, "step": 8870 }, { "epoch": 1.1, "learning_rate": 9.803809286692394e-06, "loss": 0.0396, "step": 8880 }, { "epoch": 1.1, "learning_rate": 9.803560313705963e-06, "loss": 0.0611, "step": 8890 }, { "epoch": 1.11, "learning_rate": 9.803311340719533e-06, "loss": 0.1048, "step": 8900 }, { "epoch": 1.11, "learning_rate": 9.803062367733102e-06, "loss": 0.0579, "step": 8910 }, { "epoch": 1.11, "learning_rate": 9.80281339474667e-06, "loss": 0.0645, "step": 8920 }, { "epoch": 1.11, "learning_rate": 9.80256442176024e-06, "loss": 0.0586, "step": 8930 }, { "epoch": 1.11, "learning_rate": 9.802315448773809e-06, "loss": 0.0656, "step": 8940 }, { "epoch": 1.11, "learning_rate": 9.802066475787377e-06, "loss": 0.0483, "step": 8950 }, { "epoch": 1.11, "learning_rate": 9.801817502800946e-06, "loss": 0.0648, "step": 8960 }, { "epoch": 1.11, "learning_rate": 9.801568529814516e-06, "loss": 0.0659, "step": 8970 }, { "epoch": 1.12, "learning_rate": 9.801319556828085e-06, "loss": 0.0725, "step": 8980 }, { "epoch": 1.12, "learning_rate": 9.801070583841655e-06, "loss": 0.0887, "step": 8990 }, { "epoch": 1.12, "learning_rate": 9.800821610855223e-06, "loss": 0.0938, "step": 9000 }, { "epoch": 1.12, "learning_rate": 9.800572637868792e-06, "loss": 0.1132, "step": 9010 }, { "epoch": 1.12, "learning_rate": 9.80032366488236e-06, "loss": 0.0791, "step": 9020 }, { "epoch": 1.12, "learning_rate": 9.80007469189593e-06, "loss": 0.0884, "step": 9030 }, { "epoch": 1.12, "learning_rate": 9.7998257189095e-06, "loss": 0.0662, "step": 9040 }, { "epoch": 1.12, "learning_rate": 9.799576745923068e-06, "loss": 0.0947, "step": 9050 }, { "epoch": 1.13, "learning_rate": 9.799327772936638e-06, "loss": 0.0713, "step": 9060 }, { "epoch": 1.13, "learning_rate": 9.799078799950206e-06, "loss": 0.0543, "step": 9070 }, { "epoch": 1.13, "learning_rate": 9.798829826963775e-06, "loss": 0.0526, "step": 9080 }, { "epoch": 1.13, "learning_rate": 9.798580853977343e-06, "loss": 0.0488, "step": 9090 }, { "epoch": 1.13, "learning_rate": 9.798331880990914e-06, "loss": 0.0864, "step": 9100 }, { "epoch": 1.13, "learning_rate": 9.798082908004482e-06, "loss": 0.0569, "step": 9110 }, { "epoch": 1.13, "learning_rate": 9.797833935018052e-06, "loss": 0.0884, "step": 9120 }, { "epoch": 1.13, "learning_rate": 9.79758496203162e-06, "loss": 0.099, "step": 9130 }, { "epoch": 1.13, "learning_rate": 9.79733598904519e-06, "loss": 0.0648, "step": 9140 }, { "epoch": 1.14, "learning_rate": 9.797087016058758e-06, "loss": 0.0857, "step": 9150 }, { "epoch": 1.14, "learning_rate": 9.796838043072328e-06, "loss": 0.0664, "step": 9160 }, { "epoch": 1.14, "learning_rate": 9.796589070085897e-06, "loss": 0.0606, "step": 9170 }, { "epoch": 1.14, "learning_rate": 9.796340097099465e-06, "loss": 0.0589, "step": 9180 }, { "epoch": 1.14, "learning_rate": 9.796091124113034e-06, "loss": 0.0626, "step": 9190 }, { "epoch": 1.14, "learning_rate": 9.795842151126604e-06, "loss": 0.0737, "step": 9200 }, { "epoch": 1.14, "learning_rate": 9.795593178140172e-06, "loss": 0.0874, "step": 9210 }, { "epoch": 1.14, "learning_rate": 9.795344205153741e-06, "loss": 0.0709, "step": 9220 }, { "epoch": 1.15, "learning_rate": 9.795095232167311e-06, "loss": 0.0687, "step": 9230 }, { "epoch": 1.15, "learning_rate": 9.79484625918088e-06, "loss": 0.0483, "step": 9240 }, { "epoch": 1.15, "learning_rate": 9.794597286194448e-06, "loss": 0.0436, "step": 9250 }, { "epoch": 1.15, "learning_rate": 9.794348313208017e-06, "loss": 0.0665, "step": 9260 }, { "epoch": 1.15, "learning_rate": 9.794099340221587e-06, "loss": 0.0676, "step": 9270 }, { "epoch": 1.15, "learning_rate": 9.793850367235155e-06, "loss": 0.0606, "step": 9280 }, { "epoch": 1.15, "learning_rate": 9.793601394248726e-06, "loss": 0.08, "step": 9290 }, { "epoch": 1.15, "learning_rate": 9.793352421262294e-06, "loss": 0.0646, "step": 9300 }, { "epoch": 1.16, "learning_rate": 9.793103448275863e-06, "loss": 0.0834, "step": 9310 }, { "epoch": 1.16, "learning_rate": 9.792854475289431e-06, "loss": 0.0731, "step": 9320 }, { "epoch": 1.16, "learning_rate": 9.792605502303001e-06, "loss": 0.0452, "step": 9330 }, { "epoch": 1.16, "learning_rate": 9.79235652931657e-06, "loss": 0.0474, "step": 9340 }, { "epoch": 1.16, "learning_rate": 9.79210755633014e-06, "loss": 0.0673, "step": 9350 }, { "epoch": 1.16, "learning_rate": 9.791858583343709e-06, "loss": 0.0713, "step": 9360 }, { "epoch": 1.16, "learning_rate": 9.791609610357277e-06, "loss": 0.0738, "step": 9370 }, { "epoch": 1.16, "learning_rate": 9.791360637370846e-06, "loss": 0.0675, "step": 9380 }, { "epoch": 1.17, "learning_rate": 9.791111664384416e-06, "loss": 0.0695, "step": 9390 }, { "epoch": 1.17, "learning_rate": 9.790862691397984e-06, "loss": 0.0719, "step": 9400 }, { "epoch": 1.17, "learning_rate": 9.790613718411553e-06, "loss": 0.1111, "step": 9410 }, { "epoch": 1.17, "learning_rate": 9.790364745425123e-06, "loss": 0.0527, "step": 9420 }, { "epoch": 1.17, "learning_rate": 9.790115772438692e-06, "loss": 0.076, "step": 9430 }, { "epoch": 1.17, "learning_rate": 9.78986679945226e-06, "loss": 0.0817, "step": 9440 }, { "epoch": 1.17, "learning_rate": 9.789617826465829e-06, "loss": 0.0531, "step": 9450 }, { "epoch": 1.17, "learning_rate": 9.789368853479399e-06, "loss": 0.1352, "step": 9460 }, { "epoch": 1.18, "learning_rate": 9.789119880492967e-06, "loss": 0.0742, "step": 9470 }, { "epoch": 1.18, "learning_rate": 9.788870907506536e-06, "loss": 0.0739, "step": 9480 }, { "epoch": 1.18, "learning_rate": 9.788621934520104e-06, "loss": 0.0415, "step": 9490 }, { "epoch": 1.18, "learning_rate": 9.788372961533675e-06, "loss": 0.0827, "step": 9500 }, { "epoch": 1.18, "learning_rate": 9.788123988547243e-06, "loss": 0.0785, "step": 9510 }, { "epoch": 1.18, "learning_rate": 9.787875015560813e-06, "loss": 0.073, "step": 9520 }, { "epoch": 1.18, "learning_rate": 9.787626042574382e-06, "loss": 0.0608, "step": 9530 }, { "epoch": 1.18, "learning_rate": 9.78737706958795e-06, "loss": 0.0715, "step": 9540 }, { "epoch": 1.19, "learning_rate": 9.787128096601519e-06, "loss": 0.0542, "step": 9550 }, { "epoch": 1.19, "learning_rate": 9.786879123615089e-06, "loss": 0.074, "step": 9560 }, { "epoch": 1.19, "learning_rate": 9.786630150628658e-06, "loss": 0.0762, "step": 9570 }, { "epoch": 1.19, "learning_rate": 9.786381177642226e-06, "loss": 0.038, "step": 9580 }, { "epoch": 1.19, "learning_rate": 9.786132204655796e-06, "loss": 0.0617, "step": 9590 }, { "epoch": 1.19, "learning_rate": 9.785883231669365e-06, "loss": 0.0689, "step": 9600 }, { "epoch": 1.19, "learning_rate": 9.785634258682933e-06, "loss": 0.0886, "step": 9610 }, { "epoch": 1.19, "learning_rate": 9.785385285696502e-06, "loss": 0.0663, "step": 9620 }, { "epoch": 1.2, "learning_rate": 9.785136312710072e-06, "loss": 0.0805, "step": 9630 }, { "epoch": 1.2, "learning_rate": 9.78488733972364e-06, "loss": 0.0745, "step": 9640 }, { "epoch": 1.2, "learning_rate": 9.78463836673721e-06, "loss": 0.0622, "step": 9650 }, { "epoch": 1.2, "learning_rate": 9.784389393750778e-06, "loss": 0.0869, "step": 9660 }, { "epoch": 1.2, "learning_rate": 9.784140420764348e-06, "loss": 0.072, "step": 9670 }, { "epoch": 1.2, "learning_rate": 9.783891447777916e-06, "loss": 0.0871, "step": 9680 }, { "epoch": 1.2, "learning_rate": 9.783642474791487e-06, "loss": 0.0779, "step": 9690 }, { "epoch": 1.2, "learning_rate": 9.783393501805055e-06, "loss": 0.0738, "step": 9700 }, { "epoch": 1.21, "learning_rate": 9.783144528818624e-06, "loss": 0.069, "step": 9710 }, { "epoch": 1.21, "learning_rate": 9.782895555832192e-06, "loss": 0.0625, "step": 9720 }, { "epoch": 1.21, "learning_rate": 9.782646582845762e-06, "loss": 0.0474, "step": 9730 }, { "epoch": 1.21, "learning_rate": 9.782397609859331e-06, "loss": 0.0569, "step": 9740 }, { "epoch": 1.21, "learning_rate": 9.7821486368729e-06, "loss": 0.0477, "step": 9750 }, { "epoch": 1.21, "learning_rate": 9.78189966388647e-06, "loss": 0.1023, "step": 9760 }, { "epoch": 1.21, "learning_rate": 9.781650690900038e-06, "loss": 0.0712, "step": 9770 }, { "epoch": 1.21, "learning_rate": 9.781401717913607e-06, "loss": 0.079, "step": 9780 }, { "epoch": 1.22, "learning_rate": 9.781152744927175e-06, "loss": 0.0944, "step": 9790 }, { "epoch": 1.22, "learning_rate": 9.780903771940745e-06, "loss": 0.0563, "step": 9800 }, { "epoch": 1.22, "learning_rate": 9.780654798954314e-06, "loss": 0.0618, "step": 9810 }, { "epoch": 1.22, "learning_rate": 9.780405825967884e-06, "loss": 0.0487, "step": 9820 }, { "epoch": 1.22, "learning_rate": 9.780156852981453e-06, "loss": 0.0613, "step": 9830 }, { "epoch": 1.22, "learning_rate": 9.779907879995021e-06, "loss": 0.0971, "step": 9840 }, { "epoch": 1.22, "learning_rate": 9.77965890700859e-06, "loss": 0.0733, "step": 9850 }, { "epoch": 1.22, "learning_rate": 9.77940993402216e-06, "loss": 0.1075, "step": 9860 }, { "epoch": 1.23, "learning_rate": 9.779160961035728e-06, "loss": 0.0654, "step": 9870 }, { "epoch": 1.23, "learning_rate": 9.778911988049299e-06, "loss": 0.0486, "step": 9880 }, { "epoch": 1.23, "learning_rate": 9.778663015062867e-06, "loss": 0.0611, "step": 9890 }, { "epoch": 1.23, "learning_rate": 9.778414042076436e-06, "loss": 0.0513, "step": 9900 }, { "epoch": 1.23, "learning_rate": 9.778165069090004e-06, "loss": 0.0842, "step": 9910 }, { "epoch": 1.23, "learning_rate": 9.777916096103574e-06, "loss": 0.0904, "step": 9920 }, { "epoch": 1.23, "learning_rate": 9.777667123117143e-06, "loss": 0.0739, "step": 9930 }, { "epoch": 1.23, "learning_rate": 9.777418150130711e-06, "loss": 0.0752, "step": 9940 }, { "epoch": 1.24, "learning_rate": 9.777169177144282e-06, "loss": 0.0668, "step": 9950 }, { "epoch": 1.24, "learning_rate": 9.77692020415785e-06, "loss": 0.0741, "step": 9960 }, { "epoch": 1.24, "learning_rate": 9.776671231171419e-06, "loss": 0.0899, "step": 9970 }, { "epoch": 1.24, "learning_rate": 9.776422258184987e-06, "loss": 0.0485, "step": 9980 }, { "epoch": 1.24, "learning_rate": 9.776173285198557e-06, "loss": 0.0624, "step": 9990 }, { "epoch": 1.24, "learning_rate": 9.775924312212126e-06, "loss": 0.0727, "step": 10000 }, { "epoch": 1.24, "eval_bleu": 88.8579, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.6867, "eval_has_error_f1": 0.4686, "eval_loss": 0.058412738144397736, "eval_runtime": 1412.5231, "eval_samples_per_second": 2.83, "eval_steps_per_second": 0.708, "step": 10000 }, { "epoch": 1.24, "learning_rate": 9.775675339225696e-06, "loss": 0.0847, "step": 10010 }, { "epoch": 1.24, "learning_rate": 9.775426366239263e-06, "loss": 0.0465, "step": 10020 }, { "epoch": 1.25, "learning_rate": 9.775177393252833e-06, "loss": 0.0818, "step": 10030 }, { "epoch": 1.25, "learning_rate": 9.774928420266402e-06, "loss": 0.0661, "step": 10040 }, { "epoch": 1.25, "learning_rate": 9.774679447279972e-06, "loss": 0.0742, "step": 10050 }, { "epoch": 1.25, "learning_rate": 9.77443047429354e-06, "loss": 0.0439, "step": 10060 }, { "epoch": 1.25, "learning_rate": 9.774181501307109e-06, "loss": 0.0573, "step": 10070 }, { "epoch": 1.25, "learning_rate": 9.773932528320677e-06, "loss": 0.0615, "step": 10080 }, { "epoch": 1.25, "learning_rate": 9.773683555334248e-06, "loss": 0.0547, "step": 10090 }, { "epoch": 1.25, "learning_rate": 9.773434582347816e-06, "loss": 0.0441, "step": 10100 }, { "epoch": 1.26, "learning_rate": 9.773185609361385e-06, "loss": 0.0946, "step": 10110 }, { "epoch": 1.26, "learning_rate": 9.772936636374955e-06, "loss": 0.0575, "step": 10120 }, { "epoch": 1.26, "learning_rate": 9.772687663388523e-06, "loss": 0.0887, "step": 10130 }, { "epoch": 1.26, "learning_rate": 9.772438690402092e-06, "loss": 0.0455, "step": 10140 }, { "epoch": 1.26, "learning_rate": 9.77218971741566e-06, "loss": 0.0559, "step": 10150 }, { "epoch": 1.26, "learning_rate": 9.77194074442923e-06, "loss": 0.1053, "step": 10160 }, { "epoch": 1.26, "learning_rate": 9.771691771442799e-06, "loss": 0.0622, "step": 10170 }, { "epoch": 1.26, "learning_rate": 9.77144279845637e-06, "loss": 0.0703, "step": 10180 }, { "epoch": 1.27, "learning_rate": 9.771193825469936e-06, "loss": 0.0439, "step": 10190 }, { "epoch": 1.27, "learning_rate": 9.770944852483506e-06, "loss": 0.0623, "step": 10200 }, { "epoch": 1.27, "learning_rate": 9.770695879497075e-06, "loss": 0.096, "step": 10210 }, { "epoch": 1.27, "learning_rate": 9.770446906510645e-06, "loss": 0.0624, "step": 10220 }, { "epoch": 1.27, "learning_rate": 9.770197933524214e-06, "loss": 0.0603, "step": 10230 }, { "epoch": 1.27, "learning_rate": 9.769948960537782e-06, "loss": 0.0604, "step": 10240 }, { "epoch": 1.27, "learning_rate": 9.76969998755135e-06, "loss": 0.0615, "step": 10250 }, { "epoch": 1.27, "learning_rate": 9.76945101456492e-06, "loss": 0.0681, "step": 10260 }, { "epoch": 1.28, "learning_rate": 9.76920204157849e-06, "loss": 0.0705, "step": 10270 }, { "epoch": 1.28, "learning_rate": 9.768953068592058e-06, "loss": 0.061, "step": 10280 }, { "epoch": 1.28, "learning_rate": 9.768704095605628e-06, "loss": 0.0698, "step": 10290 }, { "epoch": 1.28, "learning_rate": 9.768455122619197e-06, "loss": 0.065, "step": 10300 }, { "epoch": 1.28, "learning_rate": 9.768206149632765e-06, "loss": 0.0884, "step": 10310 }, { "epoch": 1.28, "learning_rate": 9.767957176646334e-06, "loss": 0.0833, "step": 10320 }, { "epoch": 1.28, "learning_rate": 9.767708203659904e-06, "loss": 0.0341, "step": 10330 }, { "epoch": 1.28, "learning_rate": 9.767459230673472e-06, "loss": 0.0997, "step": 10340 }, { "epoch": 1.29, "learning_rate": 9.767210257687043e-06, "loss": 0.0738, "step": 10350 }, { "epoch": 1.29, "learning_rate": 9.766961284700611e-06, "loss": 0.0705, "step": 10360 }, { "epoch": 1.29, "learning_rate": 9.76671231171418e-06, "loss": 0.0753, "step": 10370 }, { "epoch": 1.29, "learning_rate": 9.766463338727748e-06, "loss": 0.0883, "step": 10380 }, { "epoch": 1.29, "learning_rate": 9.766214365741318e-06, "loss": 0.0844, "step": 10390 }, { "epoch": 1.29, "learning_rate": 9.765965392754887e-06, "loss": 0.0869, "step": 10400 }, { "epoch": 1.29, "learning_rate": 9.765716419768457e-06, "loss": 0.095, "step": 10410 }, { "epoch": 1.29, "learning_rate": 9.765467446782025e-06, "loss": 0.0508, "step": 10420 }, { "epoch": 1.3, "learning_rate": 9.765218473795594e-06, "loss": 0.0483, "step": 10430 }, { "epoch": 1.3, "learning_rate": 9.764969500809163e-06, "loss": 0.0845, "step": 10440 }, { "epoch": 1.3, "learning_rate": 9.764720527822733e-06, "loss": 0.0609, "step": 10450 }, { "epoch": 1.3, "learning_rate": 9.764471554836301e-06, "loss": 0.0744, "step": 10460 }, { "epoch": 1.3, "learning_rate": 9.76422258184987e-06, "loss": 0.0782, "step": 10470 }, { "epoch": 1.3, "learning_rate": 9.76397360886344e-06, "loss": 0.0623, "step": 10480 }, { "epoch": 1.3, "learning_rate": 9.763724635877008e-06, "loss": 0.059, "step": 10490 }, { "epoch": 1.3, "learning_rate": 9.763475662890577e-06, "loss": 0.057, "step": 10500 }, { "epoch": 1.31, "learning_rate": 9.763226689904146e-06, "loss": 0.0675, "step": 10510 }, { "epoch": 1.31, "learning_rate": 9.762977716917716e-06, "loss": 0.0518, "step": 10520 }, { "epoch": 1.31, "learning_rate": 9.762728743931284e-06, "loss": 0.0622, "step": 10530 }, { "epoch": 1.31, "learning_rate": 9.762479770944854e-06, "loss": 0.0666, "step": 10540 }, { "epoch": 1.31, "learning_rate": 9.762230797958421e-06, "loss": 0.0589, "step": 10550 }, { "epoch": 1.31, "learning_rate": 9.761981824971991e-06, "loss": 0.0853, "step": 10560 }, { "epoch": 1.31, "learning_rate": 9.76173285198556e-06, "loss": 0.0604, "step": 10570 }, { "epoch": 1.31, "learning_rate": 9.76148387899913e-06, "loss": 0.0676, "step": 10580 }, { "epoch": 1.32, "learning_rate": 9.761234906012699e-06, "loss": 0.0871, "step": 10590 }, { "epoch": 1.32, "learning_rate": 9.760985933026267e-06, "loss": 0.0654, "step": 10600 }, { "epoch": 1.32, "learning_rate": 9.760736960039836e-06, "loss": 0.0888, "step": 10610 }, { "epoch": 1.32, "learning_rate": 9.760487987053406e-06, "loss": 0.0636, "step": 10620 }, { "epoch": 1.32, "learning_rate": 9.760239014066974e-06, "loss": 0.0877, "step": 10630 }, { "epoch": 1.32, "learning_rate": 9.759990041080543e-06, "loss": 0.0323, "step": 10640 }, { "epoch": 1.32, "learning_rate": 9.759741068094113e-06, "loss": 0.0607, "step": 10650 }, { "epoch": 1.32, "learning_rate": 9.759492095107682e-06, "loss": 0.0803, "step": 10660 }, { "epoch": 1.32, "learning_rate": 9.75924312212125e-06, "loss": 0.0502, "step": 10670 }, { "epoch": 1.33, "learning_rate": 9.758994149134819e-06, "loss": 0.1034, "step": 10680 }, { "epoch": 1.33, "learning_rate": 9.758745176148389e-06, "loss": 0.0691, "step": 10690 }, { "epoch": 1.33, "learning_rate": 9.758496203161957e-06, "loss": 0.0572, "step": 10700 }, { "epoch": 1.33, "learning_rate": 9.758247230175528e-06, "loss": 0.0714, "step": 10710 }, { "epoch": 1.33, "learning_rate": 9.757998257189096e-06, "loss": 0.0485, "step": 10720 }, { "epoch": 1.33, "learning_rate": 9.757749284202665e-06, "loss": 0.07, "step": 10730 }, { "epoch": 1.33, "learning_rate": 9.757500311216233e-06, "loss": 0.0415, "step": 10740 }, { "epoch": 1.33, "learning_rate": 9.757251338229803e-06, "loss": 0.0529, "step": 10750 }, { "epoch": 1.34, "learning_rate": 9.757002365243372e-06, "loss": 0.0782, "step": 10760 }, { "epoch": 1.34, "learning_rate": 9.75675339225694e-06, "loss": 0.0794, "step": 10770 }, { "epoch": 1.34, "learning_rate": 9.756504419270509e-06, "loss": 0.0724, "step": 10780 }, { "epoch": 1.34, "learning_rate": 9.75625544628408e-06, "loss": 0.062, "step": 10790 }, { "epoch": 1.34, "learning_rate": 9.756006473297648e-06, "loss": 0.0687, "step": 10800 }, { "epoch": 1.34, "learning_rate": 9.755757500311216e-06, "loss": 0.0622, "step": 10810 }, { "epoch": 1.34, "learning_rate": 9.755508527324786e-06, "loss": 0.0664, "step": 10820 }, { "epoch": 1.34, "learning_rate": 9.755259554338355e-06, "loss": 0.0787, "step": 10830 }, { "epoch": 1.35, "learning_rate": 9.755010581351923e-06, "loss": 0.0939, "step": 10840 }, { "epoch": 1.35, "learning_rate": 9.754761608365492e-06, "loss": 0.1007, "step": 10850 }, { "epoch": 1.35, "learning_rate": 9.754512635379062e-06, "loss": 0.0623, "step": 10860 }, { "epoch": 1.35, "learning_rate": 9.75426366239263e-06, "loss": 0.0526, "step": 10870 }, { "epoch": 1.35, "learning_rate": 9.754014689406201e-06, "loss": 0.0794, "step": 10880 }, { "epoch": 1.35, "learning_rate": 9.75376571641977e-06, "loss": 0.0806, "step": 10890 }, { "epoch": 1.35, "learning_rate": 9.753516743433338e-06, "loss": 0.0889, "step": 10900 }, { "epoch": 1.35, "learning_rate": 9.753267770446906e-06, "loss": 0.0761, "step": 10910 }, { "epoch": 1.36, "learning_rate": 9.753018797460477e-06, "loss": 0.0408, "step": 10920 }, { "epoch": 1.36, "learning_rate": 9.752769824474045e-06, "loss": 0.0944, "step": 10930 }, { "epoch": 1.36, "learning_rate": 9.752520851487615e-06, "loss": 0.0652, "step": 10940 }, { "epoch": 1.36, "learning_rate": 9.752271878501184e-06, "loss": 0.07, "step": 10950 }, { "epoch": 1.36, "learning_rate": 9.752022905514752e-06, "loss": 0.0719, "step": 10960 }, { "epoch": 1.36, "learning_rate": 9.751773932528321e-06, "loss": 0.0563, "step": 10970 }, { "epoch": 1.36, "learning_rate": 9.751524959541891e-06, "loss": 0.0692, "step": 10980 }, { "epoch": 1.36, "learning_rate": 9.75127598655546e-06, "loss": 0.0661, "step": 10990 }, { "epoch": 1.37, "learning_rate": 9.751027013569028e-06, "loss": 0.0542, "step": 11000 }, { "epoch": 1.37, "learning_rate": 9.750778040582598e-06, "loss": 0.0859, "step": 11010 }, { "epoch": 1.37, "learning_rate": 9.750529067596167e-06, "loss": 0.0543, "step": 11020 }, { "epoch": 1.37, "learning_rate": 9.750280094609735e-06, "loss": 0.0865, "step": 11030 }, { "epoch": 1.37, "learning_rate": 9.750031121623304e-06, "loss": 0.051, "step": 11040 }, { "epoch": 1.37, "learning_rate": 9.749782148636874e-06, "loss": 0.0631, "step": 11050 }, { "epoch": 1.37, "learning_rate": 9.749533175650443e-06, "loss": 0.0925, "step": 11060 }, { "epoch": 1.37, "learning_rate": 9.749284202664013e-06, "loss": 0.065, "step": 11070 }, { "epoch": 1.38, "learning_rate": 9.74903522967758e-06, "loss": 0.0626, "step": 11080 }, { "epoch": 1.38, "learning_rate": 9.74878625669115e-06, "loss": 0.0571, "step": 11090 }, { "epoch": 1.38, "learning_rate": 9.748537283704718e-06, "loss": 0.0667, "step": 11100 }, { "epoch": 1.38, "learning_rate": 9.748288310718289e-06, "loss": 0.1114, "step": 11110 }, { "epoch": 1.38, "learning_rate": 9.748039337731857e-06, "loss": 0.0569, "step": 11120 }, { "epoch": 1.38, "learning_rate": 9.747790364745426e-06, "loss": 0.0706, "step": 11130 }, { "epoch": 1.38, "learning_rate": 9.747541391758994e-06, "loss": 0.0644, "step": 11140 }, { "epoch": 1.38, "learning_rate": 9.747292418772564e-06, "loss": 0.0688, "step": 11150 }, { "epoch": 1.39, "learning_rate": 9.747043445786133e-06, "loss": 0.1074, "step": 11160 }, { "epoch": 1.39, "learning_rate": 9.746794472799701e-06, "loss": 0.0994, "step": 11170 }, { "epoch": 1.39, "learning_rate": 9.746545499813272e-06, "loss": 0.04, "step": 11180 }, { "epoch": 1.39, "learning_rate": 9.74629652682684e-06, "loss": 0.062, "step": 11190 }, { "epoch": 1.39, "learning_rate": 9.746047553840409e-06, "loss": 0.062, "step": 11200 }, { "epoch": 1.39, "learning_rate": 9.745798580853977e-06, "loss": 0.0927, "step": 11210 }, { "epoch": 1.39, "learning_rate": 9.745549607867547e-06, "loss": 0.089, "step": 11220 }, { "epoch": 1.39, "learning_rate": 9.745300634881116e-06, "loss": 0.0766, "step": 11230 }, { "epoch": 1.4, "learning_rate": 9.745051661894686e-06, "loss": 0.0719, "step": 11240 }, { "epoch": 1.4, "learning_rate": 9.744802688908255e-06, "loss": 0.0624, "step": 11250 }, { "epoch": 1.4, "learning_rate": 9.744553715921823e-06, "loss": 0.1005, "step": 11260 }, { "epoch": 1.4, "learning_rate": 9.744304742935392e-06, "loss": 0.0667, "step": 11270 }, { "epoch": 1.4, "learning_rate": 9.744055769948962e-06, "loss": 0.0761, "step": 11280 }, { "epoch": 1.4, "learning_rate": 9.74380679696253e-06, "loss": 0.0791, "step": 11290 }, { "epoch": 1.4, "learning_rate": 9.743557823976099e-06, "loss": 0.0632, "step": 11300 }, { "epoch": 1.4, "learning_rate": 9.743308850989669e-06, "loss": 0.073, "step": 11310 }, { "epoch": 1.41, "learning_rate": 9.743059878003238e-06, "loss": 0.0536, "step": 11320 }, { "epoch": 1.41, "learning_rate": 9.742810905016806e-06, "loss": 0.0481, "step": 11330 }, { "epoch": 1.41, "learning_rate": 9.742561932030375e-06, "loss": 0.058, "step": 11340 }, { "epoch": 1.41, "learning_rate": 9.742312959043945e-06, "loss": 0.0611, "step": 11350 }, { "epoch": 1.41, "learning_rate": 9.742063986057513e-06, "loss": 0.0837, "step": 11360 }, { "epoch": 1.41, "learning_rate": 9.741815013071084e-06, "loss": 0.0627, "step": 11370 }, { "epoch": 1.41, "learning_rate": 9.74156604008465e-06, "loss": 0.0692, "step": 11380 }, { "epoch": 1.41, "learning_rate": 9.74131706709822e-06, "loss": 0.0742, "step": 11390 }, { "epoch": 1.42, "learning_rate": 9.74106809411179e-06, "loss": 0.083, "step": 11400 }, { "epoch": 1.42, "learning_rate": 9.74081912112536e-06, "loss": 0.0793, "step": 11410 }, { "epoch": 1.42, "learning_rate": 9.740570148138928e-06, "loss": 0.0774, "step": 11420 }, { "epoch": 1.42, "learning_rate": 9.740321175152496e-06, "loss": 0.0821, "step": 11430 }, { "epoch": 1.42, "learning_rate": 9.740072202166065e-06, "loss": 0.0892, "step": 11440 }, { "epoch": 1.42, "learning_rate": 9.739823229179635e-06, "loss": 0.0877, "step": 11450 }, { "epoch": 1.42, "learning_rate": 9.739574256193204e-06, "loss": 0.0686, "step": 11460 }, { "epoch": 1.42, "learning_rate": 9.739325283206774e-06, "loss": 0.0971, "step": 11470 }, { "epoch": 1.43, "learning_rate": 9.739076310220342e-06, "loss": 0.0763, "step": 11480 }, { "epoch": 1.43, "learning_rate": 9.738827337233911e-06, "loss": 0.0702, "step": 11490 }, { "epoch": 1.43, "learning_rate": 9.73857836424748e-06, "loss": 0.041, "step": 11500 }, { "epoch": 1.43, "learning_rate": 9.73832939126105e-06, "loss": 0.1312, "step": 11510 }, { "epoch": 1.43, "learning_rate": 9.738080418274618e-06, "loss": 0.0493, "step": 11520 }, { "epoch": 1.43, "learning_rate": 9.737831445288187e-06, "loss": 0.0504, "step": 11530 }, { "epoch": 1.43, "learning_rate": 9.737582472301757e-06, "loss": 0.0755, "step": 11540 }, { "epoch": 1.43, "learning_rate": 9.737333499315325e-06, "loss": 0.0817, "step": 11550 }, { "epoch": 1.44, "learning_rate": 9.737084526328894e-06, "loss": 0.0633, "step": 11560 }, { "epoch": 1.44, "learning_rate": 9.736835553342462e-06, "loss": 0.0802, "step": 11570 }, { "epoch": 1.44, "learning_rate": 9.736586580356033e-06, "loss": 0.0805, "step": 11580 }, { "epoch": 1.44, "learning_rate": 9.736337607369601e-06, "loss": 0.0703, "step": 11590 }, { "epoch": 1.44, "learning_rate": 9.736088634383171e-06, "loss": 0.0526, "step": 11600 }, { "epoch": 1.44, "learning_rate": 9.735839661396738e-06, "loss": 0.1125, "step": 11610 }, { "epoch": 1.44, "learning_rate": 9.735590688410308e-06, "loss": 0.0731, "step": 11620 }, { "epoch": 1.44, "learning_rate": 9.735341715423877e-06, "loss": 0.0607, "step": 11630 }, { "epoch": 1.45, "learning_rate": 9.735092742437447e-06, "loss": 0.0507, "step": 11640 }, { "epoch": 1.45, "learning_rate": 9.734843769451016e-06, "loss": 0.0802, "step": 11650 }, { "epoch": 1.45, "learning_rate": 9.734594796464584e-06, "loss": 0.0822, "step": 11660 }, { "epoch": 1.45, "learning_rate": 9.734345823478153e-06, "loss": 0.0573, "step": 11670 }, { "epoch": 1.45, "learning_rate": 9.734096850491723e-06, "loss": 0.0751, "step": 11680 }, { "epoch": 1.45, "learning_rate": 9.733847877505291e-06, "loss": 0.0698, "step": 11690 }, { "epoch": 1.45, "learning_rate": 9.73359890451886e-06, "loss": 0.065, "step": 11700 }, { "epoch": 1.45, "learning_rate": 9.73334993153243e-06, "loss": 0.1054, "step": 11710 }, { "epoch": 1.46, "learning_rate": 9.733100958545999e-06, "loss": 0.1022, "step": 11720 }, { "epoch": 1.46, "learning_rate": 9.732851985559567e-06, "loss": 0.1025, "step": 11730 }, { "epoch": 1.46, "learning_rate": 9.732603012573136e-06, "loss": 0.0804, "step": 11740 }, { "epoch": 1.46, "learning_rate": 9.732354039586706e-06, "loss": 0.0678, "step": 11750 }, { "epoch": 1.46, "learning_rate": 9.732105066600274e-06, "loss": 0.0489, "step": 11760 }, { "epoch": 1.46, "learning_rate": 9.731856093613845e-06, "loss": 0.0762, "step": 11770 }, { "epoch": 1.46, "learning_rate": 9.731607120627413e-06, "loss": 0.1064, "step": 11780 }, { "epoch": 1.46, "learning_rate": 9.731358147640982e-06, "loss": 0.075, "step": 11790 }, { "epoch": 1.47, "learning_rate": 9.73110917465455e-06, "loss": 0.0535, "step": 11800 }, { "epoch": 1.47, "learning_rate": 9.73086020166812e-06, "loss": 0.0643, "step": 11810 }, { "epoch": 1.47, "learning_rate": 9.730611228681689e-06, "loss": 0.0603, "step": 11820 }, { "epoch": 1.47, "learning_rate": 9.730362255695257e-06, "loss": 0.0859, "step": 11830 }, { "epoch": 1.47, "learning_rate": 9.730113282708828e-06, "loss": 0.0624, "step": 11840 }, { "epoch": 1.47, "learning_rate": 9.729864309722396e-06, "loss": 0.0867, "step": 11850 }, { "epoch": 1.47, "learning_rate": 9.729615336735965e-06, "loss": 0.0481, "step": 11860 }, { "epoch": 1.47, "learning_rate": 9.729366363749533e-06, "loss": 0.057, "step": 11870 }, { "epoch": 1.48, "learning_rate": 9.729117390763103e-06, "loss": 0.0608, "step": 11880 }, { "epoch": 1.48, "learning_rate": 9.728868417776672e-06, "loss": 0.0637, "step": 11890 }, { "epoch": 1.48, "learning_rate": 9.728619444790242e-06, "loss": 0.0605, "step": 11900 }, { "epoch": 1.48, "learning_rate": 9.728370471803809e-06, "loss": 0.0795, "step": 11910 }, { "epoch": 1.48, "learning_rate": 9.728121498817379e-06, "loss": 0.0745, "step": 11920 }, { "epoch": 1.48, "learning_rate": 9.727872525830948e-06, "loss": 0.0651, "step": 11930 }, { "epoch": 1.48, "learning_rate": 9.727623552844518e-06, "loss": 0.0544, "step": 11940 }, { "epoch": 1.48, "learning_rate": 9.727374579858086e-06, "loss": 0.0637, "step": 11950 }, { "epoch": 1.49, "learning_rate": 9.727125606871657e-06, "loss": 0.0735, "step": 11960 }, { "epoch": 1.49, "learning_rate": 9.726876633885223e-06, "loss": 0.0757, "step": 11970 }, { "epoch": 1.49, "learning_rate": 9.726627660898794e-06, "loss": 0.0832, "step": 11980 }, { "epoch": 1.49, "learning_rate": 9.726378687912362e-06, "loss": 0.0702, "step": 11990 }, { "epoch": 1.49, "learning_rate": 9.726129714925932e-06, "loss": 0.0623, "step": 12000 }, { "epoch": 1.49, "learning_rate": 9.7258807419395e-06, "loss": 0.0804, "step": 12010 }, { "epoch": 1.49, "learning_rate": 9.72563176895307e-06, "loss": 0.0781, "step": 12020 }, { "epoch": 1.49, "learning_rate": 9.725382795966638e-06, "loss": 0.0703, "step": 12030 }, { "epoch": 1.5, "learning_rate": 9.725133822980208e-06, "loss": 0.0554, "step": 12040 }, { "epoch": 1.5, "learning_rate": 9.724884849993777e-06, "loss": 0.0751, "step": 12050 }, { "epoch": 1.5, "learning_rate": 9.724635877007345e-06, "loss": 0.0859, "step": 12060 }, { "epoch": 1.5, "learning_rate": 9.724386904020915e-06, "loss": 0.074, "step": 12070 }, { "epoch": 1.5, "learning_rate": 9.724137931034484e-06, "loss": 0.064, "step": 12080 }, { "epoch": 1.5, "learning_rate": 9.723888958048052e-06, "loss": 0.0716, "step": 12090 }, { "epoch": 1.5, "learning_rate": 9.723639985061621e-06, "loss": 0.058, "step": 12100 }, { "epoch": 1.5, "learning_rate": 9.723391012075191e-06, "loss": 0.075, "step": 12110 }, { "epoch": 1.5, "learning_rate": 9.72314203908876e-06, "loss": 0.0477, "step": 12120 }, { "epoch": 1.51, "learning_rate": 9.72289306610233e-06, "loss": 0.0597, "step": 12130 }, { "epoch": 1.51, "learning_rate": 9.722644093115897e-06, "loss": 0.0845, "step": 12140 }, { "epoch": 1.51, "learning_rate": 9.722395120129467e-06, "loss": 0.108, "step": 12150 }, { "epoch": 1.51, "learning_rate": 9.722146147143035e-06, "loss": 0.0918, "step": 12160 }, { "epoch": 1.51, "learning_rate": 9.721897174156606e-06, "loss": 0.0859, "step": 12170 }, { "epoch": 1.51, "learning_rate": 9.721648201170174e-06, "loss": 0.0645, "step": 12180 }, { "epoch": 1.51, "learning_rate": 9.721399228183743e-06, "loss": 0.055, "step": 12190 }, { "epoch": 1.51, "learning_rate": 9.721150255197311e-06, "loss": 0.0618, "step": 12200 }, { "epoch": 1.52, "learning_rate": 9.720901282210881e-06, "loss": 0.0609, "step": 12210 }, { "epoch": 1.52, "learning_rate": 9.72065230922445e-06, "loss": 0.0799, "step": 12220 }, { "epoch": 1.52, "learning_rate": 9.720403336238018e-06, "loss": 0.0758, "step": 12230 }, { "epoch": 1.52, "learning_rate": 9.720154363251589e-06, "loss": 0.0641, "step": 12240 }, { "epoch": 1.52, "learning_rate": 9.719905390265157e-06, "loss": 0.0458, "step": 12250 }, { "epoch": 1.52, "learning_rate": 9.719656417278726e-06, "loss": 0.0931, "step": 12260 }, { "epoch": 1.52, "learning_rate": 9.719407444292294e-06, "loss": 0.0694, "step": 12270 }, { "epoch": 1.52, "learning_rate": 9.719158471305864e-06, "loss": 0.0962, "step": 12280 }, { "epoch": 1.53, "learning_rate": 9.718909498319433e-06, "loss": 0.0583, "step": 12290 }, { "epoch": 1.53, "learning_rate": 9.718660525333003e-06, "loss": 0.0678, "step": 12300 }, { "epoch": 1.53, "learning_rate": 9.718411552346572e-06, "loss": 0.0749, "step": 12310 }, { "epoch": 1.53, "learning_rate": 9.71816257936014e-06, "loss": 0.0818, "step": 12320 }, { "epoch": 1.53, "learning_rate": 9.717913606373709e-06, "loss": 0.0686, "step": 12330 }, { "epoch": 1.53, "learning_rate": 9.717664633387279e-06, "loss": 0.069, "step": 12340 }, { "epoch": 1.53, "learning_rate": 9.717415660400847e-06, "loss": 0.0658, "step": 12350 }, { "epoch": 1.53, "learning_rate": 9.717166687414416e-06, "loss": 0.0939, "step": 12360 }, { "epoch": 1.54, "learning_rate": 9.716917714427986e-06, "loss": 0.0684, "step": 12370 }, { "epoch": 1.54, "learning_rate": 9.716668741441555e-06, "loss": 0.0775, "step": 12380 }, { "epoch": 1.54, "learning_rate": 9.716419768455123e-06, "loss": 0.0765, "step": 12390 }, { "epoch": 1.54, "learning_rate": 9.716170795468692e-06, "loss": 0.0828, "step": 12400 }, { "epoch": 1.54, "learning_rate": 9.715921822482262e-06, "loss": 0.0772, "step": 12410 }, { "epoch": 1.54, "learning_rate": 9.71567284949583e-06, "loss": 0.0604, "step": 12420 }, { "epoch": 1.54, "learning_rate": 9.7154238765094e-06, "loss": 0.0588, "step": 12430 }, { "epoch": 1.54, "learning_rate": 9.715174903522967e-06, "loss": 0.0441, "step": 12440 }, { "epoch": 1.55, "learning_rate": 9.714925930536538e-06, "loss": 0.0521, "step": 12450 }, { "epoch": 1.55, "learning_rate": 9.714676957550106e-06, "loss": 0.0633, "step": 12460 }, { "epoch": 1.55, "learning_rate": 9.714427984563676e-06, "loss": 0.0663, "step": 12470 }, { "epoch": 1.55, "learning_rate": 9.714179011577245e-06, "loss": 0.0513, "step": 12480 }, { "epoch": 1.55, "learning_rate": 9.713930038590815e-06, "loss": 0.0521, "step": 12490 }, { "epoch": 1.55, "learning_rate": 9.713681065604382e-06, "loss": 0.069, "step": 12500 }, { "epoch": 1.55, "learning_rate": 9.713432092617952e-06, "loss": 0.0907, "step": 12510 }, { "epoch": 1.55, "learning_rate": 9.71318311963152e-06, "loss": 0.0722, "step": 12520 }, { "epoch": 1.56, "learning_rate": 9.71293414664509e-06, "loss": 0.0804, "step": 12530 }, { "epoch": 1.56, "learning_rate": 9.71268517365866e-06, "loss": 0.0632, "step": 12540 }, { "epoch": 1.56, "learning_rate": 9.712436200672228e-06, "loss": 0.0701, "step": 12550 }, { "epoch": 1.56, "learning_rate": 9.712187227685796e-06, "loss": 0.0712, "step": 12560 }, { "epoch": 1.56, "learning_rate": 9.711938254699367e-06, "loss": 0.0714, "step": 12570 }, { "epoch": 1.56, "learning_rate": 9.711689281712935e-06, "loss": 0.0728, "step": 12580 }, { "epoch": 1.56, "learning_rate": 9.711440308726504e-06, "loss": 0.0352, "step": 12590 }, { "epoch": 1.56, "learning_rate": 9.711191335740074e-06, "loss": 0.0593, "step": 12600 }, { "epoch": 1.57, "learning_rate": 9.710942362753642e-06, "loss": 0.0578, "step": 12610 }, { "epoch": 1.57, "learning_rate": 9.71069338976721e-06, "loss": 0.06, "step": 12620 }, { "epoch": 1.57, "learning_rate": 9.71044441678078e-06, "loss": 0.0659, "step": 12630 }, { "epoch": 1.57, "learning_rate": 9.71019544379435e-06, "loss": 0.063, "step": 12640 }, { "epoch": 1.57, "learning_rate": 9.709946470807918e-06, "loss": 0.0826, "step": 12650 }, { "epoch": 1.57, "learning_rate": 9.709697497821488e-06, "loss": 0.0719, "step": 12660 }, { "epoch": 1.57, "learning_rate": 9.709448524835057e-06, "loss": 0.0849, "step": 12670 }, { "epoch": 1.57, "learning_rate": 9.709199551848625e-06, "loss": 0.089, "step": 12680 }, { "epoch": 1.58, "learning_rate": 9.708950578862194e-06, "loss": 0.0501, "step": 12690 }, { "epoch": 1.58, "learning_rate": 9.708701605875764e-06, "loss": 0.0746, "step": 12700 }, { "epoch": 1.58, "learning_rate": 9.708452632889333e-06, "loss": 0.06, "step": 12710 }, { "epoch": 1.58, "learning_rate": 9.708203659902901e-06, "loss": 0.0564, "step": 12720 }, { "epoch": 1.58, "learning_rate": 9.70795468691647e-06, "loss": 0.0841, "step": 12730 }, { "epoch": 1.58, "learning_rate": 9.70770571393004e-06, "loss": 0.0572, "step": 12740 }, { "epoch": 1.58, "learning_rate": 9.707456740943608e-06, "loss": 0.0598, "step": 12750 }, { "epoch": 1.58, "learning_rate": 9.707207767957177e-06, "loss": 0.0605, "step": 12760 }, { "epoch": 1.59, "learning_rate": 9.706958794970747e-06, "loss": 0.1015, "step": 12770 }, { "epoch": 1.59, "learning_rate": 9.706709821984316e-06, "loss": 0.0799, "step": 12780 }, { "epoch": 1.59, "learning_rate": 9.706460848997884e-06, "loss": 0.0355, "step": 12790 }, { "epoch": 1.59, "learning_rate": 9.706211876011453e-06, "loss": 0.0766, "step": 12800 }, { "epoch": 1.59, "learning_rate": 9.705962903025023e-06, "loss": 0.0609, "step": 12810 }, { "epoch": 1.59, "learning_rate": 9.705713930038591e-06, "loss": 0.0893, "step": 12820 }, { "epoch": 1.59, "learning_rate": 9.705464957052161e-06, "loss": 0.0514, "step": 12830 }, { "epoch": 1.59, "learning_rate": 9.70521598406573e-06, "loss": 0.0827, "step": 12840 }, { "epoch": 1.6, "learning_rate": 9.704967011079299e-06, "loss": 0.037, "step": 12850 }, { "epoch": 1.6, "learning_rate": 9.704718038092867e-06, "loss": 0.0874, "step": 12860 }, { "epoch": 1.6, "learning_rate": 9.704469065106437e-06, "loss": 0.0925, "step": 12870 }, { "epoch": 1.6, "learning_rate": 9.704220092120006e-06, "loss": 0.047, "step": 12880 }, { "epoch": 1.6, "learning_rate": 9.703971119133574e-06, "loss": 0.0991, "step": 12890 }, { "epoch": 1.6, "learning_rate": 9.703722146147144e-06, "loss": 0.0662, "step": 12900 }, { "epoch": 1.6, "learning_rate": 9.703473173160713e-06, "loss": 0.0796, "step": 12910 }, { "epoch": 1.6, "learning_rate": 9.703224200174282e-06, "loss": 0.0801, "step": 12920 }, { "epoch": 1.61, "learning_rate": 9.70297522718785e-06, "loss": 0.0596, "step": 12930 }, { "epoch": 1.61, "learning_rate": 9.70272625420142e-06, "loss": 0.0454, "step": 12940 }, { "epoch": 1.61, "learning_rate": 9.702477281214989e-06, "loss": 0.0777, "step": 12950 }, { "epoch": 1.61, "learning_rate": 9.702228308228559e-06, "loss": 0.0854, "step": 12960 }, { "epoch": 1.61, "learning_rate": 9.701979335242126e-06, "loss": 0.0698, "step": 12970 }, { "epoch": 1.61, "learning_rate": 9.701730362255696e-06, "loss": 0.0809, "step": 12980 }, { "epoch": 1.61, "learning_rate": 9.701481389269264e-06, "loss": 0.05, "step": 12990 }, { "epoch": 1.61, "learning_rate": 9.701232416282835e-06, "loss": 0.0687, "step": 13000 }, { "epoch": 1.62, "learning_rate": 9.700983443296403e-06, "loss": 0.1042, "step": 13010 }, { "epoch": 1.62, "learning_rate": 9.700734470309973e-06, "loss": 0.063, "step": 13020 }, { "epoch": 1.62, "learning_rate": 9.70048549732354e-06, "loss": 0.0624, "step": 13030 }, { "epoch": 1.62, "learning_rate": 9.70023652433711e-06, "loss": 0.0832, "step": 13040 }, { "epoch": 1.62, "learning_rate": 9.699987551350679e-06, "loss": 0.0542, "step": 13050 }, { "epoch": 1.62, "learning_rate": 9.69973857836425e-06, "loss": 0.0579, "step": 13060 }, { "epoch": 1.62, "learning_rate": 9.699489605377818e-06, "loss": 0.0657, "step": 13070 }, { "epoch": 1.62, "learning_rate": 9.699240632391386e-06, "loss": 0.0851, "step": 13080 }, { "epoch": 1.63, "learning_rate": 9.698991659404955e-06, "loss": 0.0513, "step": 13090 }, { "epoch": 1.63, "learning_rate": 9.698742686418525e-06, "loss": 0.0892, "step": 13100 }, { "epoch": 1.63, "learning_rate": 9.698493713432093e-06, "loss": 0.0757, "step": 13110 }, { "epoch": 1.63, "learning_rate": 9.698244740445662e-06, "loss": 0.0975, "step": 13120 }, { "epoch": 1.63, "learning_rate": 9.697995767459232e-06, "loss": 0.0557, "step": 13130 }, { "epoch": 1.63, "learning_rate": 9.6977467944728e-06, "loss": 0.0689, "step": 13140 }, { "epoch": 1.63, "learning_rate": 9.69749782148637e-06, "loss": 0.0884, "step": 13150 }, { "epoch": 1.63, "learning_rate": 9.697248848499938e-06, "loss": 0.0793, "step": 13160 }, { "epoch": 1.64, "learning_rate": 9.696999875513508e-06, "loss": 0.0465, "step": 13170 }, { "epoch": 1.64, "learning_rate": 9.696750902527076e-06, "loss": 0.0751, "step": 13180 }, { "epoch": 1.64, "learning_rate": 9.696501929540647e-06, "loss": 0.0889, "step": 13190 }, { "epoch": 1.64, "learning_rate": 9.696252956554215e-06, "loss": 0.0693, "step": 13200 }, { "epoch": 1.64, "learning_rate": 9.696003983567784e-06, "loss": 0.0683, "step": 13210 }, { "epoch": 1.64, "learning_rate": 9.695755010581352e-06, "loss": 0.0788, "step": 13220 }, { "epoch": 1.64, "learning_rate": 9.695506037594922e-06, "loss": 0.065, "step": 13230 }, { "epoch": 1.64, "learning_rate": 9.695257064608491e-06, "loss": 0.0743, "step": 13240 }, { "epoch": 1.65, "learning_rate": 9.69500809162206e-06, "loss": 0.0586, "step": 13250 }, { "epoch": 1.65, "learning_rate": 9.69475911863563e-06, "loss": 0.1016, "step": 13260 }, { "epoch": 1.65, "learning_rate": 9.694510145649198e-06, "loss": 0.064, "step": 13270 }, { "epoch": 1.65, "learning_rate": 9.694261172662767e-06, "loss": 0.0817, "step": 13280 }, { "epoch": 1.65, "learning_rate": 9.694012199676335e-06, "loss": 0.0844, "step": 13290 }, { "epoch": 1.65, "learning_rate": 9.693763226689905e-06, "loss": 0.0535, "step": 13300 }, { "epoch": 1.65, "learning_rate": 9.693514253703474e-06, "loss": 0.0746, "step": 13310 }, { "epoch": 1.65, "learning_rate": 9.693265280717044e-06, "loss": 0.0804, "step": 13320 }, { "epoch": 1.66, "learning_rate": 9.693016307730611e-06, "loss": 0.0696, "step": 13330 }, { "epoch": 1.66, "learning_rate": 9.692767334744181e-06, "loss": 0.0505, "step": 13340 }, { "epoch": 1.66, "learning_rate": 9.69251836175775e-06, "loss": 0.0459, "step": 13350 }, { "epoch": 1.66, "learning_rate": 9.69226938877132e-06, "loss": 0.0731, "step": 13360 }, { "epoch": 1.66, "learning_rate": 9.692020415784888e-06, "loss": 0.0745, "step": 13370 }, { "epoch": 1.66, "learning_rate": 9.691771442798457e-06, "loss": 0.0505, "step": 13380 }, { "epoch": 1.66, "learning_rate": 9.691522469812025e-06, "loss": 0.0848, "step": 13390 }, { "epoch": 1.66, "learning_rate": 9.691273496825596e-06, "loss": 0.0705, "step": 13400 }, { "epoch": 1.67, "learning_rate": 9.691024523839164e-06, "loss": 0.0759, "step": 13410 }, { "epoch": 1.67, "learning_rate": 9.690775550852733e-06, "loss": 0.0533, "step": 13420 }, { "epoch": 1.67, "learning_rate": 9.690526577866303e-06, "loss": 0.0661, "step": 13430 }, { "epoch": 1.67, "learning_rate": 9.690277604879871e-06, "loss": 0.0662, "step": 13440 }, { "epoch": 1.67, "learning_rate": 9.69002863189344e-06, "loss": 0.0749, "step": 13450 }, { "epoch": 1.67, "learning_rate": 9.689779658907008e-06, "loss": 0.0916, "step": 13460 }, { "epoch": 1.67, "learning_rate": 9.689530685920579e-06, "loss": 0.06, "step": 13470 }, { "epoch": 1.67, "learning_rate": 9.689281712934147e-06, "loss": 0.0648, "step": 13480 }, { "epoch": 1.68, "learning_rate": 9.689032739947717e-06, "loss": 0.0639, "step": 13490 }, { "epoch": 1.68, "learning_rate": 9.688783766961284e-06, "loss": 0.047, "step": 13500 }, { "epoch": 1.68, "learning_rate": 9.688534793974854e-06, "loss": 0.0772, "step": 13510 }, { "epoch": 1.68, "learning_rate": 9.688285820988423e-06, "loss": 0.0848, "step": 13520 }, { "epoch": 1.68, "learning_rate": 9.688036848001993e-06, "loss": 0.0604, "step": 13530 }, { "epoch": 1.68, "learning_rate": 9.687787875015562e-06, "loss": 0.0983, "step": 13540 }, { "epoch": 1.68, "learning_rate": 9.687538902029132e-06, "loss": 0.0767, "step": 13550 }, { "epoch": 1.68, "learning_rate": 9.687289929042699e-06, "loss": 0.0883, "step": 13560 }, { "epoch": 1.69, "learning_rate": 9.687040956056269e-06, "loss": 0.0835, "step": 13570 }, { "epoch": 1.69, "learning_rate": 9.686791983069837e-06, "loss": 0.0439, "step": 13580 }, { "epoch": 1.69, "learning_rate": 9.686543010083408e-06, "loss": 0.0738, "step": 13590 }, { "epoch": 1.69, "learning_rate": 9.686294037096976e-06, "loss": 0.0833, "step": 13600 }, { "epoch": 1.69, "learning_rate": 9.686045064110545e-06, "loss": 0.0903, "step": 13610 }, { "epoch": 1.69, "learning_rate": 9.685796091124113e-06, "loss": 0.0873, "step": 13620 }, { "epoch": 1.69, "learning_rate": 9.685547118137683e-06, "loss": 0.0637, "step": 13630 }, { "epoch": 1.69, "learning_rate": 9.685298145151252e-06, "loss": 0.0595, "step": 13640 }, { "epoch": 1.69, "learning_rate": 9.68504917216482e-06, "loss": 0.0828, "step": 13650 }, { "epoch": 1.7, "learning_rate": 9.68480019917839e-06, "loss": 0.074, "step": 13660 }, { "epoch": 1.7, "learning_rate": 9.684551226191959e-06, "loss": 0.0702, "step": 13670 }, { "epoch": 1.7, "learning_rate": 9.684302253205528e-06, "loss": 0.0539, "step": 13680 }, { "epoch": 1.7, "learning_rate": 9.684053280219096e-06, "loss": 0.083, "step": 13690 }, { "epoch": 1.7, "learning_rate": 9.683804307232666e-06, "loss": 0.0782, "step": 13700 }, { "epoch": 1.7, "learning_rate": 9.683555334246235e-06, "loss": 0.0567, "step": 13710 }, { "epoch": 1.7, "learning_rate": 9.683306361259805e-06, "loss": 0.0613, "step": 13720 }, { "epoch": 1.7, "learning_rate": 9.683057388273374e-06, "loss": 0.0796, "step": 13730 }, { "epoch": 1.71, "learning_rate": 9.682808415286942e-06, "loss": 0.046, "step": 13740 }, { "epoch": 1.71, "learning_rate": 9.68255944230051e-06, "loss": 0.0696, "step": 13750 }, { "epoch": 1.71, "learning_rate": 9.682310469314081e-06, "loss": 0.0669, "step": 13760 }, { "epoch": 1.71, "learning_rate": 9.68206149632765e-06, "loss": 0.1001, "step": 13770 }, { "epoch": 1.71, "learning_rate": 9.681812523341218e-06, "loss": 0.0896, "step": 13780 }, { "epoch": 1.71, "learning_rate": 9.681563550354788e-06, "loss": 0.0536, "step": 13790 }, { "epoch": 1.71, "learning_rate": 9.681314577368357e-06, "loss": 0.0794, "step": 13800 }, { "epoch": 1.71, "learning_rate": 9.681065604381925e-06, "loss": 0.0716, "step": 13810 }, { "epoch": 1.72, "learning_rate": 9.680816631395494e-06, "loss": 0.0388, "step": 13820 }, { "epoch": 1.72, "learning_rate": 9.680567658409064e-06, "loss": 0.0864, "step": 13830 }, { "epoch": 1.72, "learning_rate": 9.680318685422632e-06, "loss": 0.0344, "step": 13840 }, { "epoch": 1.72, "learning_rate": 9.680069712436203e-06, "loss": 0.0592, "step": 13850 }, { "epoch": 1.72, "learning_rate": 9.67982073944977e-06, "loss": 0.0688, "step": 13860 }, { "epoch": 1.72, "learning_rate": 9.67957176646334e-06, "loss": 0.0662, "step": 13870 }, { "epoch": 1.72, "learning_rate": 9.679322793476908e-06, "loss": 0.0897, "step": 13880 }, { "epoch": 1.72, "learning_rate": 9.679073820490478e-06, "loss": 0.0537, "step": 13890 }, { "epoch": 1.73, "learning_rate": 9.678824847504047e-06, "loss": 0.0457, "step": 13900 }, { "epoch": 1.73, "learning_rate": 9.678575874517615e-06, "loss": 0.0522, "step": 13910 }, { "epoch": 1.73, "learning_rate": 9.678326901531184e-06, "loss": 0.0537, "step": 13920 }, { "epoch": 1.73, "learning_rate": 9.678077928544754e-06, "loss": 0.0656, "step": 13930 }, { "epoch": 1.73, "learning_rate": 9.677828955558323e-06, "loss": 0.0551, "step": 13940 }, { "epoch": 1.73, "learning_rate": 9.677579982571891e-06, "loss": 0.0308, "step": 13950 }, { "epoch": 1.73, "learning_rate": 9.677331009585461e-06, "loss": 0.0642, "step": 13960 }, { "epoch": 1.73, "learning_rate": 9.67708203659903e-06, "loss": 0.0624, "step": 13970 }, { "epoch": 1.74, "learning_rate": 9.676833063612598e-06, "loss": 0.078, "step": 13980 }, { "epoch": 1.74, "learning_rate": 9.676584090626167e-06, "loss": 0.0727, "step": 13990 }, { "epoch": 1.74, "learning_rate": 9.676335117639737e-06, "loss": 0.0332, "step": 14000 }, { "epoch": 1.74, "learning_rate": 9.676086144653306e-06, "loss": 0.0796, "step": 14010 }, { "epoch": 1.74, "learning_rate": 9.675837171666876e-06, "loss": 0.0523, "step": 14020 }, { "epoch": 1.74, "learning_rate": 9.675588198680443e-06, "loss": 0.0793, "step": 14030 }, { "epoch": 1.74, "learning_rate": 9.675339225694013e-06, "loss": 0.0724, "step": 14040 }, { "epoch": 1.74, "learning_rate": 9.675090252707581e-06, "loss": 0.0636, "step": 14050 }, { "epoch": 1.75, "learning_rate": 9.674841279721152e-06, "loss": 0.0712, "step": 14060 }, { "epoch": 1.75, "learning_rate": 9.67459230673472e-06, "loss": 0.0737, "step": 14070 }, { "epoch": 1.75, "learning_rate": 9.67434333374829e-06, "loss": 0.0651, "step": 14080 }, { "epoch": 1.75, "learning_rate": 9.674094360761857e-06, "loss": 0.0743, "step": 14090 }, { "epoch": 1.75, "learning_rate": 9.673845387775427e-06, "loss": 0.0615, "step": 14100 }, { "epoch": 1.75, "learning_rate": 9.673596414788996e-06, "loss": 0.1033, "step": 14110 }, { "epoch": 1.75, "learning_rate": 9.673347441802566e-06, "loss": 0.0819, "step": 14120 }, { "epoch": 1.75, "learning_rate": 9.673098468816135e-06, "loss": 0.0751, "step": 14130 }, { "epoch": 1.76, "learning_rate": 9.672849495829703e-06, "loss": 0.0742, "step": 14140 }, { "epoch": 1.76, "learning_rate": 9.672600522843272e-06, "loss": 0.0593, "step": 14150 }, { "epoch": 1.76, "learning_rate": 9.672351549856842e-06, "loss": 0.0879, "step": 14160 }, { "epoch": 1.76, "learning_rate": 9.67210257687041e-06, "loss": 0.0981, "step": 14170 }, { "epoch": 1.76, "learning_rate": 9.671853603883979e-06, "loss": 0.0736, "step": 14180 }, { "epoch": 1.76, "learning_rate": 9.671604630897549e-06, "loss": 0.0797, "step": 14190 }, { "epoch": 1.76, "learning_rate": 9.671355657911118e-06, "loss": 0.0734, "step": 14200 }, { "epoch": 1.76, "learning_rate": 9.671106684924686e-06, "loss": 0.0392, "step": 14210 }, { "epoch": 1.77, "learning_rate": 9.670857711938255e-06, "loss": 0.0521, "step": 14220 }, { "epoch": 1.77, "learning_rate": 9.670608738951825e-06, "loss": 0.0579, "step": 14230 }, { "epoch": 1.77, "learning_rate": 9.670359765965393e-06, "loss": 0.0626, "step": 14240 }, { "epoch": 1.77, "learning_rate": 9.670110792978964e-06, "loss": 0.0338, "step": 14250 }, { "epoch": 1.77, "learning_rate": 9.669861819992532e-06, "loss": 0.0873, "step": 14260 }, { "epoch": 1.77, "learning_rate": 9.6696128470061e-06, "loss": 0.0584, "step": 14270 }, { "epoch": 1.77, "learning_rate": 9.669363874019669e-06, "loss": 0.0772, "step": 14280 }, { "epoch": 1.77, "learning_rate": 9.66911490103324e-06, "loss": 0.0714, "step": 14290 }, { "epoch": 1.78, "learning_rate": 9.668865928046808e-06, "loss": 0.059, "step": 14300 }, { "epoch": 1.78, "learning_rate": 9.668616955060376e-06, "loss": 0.0607, "step": 14310 }, { "epoch": 1.78, "learning_rate": 9.668367982073947e-06, "loss": 0.0803, "step": 14320 }, { "epoch": 1.78, "learning_rate": 9.668119009087515e-06, "loss": 0.0611, "step": 14330 }, { "epoch": 1.78, "learning_rate": 9.667870036101084e-06, "loss": 0.069, "step": 14340 }, { "epoch": 1.78, "learning_rate": 9.667621063114652e-06, "loss": 0.0816, "step": 14350 }, { "epoch": 1.78, "learning_rate": 9.667372090128222e-06, "loss": 0.0921, "step": 14360 }, { "epoch": 1.78, "learning_rate": 9.66712311714179e-06, "loss": 0.0554, "step": 14370 }, { "epoch": 1.79, "learning_rate": 9.666874144155361e-06, "loss": 0.0682, "step": 14380 }, { "epoch": 1.79, "learning_rate": 9.666625171168928e-06, "loss": 0.0379, "step": 14390 }, { "epoch": 1.79, "learning_rate": 9.666376198182498e-06, "loss": 0.07, "step": 14400 }, { "epoch": 1.79, "learning_rate": 9.666127225196067e-06, "loss": 0.0628, "step": 14410 }, { "epoch": 1.79, "learning_rate": 9.665878252209637e-06, "loss": 0.0969, "step": 14420 }, { "epoch": 1.79, "learning_rate": 9.665629279223205e-06, "loss": 0.0626, "step": 14430 }, { "epoch": 1.79, "learning_rate": 9.665380306236774e-06, "loss": 0.0821, "step": 14440 }, { "epoch": 1.79, "learning_rate": 9.665131333250342e-06, "loss": 0.0544, "step": 14450 }, { "epoch": 1.8, "learning_rate": 9.664882360263913e-06, "loss": 0.0666, "step": 14460 }, { "epoch": 1.8, "learning_rate": 9.664633387277481e-06, "loss": 0.0507, "step": 14470 }, { "epoch": 1.8, "learning_rate": 9.66438441429105e-06, "loss": 0.0667, "step": 14480 }, { "epoch": 1.8, "learning_rate": 9.66413544130462e-06, "loss": 0.0707, "step": 14490 }, { "epoch": 1.8, "learning_rate": 9.663886468318188e-06, "loss": 0.0686, "step": 14500 }, { "epoch": 1.8, "learning_rate": 9.663637495331757e-06, "loss": 0.08, "step": 14510 }, { "epoch": 1.8, "learning_rate": 9.663388522345325e-06, "loss": 0.0857, "step": 14520 }, { "epoch": 1.8, "learning_rate": 9.663139549358896e-06, "loss": 0.0572, "step": 14530 }, { "epoch": 1.81, "learning_rate": 9.662890576372464e-06, "loss": 0.041, "step": 14540 }, { "epoch": 1.81, "learning_rate": 9.662641603386034e-06, "loss": 0.0483, "step": 14550 }, { "epoch": 1.81, "learning_rate": 9.662392630399603e-06, "loss": 0.0772, "step": 14560 }, { "epoch": 1.81, "learning_rate": 9.662143657413171e-06, "loss": 0.1036, "step": 14570 }, { "epoch": 1.81, "learning_rate": 9.66189468442674e-06, "loss": 0.0383, "step": 14580 }, { "epoch": 1.81, "learning_rate": 9.66164571144031e-06, "loss": 0.0673, "step": 14590 }, { "epoch": 1.81, "learning_rate": 9.661396738453879e-06, "loss": 0.0709, "step": 14600 }, { "epoch": 1.81, "learning_rate": 9.661147765467449e-06, "loss": 0.0814, "step": 14610 }, { "epoch": 1.82, "learning_rate": 9.660898792481017e-06, "loss": 0.0521, "step": 14620 }, { "epoch": 1.82, "learning_rate": 9.660649819494586e-06, "loss": 0.0503, "step": 14630 }, { "epoch": 1.82, "learning_rate": 9.660400846508154e-06, "loss": 0.0817, "step": 14640 }, { "epoch": 1.82, "learning_rate": 9.660151873521725e-06, "loss": 0.0707, "step": 14650 }, { "epoch": 1.82, "learning_rate": 9.659902900535293e-06, "loss": 0.0521, "step": 14660 }, { "epoch": 1.82, "learning_rate": 9.659653927548862e-06, "loss": 0.0391, "step": 14670 }, { "epoch": 1.82, "learning_rate": 9.65940495456243e-06, "loss": 0.0756, "step": 14680 }, { "epoch": 1.82, "learning_rate": 9.659155981576e-06, "loss": 0.0675, "step": 14690 }, { "epoch": 1.83, "learning_rate": 9.658907008589569e-06, "loss": 0.0568, "step": 14700 }, { "epoch": 1.83, "learning_rate": 9.658658035603137e-06, "loss": 0.061, "step": 14710 }, { "epoch": 1.83, "learning_rate": 9.658409062616708e-06, "loss": 0.0778, "step": 14720 }, { "epoch": 1.83, "learning_rate": 9.658160089630276e-06, "loss": 0.0635, "step": 14730 }, { "epoch": 1.83, "learning_rate": 9.657911116643845e-06, "loss": 0.0752, "step": 14740 }, { "epoch": 1.83, "learning_rate": 9.657662143657413e-06, "loss": 0.0609, "step": 14750 }, { "epoch": 1.83, "learning_rate": 9.657413170670983e-06, "loss": 0.0658, "step": 14760 }, { "epoch": 1.83, "learning_rate": 9.657164197684552e-06, "loss": 0.0638, "step": 14770 }, { "epoch": 1.84, "learning_rate": 9.656915224698122e-06, "loss": 0.0617, "step": 14780 }, { "epoch": 1.84, "learning_rate": 9.65666625171169e-06, "loss": 0.0572, "step": 14790 }, { "epoch": 1.84, "learning_rate": 9.656417278725259e-06, "loss": 0.0881, "step": 14800 }, { "epoch": 1.84, "learning_rate": 9.656168305738828e-06, "loss": 0.0617, "step": 14810 }, { "epoch": 1.84, "learning_rate": 9.655919332752398e-06, "loss": 0.0527, "step": 14820 }, { "epoch": 1.84, "learning_rate": 9.655670359765966e-06, "loss": 0.0704, "step": 14830 }, { "epoch": 1.84, "learning_rate": 9.655421386779535e-06, "loss": 0.0759, "step": 14840 }, { "epoch": 1.84, "learning_rate": 9.655172413793105e-06, "loss": 0.0624, "step": 14850 }, { "epoch": 1.85, "learning_rate": 9.654923440806674e-06, "loss": 0.0723, "step": 14860 }, { "epoch": 1.85, "learning_rate": 9.654674467820242e-06, "loss": 0.0791, "step": 14870 }, { "epoch": 1.85, "learning_rate": 9.65442549483381e-06, "loss": 0.0707, "step": 14880 }, { "epoch": 1.85, "learning_rate": 9.65417652184738e-06, "loss": 0.0484, "step": 14890 }, { "epoch": 1.85, "learning_rate": 9.65392754886095e-06, "loss": 0.0609, "step": 14900 }, { "epoch": 1.85, "learning_rate": 9.65367857587452e-06, "loss": 0.0579, "step": 14910 }, { "epoch": 1.85, "learning_rate": 9.653429602888086e-06, "loss": 0.079, "step": 14920 }, { "epoch": 1.85, "learning_rate": 9.653180629901657e-06, "loss": 0.0607, "step": 14930 }, { "epoch": 1.86, "learning_rate": 9.652931656915225e-06, "loss": 0.0456, "step": 14940 }, { "epoch": 1.86, "learning_rate": 9.652682683928795e-06, "loss": 0.0987, "step": 14950 }, { "epoch": 1.86, "learning_rate": 9.652433710942364e-06, "loss": 0.0791, "step": 14960 }, { "epoch": 1.86, "learning_rate": 9.652184737955932e-06, "loss": 0.0845, "step": 14970 }, { "epoch": 1.86, "learning_rate": 9.6519357649695e-06, "loss": 0.0869, "step": 14980 }, { "epoch": 1.86, "learning_rate": 9.651686791983071e-06, "loss": 0.0744, "step": 14990 }, { "epoch": 1.86, "learning_rate": 9.65143781899664e-06, "loss": 0.0685, "step": 15000 }, { "epoch": 1.86, "eval_bleu": 89.0594, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7107, "eval_has_error_f1": 0.5339, "eval_loss": 0.05608096718788147, "eval_runtime": 1380.054, "eval_samples_per_second": 2.897, "eval_steps_per_second": 0.725, "step": 15000 }, { "epoch": 1.86, "learning_rate": 9.651188846010208e-06, "loss": 0.0829, "step": 15010 }, { "epoch": 1.87, "learning_rate": 9.650939873023778e-06, "loss": 0.0676, "step": 15020 }, { "epoch": 1.87, "learning_rate": 9.650690900037347e-06, "loss": 0.0398, "step": 15030 }, { "epoch": 1.87, "learning_rate": 9.650441927050915e-06, "loss": 0.0585, "step": 15040 }, { "epoch": 1.87, "learning_rate": 9.650192954064484e-06, "loss": 0.0722, "step": 15050 }, { "epoch": 1.87, "learning_rate": 9.649943981078054e-06, "loss": 0.0745, "step": 15060 }, { "epoch": 1.87, "learning_rate": 9.649695008091623e-06, "loss": 0.07, "step": 15070 }, { "epoch": 1.87, "learning_rate": 9.649446035105193e-06, "loss": 0.0625, "step": 15080 }, { "epoch": 1.87, "learning_rate": 9.649197062118761e-06, "loss": 0.0742, "step": 15090 }, { "epoch": 1.88, "learning_rate": 9.64894808913233e-06, "loss": 0.0465, "step": 15100 }, { "epoch": 1.88, "learning_rate": 9.648699116145898e-06, "loss": 0.0796, "step": 15110 }, { "epoch": 1.88, "learning_rate": 9.648450143159468e-06, "loss": 0.0885, "step": 15120 }, { "epoch": 1.88, "learning_rate": 9.648201170173037e-06, "loss": 0.06, "step": 15130 }, { "epoch": 1.88, "learning_rate": 9.647952197186607e-06, "loss": 0.0831, "step": 15140 }, { "epoch": 1.88, "learning_rate": 9.647703224200176e-06, "loss": 0.0515, "step": 15150 }, { "epoch": 1.88, "learning_rate": 9.647454251213744e-06, "loss": 0.0646, "step": 15160 }, { "epoch": 1.88, "learning_rate": 9.647205278227313e-06, "loss": 0.0535, "step": 15170 }, { "epoch": 1.88, "learning_rate": 9.646956305240883e-06, "loss": 0.0631, "step": 15180 }, { "epoch": 1.89, "learning_rate": 9.646707332254451e-06, "loss": 0.093, "step": 15190 }, { "epoch": 1.89, "learning_rate": 9.64645835926802e-06, "loss": 0.0662, "step": 15200 }, { "epoch": 1.89, "learning_rate": 9.64620938628159e-06, "loss": 0.0782, "step": 15210 }, { "epoch": 1.89, "learning_rate": 9.645960413295157e-06, "loss": 0.0823, "step": 15220 }, { "epoch": 1.89, "learning_rate": 9.645711440308727e-06, "loss": 0.0624, "step": 15230 }, { "epoch": 1.89, "learning_rate": 9.645462467322296e-06, "loss": 0.0481, "step": 15240 }, { "epoch": 1.89, "learning_rate": 9.645213494335866e-06, "loss": 0.0711, "step": 15250 }, { "epoch": 1.89, "learning_rate": 9.644964521349434e-06, "loss": 0.0896, "step": 15260 }, { "epoch": 1.9, "learning_rate": 9.644715548363005e-06, "loss": 0.0696, "step": 15270 }, { "epoch": 1.9, "learning_rate": 9.644466575376572e-06, "loss": 0.0614, "step": 15280 }, { "epoch": 1.9, "learning_rate": 9.644217602390142e-06, "loss": 0.0577, "step": 15290 }, { "epoch": 1.9, "learning_rate": 9.64396862940371e-06, "loss": 0.0819, "step": 15300 }, { "epoch": 1.9, "learning_rate": 9.64371965641728e-06, "loss": 0.07, "step": 15310 }, { "epoch": 1.9, "learning_rate": 9.643470683430849e-06, "loss": 0.0641, "step": 15320 }, { "epoch": 1.9, "learning_rate": 9.643221710444417e-06, "loss": 0.0655, "step": 15330 }, { "epoch": 1.9, "learning_rate": 9.642972737457986e-06, "loss": 0.0471, "step": 15340 }, { "epoch": 1.91, "learning_rate": 9.642723764471556e-06, "loss": 0.0696, "step": 15350 }, { "epoch": 1.91, "learning_rate": 9.642474791485125e-06, "loss": 0.092, "step": 15360 }, { "epoch": 1.91, "learning_rate": 9.642225818498693e-06, "loss": 0.0588, "step": 15370 }, { "epoch": 1.91, "learning_rate": 9.641976845512263e-06, "loss": 0.0404, "step": 15380 }, { "epoch": 1.91, "learning_rate": 9.641727872525832e-06, "loss": 0.0506, "step": 15390 }, { "epoch": 1.91, "learning_rate": 9.6414788995394e-06, "loss": 0.087, "step": 15400 }, { "epoch": 1.91, "learning_rate": 9.641229926552969e-06, "loss": 0.0754, "step": 15410 }, { "epoch": 1.91, "learning_rate": 9.64098095356654e-06, "loss": 0.0791, "step": 15420 }, { "epoch": 1.92, "learning_rate": 9.640731980580108e-06, "loss": 0.0692, "step": 15430 }, { "epoch": 1.92, "learning_rate": 9.640483007593678e-06, "loss": 0.0724, "step": 15440 }, { "epoch": 1.92, "learning_rate": 9.640234034607245e-06, "loss": 0.0483, "step": 15450 }, { "epoch": 1.92, "learning_rate": 9.639985061620815e-06, "loss": 0.0714, "step": 15460 }, { "epoch": 1.92, "learning_rate": 9.639736088634383e-06, "loss": 0.086, "step": 15470 }, { "epoch": 1.92, "learning_rate": 9.639487115647954e-06, "loss": 0.0707, "step": 15480 }, { "epoch": 1.92, "learning_rate": 9.639238142661522e-06, "loss": 0.0466, "step": 15490 }, { "epoch": 1.92, "learning_rate": 9.63898916967509e-06, "loss": 0.0683, "step": 15500 }, { "epoch": 1.93, "learning_rate": 9.63874019668866e-06, "loss": 0.072, "step": 15510 }, { "epoch": 1.93, "learning_rate": 9.63849122370223e-06, "loss": 0.0454, "step": 15520 }, { "epoch": 1.93, "learning_rate": 9.638242250715798e-06, "loss": 0.0626, "step": 15530 }, { "epoch": 1.93, "learning_rate": 9.637993277729366e-06, "loss": 0.0617, "step": 15540 }, { "epoch": 1.93, "learning_rate": 9.637744304742937e-06, "loss": 0.0558, "step": 15550 }, { "epoch": 1.93, "learning_rate": 9.637495331756505e-06, "loss": 0.0642, "step": 15560 }, { "epoch": 1.93, "learning_rate": 9.637246358770074e-06, "loss": 0.0943, "step": 15570 }, { "epoch": 1.93, "learning_rate": 9.636997385783642e-06, "loss": 0.0517, "step": 15580 }, { "epoch": 1.94, "learning_rate": 9.636748412797212e-06, "loss": 0.0747, "step": 15590 }, { "epoch": 1.94, "learning_rate": 9.636499439810781e-06, "loss": 0.0448, "step": 15600 }, { "epoch": 1.94, "learning_rate": 9.636250466824351e-06, "loss": 0.1063, "step": 15610 }, { "epoch": 1.94, "learning_rate": 9.63600149383792e-06, "loss": 0.0783, "step": 15620 }, { "epoch": 1.94, "learning_rate": 9.635752520851488e-06, "loss": 0.062, "step": 15630 }, { "epoch": 1.94, "learning_rate": 9.635503547865057e-06, "loss": 0.0775, "step": 15640 }, { "epoch": 1.94, "learning_rate": 9.635254574878627e-06, "loss": 0.0563, "step": 15650 }, { "epoch": 1.94, "learning_rate": 9.635005601892195e-06, "loss": 0.068, "step": 15660 }, { "epoch": 1.95, "learning_rate": 9.634756628905766e-06, "loss": 0.0704, "step": 15670 }, { "epoch": 1.95, "learning_rate": 9.634507655919334e-06, "loss": 0.0842, "step": 15680 }, { "epoch": 1.95, "learning_rate": 9.634258682932903e-06, "loss": 0.0724, "step": 15690 }, { "epoch": 1.95, "learning_rate": 9.634009709946471e-06, "loss": 0.0806, "step": 15700 }, { "epoch": 1.95, "learning_rate": 9.63376073696004e-06, "loss": 0.0758, "step": 15710 }, { "epoch": 1.95, "learning_rate": 9.63351176397361e-06, "loss": 0.0599, "step": 15720 }, { "epoch": 1.95, "learning_rate": 9.633262790987178e-06, "loss": 0.0862, "step": 15730 }, { "epoch": 1.95, "learning_rate": 9.633013818000749e-06, "loss": 0.0453, "step": 15740 }, { "epoch": 1.96, "learning_rate": 9.632764845014315e-06, "loss": 0.0524, "step": 15750 }, { "epoch": 1.96, "learning_rate": 9.632515872027886e-06, "loss": 0.08, "step": 15760 }, { "epoch": 1.96, "learning_rate": 9.632266899041454e-06, "loss": 0.0623, "step": 15770 }, { "epoch": 1.96, "learning_rate": 9.632017926055024e-06, "loss": 0.0502, "step": 15780 }, { "epoch": 1.96, "learning_rate": 9.631768953068593e-06, "loss": 0.059, "step": 15790 }, { "epoch": 1.96, "learning_rate": 9.631519980082163e-06, "loss": 0.0551, "step": 15800 }, { "epoch": 1.96, "learning_rate": 9.63127100709573e-06, "loss": 0.0675, "step": 15810 }, { "epoch": 1.96, "learning_rate": 9.6310220341093e-06, "loss": 0.0516, "step": 15820 }, { "epoch": 1.97, "learning_rate": 9.630773061122869e-06, "loss": 0.0588, "step": 15830 }, { "epoch": 1.97, "learning_rate": 9.630524088136439e-06, "loss": 0.0652, "step": 15840 }, { "epoch": 1.97, "learning_rate": 9.630275115150007e-06, "loss": 0.0662, "step": 15850 }, { "epoch": 1.97, "learning_rate": 9.630026142163576e-06, "loss": 0.097, "step": 15860 }, { "epoch": 1.97, "learning_rate": 9.629777169177144e-06, "loss": 0.055, "step": 15870 }, { "epoch": 1.97, "learning_rate": 9.629528196190715e-06, "loss": 0.0762, "step": 15880 }, { "epoch": 1.97, "learning_rate": 9.629279223204283e-06, "loss": 0.0425, "step": 15890 }, { "epoch": 1.97, "learning_rate": 9.629030250217852e-06, "loss": 0.064, "step": 15900 }, { "epoch": 1.98, "learning_rate": 9.628781277231422e-06, "loss": 0.0631, "step": 15910 }, { "epoch": 1.98, "learning_rate": 9.62853230424499e-06, "loss": 0.0384, "step": 15920 }, { "epoch": 1.98, "learning_rate": 9.628283331258559e-06, "loss": 0.0502, "step": 15930 }, { "epoch": 1.98, "learning_rate": 9.628034358272127e-06, "loss": 0.0565, "step": 15940 }, { "epoch": 1.98, "learning_rate": 9.627785385285698e-06, "loss": 0.0787, "step": 15950 }, { "epoch": 1.98, "learning_rate": 9.627536412299266e-06, "loss": 0.0656, "step": 15960 }, { "epoch": 1.98, "learning_rate": 9.627287439312836e-06, "loss": 0.0687, "step": 15970 }, { "epoch": 1.98, "learning_rate": 9.627038466326403e-06, "loss": 0.0502, "step": 15980 }, { "epoch": 1.99, "learning_rate": 9.626789493339973e-06, "loss": 0.0413, "step": 15990 }, { "epoch": 1.99, "learning_rate": 9.626540520353542e-06, "loss": 0.071, "step": 16000 }, { "epoch": 1.99, "learning_rate": 9.626291547367112e-06, "loss": 0.0579, "step": 16010 }, { "epoch": 1.99, "learning_rate": 9.62604257438068e-06, "loss": 0.1044, "step": 16020 }, { "epoch": 1.99, "learning_rate": 9.625793601394249e-06, "loss": 0.0813, "step": 16030 }, { "epoch": 1.99, "learning_rate": 9.625544628407818e-06, "loss": 0.0489, "step": 16040 }, { "epoch": 1.99, "learning_rate": 9.625295655421388e-06, "loss": 0.0431, "step": 16050 }, { "epoch": 1.99, "learning_rate": 9.625046682434956e-06, "loss": 0.093, "step": 16060 }, { "epoch": 2.0, "learning_rate": 9.624797709448525e-06, "loss": 0.0633, "step": 16070 }, { "epoch": 2.0, "learning_rate": 9.624548736462095e-06, "loss": 0.0652, "step": 16080 }, { "epoch": 2.0, "learning_rate": 9.624299763475664e-06, "loss": 0.0712, "step": 16090 }, { "epoch": 2.0, "learning_rate": 9.624050790489232e-06, "loss": 0.0737, "step": 16100 }, { "epoch": 2.0, "learning_rate": 9.6238018175028e-06, "loss": 0.0529, "step": 16110 }, { "epoch": 2.0, "learning_rate": 9.623552844516371e-06, "loss": 0.0568, "step": 16120 }, { "epoch": 2.0, "learning_rate": 9.62330387152994e-06, "loss": 0.0887, "step": 16130 }, { "epoch": 2.0, "learning_rate": 9.62305489854351e-06, "loss": 0.0647, "step": 16140 }, { "epoch": 2.01, "learning_rate": 9.622805925557078e-06, "loss": 0.0379, "step": 16150 }, { "epoch": 2.01, "learning_rate": 9.622556952570647e-06, "loss": 0.0691, "step": 16160 }, { "epoch": 2.01, "learning_rate": 9.622307979584215e-06, "loss": 0.0845, "step": 16170 }, { "epoch": 2.01, "learning_rate": 9.622059006597785e-06, "loss": 0.0612, "step": 16180 }, { "epoch": 2.01, "learning_rate": 9.621810033611354e-06, "loss": 0.0496, "step": 16190 }, { "epoch": 2.01, "learning_rate": 9.621561060624922e-06, "loss": 0.0996, "step": 16200 }, { "epoch": 2.01, "learning_rate": 9.621312087638493e-06, "loss": 0.0609, "step": 16210 }, { "epoch": 2.01, "learning_rate": 9.621063114652061e-06, "loss": 0.0621, "step": 16220 }, { "epoch": 2.02, "learning_rate": 9.62081414166563e-06, "loss": 0.0972, "step": 16230 }, { "epoch": 2.02, "learning_rate": 9.620565168679198e-06, "loss": 0.0522, "step": 16240 }, { "epoch": 2.02, "learning_rate": 9.620316195692768e-06, "loss": 0.0697, "step": 16250 }, { "epoch": 2.02, "learning_rate": 9.620067222706337e-06, "loss": 0.0761, "step": 16260 }, { "epoch": 2.02, "learning_rate": 9.619818249719907e-06, "loss": 0.0787, "step": 16270 }, { "epoch": 2.02, "learning_rate": 9.619569276733474e-06, "loss": 0.066, "step": 16280 }, { "epoch": 2.02, "learning_rate": 9.619320303747044e-06, "loss": 0.0873, "step": 16290 }, { "epoch": 2.02, "learning_rate": 9.619071330760613e-06, "loss": 0.0658, "step": 16300 }, { "epoch": 2.03, "learning_rate": 9.618822357774183e-06, "loss": 0.0883, "step": 16310 }, { "epoch": 2.03, "learning_rate": 9.618573384787751e-06, "loss": 0.0487, "step": 16320 }, { "epoch": 2.03, "learning_rate": 9.618324411801322e-06, "loss": 0.0605, "step": 16330 }, { "epoch": 2.03, "learning_rate": 9.618075438814888e-06, "loss": 0.1235, "step": 16340 }, { "epoch": 2.03, "learning_rate": 9.617826465828459e-06, "loss": 0.044, "step": 16350 }, { "epoch": 2.03, "learning_rate": 9.617577492842027e-06, "loss": 0.0643, "step": 16360 }, { "epoch": 2.03, "learning_rate": 9.617328519855597e-06, "loss": 0.1103, "step": 16370 }, { "epoch": 2.03, "learning_rate": 9.617079546869166e-06, "loss": 0.053, "step": 16380 }, { "epoch": 2.04, "learning_rate": 9.616830573882734e-06, "loss": 0.0797, "step": 16390 }, { "epoch": 2.04, "learning_rate": 9.616581600896303e-06, "loss": 0.0347, "step": 16400 }, { "epoch": 2.04, "learning_rate": 9.616332627909873e-06, "loss": 0.065, "step": 16410 }, { "epoch": 2.04, "learning_rate": 9.616083654923442e-06, "loss": 0.0888, "step": 16420 }, { "epoch": 2.04, "learning_rate": 9.61583468193701e-06, "loss": 0.063, "step": 16430 }, { "epoch": 2.04, "learning_rate": 9.61558570895058e-06, "loss": 0.0755, "step": 16440 }, { "epoch": 2.04, "learning_rate": 9.615336735964149e-06, "loss": 0.0661, "step": 16450 }, { "epoch": 2.04, "learning_rate": 9.615087762977717e-06, "loss": 0.0966, "step": 16460 }, { "epoch": 2.05, "learning_rate": 9.614838789991286e-06, "loss": 0.0591, "step": 16470 }, { "epoch": 2.05, "learning_rate": 9.614589817004856e-06, "loss": 0.0638, "step": 16480 }, { "epoch": 2.05, "learning_rate": 9.614340844018425e-06, "loss": 0.0621, "step": 16490 }, { "epoch": 2.05, "learning_rate": 9.614091871031995e-06, "loss": 0.0659, "step": 16500 }, { "epoch": 2.05, "learning_rate": 9.613842898045563e-06, "loss": 0.0845, "step": 16510 }, { "epoch": 2.05, "learning_rate": 9.613593925059132e-06, "loss": 0.0841, "step": 16520 }, { "epoch": 2.05, "learning_rate": 9.6133449520727e-06, "loss": 0.0686, "step": 16530 }, { "epoch": 2.05, "learning_rate": 9.61309597908627e-06, "loss": 0.0438, "step": 16540 }, { "epoch": 2.06, "learning_rate": 9.612847006099839e-06, "loss": 0.0436, "step": 16550 }, { "epoch": 2.06, "learning_rate": 9.612598033113408e-06, "loss": 0.0674, "step": 16560 }, { "epoch": 2.06, "learning_rate": 9.612349060126978e-06, "loss": 0.072, "step": 16570 }, { "epoch": 2.06, "learning_rate": 9.612100087140546e-06, "loss": 0.0703, "step": 16580 }, { "epoch": 2.06, "learning_rate": 9.611851114154115e-06, "loss": 0.0593, "step": 16590 }, { "epoch": 2.06, "learning_rate": 9.611602141167683e-06, "loss": 0.0698, "step": 16600 }, { "epoch": 2.06, "learning_rate": 9.611353168181254e-06, "loss": 0.06, "step": 16610 }, { "epoch": 2.06, "learning_rate": 9.611104195194822e-06, "loss": 0.0678, "step": 16620 }, { "epoch": 2.07, "learning_rate": 9.61085522220839e-06, "loss": 0.0636, "step": 16630 }, { "epoch": 2.07, "learning_rate": 9.610606249221959e-06, "loss": 0.0672, "step": 16640 }, { "epoch": 2.07, "learning_rate": 9.61035727623553e-06, "loss": 0.0598, "step": 16650 }, { "epoch": 2.07, "learning_rate": 9.610108303249098e-06, "loss": 0.0756, "step": 16660 }, { "epoch": 2.07, "learning_rate": 9.609859330262668e-06, "loss": 0.0771, "step": 16670 }, { "epoch": 2.07, "learning_rate": 9.609610357276237e-06, "loss": 0.0648, "step": 16680 }, { "epoch": 2.07, "learning_rate": 9.609361384289805e-06, "loss": 0.0453, "step": 16690 }, { "epoch": 2.07, "learning_rate": 9.609112411303374e-06, "loss": 0.0495, "step": 16700 }, { "epoch": 2.07, "learning_rate": 9.608863438316944e-06, "loss": 0.0784, "step": 16710 }, { "epoch": 2.08, "learning_rate": 9.608614465330512e-06, "loss": 0.0451, "step": 16720 }, { "epoch": 2.08, "learning_rate": 9.60836549234408e-06, "loss": 0.0426, "step": 16730 }, { "epoch": 2.08, "learning_rate": 9.608116519357651e-06, "loss": 0.051, "step": 16740 }, { "epoch": 2.08, "learning_rate": 9.60786754637122e-06, "loss": 0.0866, "step": 16750 }, { "epoch": 2.08, "learning_rate": 9.607618573384788e-06, "loss": 0.0498, "step": 16760 }, { "epoch": 2.08, "learning_rate": 9.607369600398357e-06, "loss": 0.0656, "step": 16770 }, { "epoch": 2.08, "learning_rate": 9.607120627411927e-06, "loss": 0.0687, "step": 16780 }, { "epoch": 2.08, "learning_rate": 9.606871654425495e-06, "loss": 0.0635, "step": 16790 }, { "epoch": 2.09, "learning_rate": 9.606622681439066e-06, "loss": 0.0567, "step": 16800 }, { "epoch": 2.09, "learning_rate": 9.606373708452632e-06, "loss": 0.0629, "step": 16810 }, { "epoch": 2.09, "learning_rate": 9.606124735466203e-06, "loss": 0.0402, "step": 16820 }, { "epoch": 2.09, "learning_rate": 9.605875762479771e-06, "loss": 0.0638, "step": 16830 }, { "epoch": 2.09, "learning_rate": 9.605626789493341e-06, "loss": 0.0533, "step": 16840 }, { "epoch": 2.09, "learning_rate": 9.60537781650691e-06, "loss": 0.0564, "step": 16850 }, { "epoch": 2.09, "learning_rate": 9.60512884352048e-06, "loss": 0.0608, "step": 16860 }, { "epoch": 2.09, "learning_rate": 9.604879870534047e-06, "loss": 0.0402, "step": 16870 }, { "epoch": 2.1, "learning_rate": 9.604630897547617e-06, "loss": 0.085, "step": 16880 }, { "epoch": 2.1, "learning_rate": 9.604381924561186e-06, "loss": 0.0603, "step": 16890 }, { "epoch": 2.1, "learning_rate": 9.604132951574756e-06, "loss": 0.0731, "step": 16900 }, { "epoch": 2.1, "learning_rate": 9.603883978588324e-06, "loss": 0.0579, "step": 16910 }, { "epoch": 2.1, "learning_rate": 9.603635005601893e-06, "loss": 0.0364, "step": 16920 }, { "epoch": 2.1, "learning_rate": 9.603386032615461e-06, "loss": 0.0563, "step": 16930 }, { "epoch": 2.1, "learning_rate": 9.603137059629032e-06, "loss": 0.0584, "step": 16940 }, { "epoch": 2.1, "learning_rate": 9.6028880866426e-06, "loss": 0.0567, "step": 16950 }, { "epoch": 2.11, "learning_rate": 9.602639113656169e-06, "loss": 0.0707, "step": 16960 }, { "epoch": 2.11, "learning_rate": 9.602390140669739e-06, "loss": 0.0719, "step": 16970 }, { "epoch": 2.11, "learning_rate": 9.602141167683307e-06, "loss": 0.0661, "step": 16980 }, { "epoch": 2.11, "learning_rate": 9.601892194696876e-06, "loss": 0.0502, "step": 16990 }, { "epoch": 2.11, "learning_rate": 9.601643221710444e-06, "loss": 0.0691, "step": 17000 }, { "epoch": 2.11, "learning_rate": 9.601394248724015e-06, "loss": 0.063, "step": 17010 }, { "epoch": 2.11, "learning_rate": 9.601145275737583e-06, "loss": 0.0738, "step": 17020 }, { "epoch": 2.11, "learning_rate": 9.600896302751153e-06, "loss": 0.0652, "step": 17030 }, { "epoch": 2.12, "learning_rate": 9.600647329764722e-06, "loss": 0.0775, "step": 17040 }, { "epoch": 2.12, "learning_rate": 9.60039835677829e-06, "loss": 0.0775, "step": 17050 }, { "epoch": 2.12, "learning_rate": 9.600149383791859e-06, "loss": 0.0342, "step": 17060 }, { "epoch": 2.12, "learning_rate": 9.599900410805429e-06, "loss": 0.0482, "step": 17070 }, { "epoch": 2.12, "learning_rate": 9.599651437818998e-06, "loss": 0.0638, "step": 17080 }, { "epoch": 2.12, "learning_rate": 9.599402464832566e-06, "loss": 0.0549, "step": 17090 }, { "epoch": 2.12, "learning_rate": 9.599153491846136e-06, "loss": 0.0504, "step": 17100 }, { "epoch": 2.12, "learning_rate": 9.598904518859705e-06, "loss": 0.0514, "step": 17110 }, { "epoch": 2.13, "learning_rate": 9.598655545873273e-06, "loss": 0.0776, "step": 17120 }, { "epoch": 2.13, "learning_rate": 9.598406572886842e-06, "loss": 0.0586, "step": 17130 }, { "epoch": 2.13, "learning_rate": 9.598157599900412e-06, "loss": 0.0629, "step": 17140 }, { "epoch": 2.13, "learning_rate": 9.59790862691398e-06, "loss": 0.0308, "step": 17150 }, { "epoch": 2.13, "learning_rate": 9.59765965392755e-06, "loss": 0.0419, "step": 17160 }, { "epoch": 2.13, "learning_rate": 9.597410680941118e-06, "loss": 0.0673, "step": 17170 }, { "epoch": 2.13, "learning_rate": 9.597161707954688e-06, "loss": 0.053, "step": 17180 }, { "epoch": 2.13, "learning_rate": 9.596912734968256e-06, "loss": 0.0786, "step": 17190 }, { "epoch": 2.14, "learning_rate": 9.596663761981826e-06, "loss": 0.068, "step": 17200 }, { "epoch": 2.14, "learning_rate": 9.596414788995395e-06, "loss": 0.0799, "step": 17210 }, { "epoch": 2.14, "learning_rate": 9.596165816008964e-06, "loss": 0.0712, "step": 17220 }, { "epoch": 2.14, "learning_rate": 9.595916843022532e-06, "loss": 0.054, "step": 17230 }, { "epoch": 2.14, "learning_rate": 9.595667870036102e-06, "loss": 0.0599, "step": 17240 }, { "epoch": 2.14, "learning_rate": 9.59541889704967e-06, "loss": 0.0596, "step": 17250 }, { "epoch": 2.14, "learning_rate": 9.59516992406324e-06, "loss": 0.1084, "step": 17260 }, { "epoch": 2.14, "learning_rate": 9.59492095107681e-06, "loss": 0.0591, "step": 17270 }, { "epoch": 2.15, "learning_rate": 9.594671978090378e-06, "loss": 0.0343, "step": 17280 }, { "epoch": 2.15, "learning_rate": 9.594423005103947e-06, "loss": 0.0463, "step": 17290 }, { "epoch": 2.15, "learning_rate": 9.594174032117515e-06, "loss": 0.0541, "step": 17300 }, { "epoch": 2.15, "learning_rate": 9.593925059131085e-06, "loss": 0.0908, "step": 17310 }, { "epoch": 2.15, "learning_rate": 9.593676086144654e-06, "loss": 0.1081, "step": 17320 }, { "epoch": 2.15, "learning_rate": 9.593427113158224e-06, "loss": 0.0947, "step": 17330 }, { "epoch": 2.15, "learning_rate": 9.59317814017179e-06, "loss": 0.0534, "step": 17340 }, { "epoch": 2.15, "learning_rate": 9.592929167185361e-06, "loss": 0.0891, "step": 17350 }, { "epoch": 2.16, "learning_rate": 9.59268019419893e-06, "loss": 0.0758, "step": 17360 }, { "epoch": 2.16, "learning_rate": 9.5924312212125e-06, "loss": 0.0815, "step": 17370 }, { "epoch": 2.16, "learning_rate": 9.592182248226068e-06, "loss": 0.0585, "step": 17380 }, { "epoch": 2.16, "learning_rate": 9.591933275239638e-06, "loss": 0.0456, "step": 17390 }, { "epoch": 2.16, "learning_rate": 9.591684302253205e-06, "loss": 0.0519, "step": 17400 }, { "epoch": 2.16, "learning_rate": 9.591435329266775e-06, "loss": 0.0831, "step": 17410 }, { "epoch": 2.16, "learning_rate": 9.591186356280344e-06, "loss": 0.0516, "step": 17420 }, { "epoch": 2.16, "learning_rate": 9.590937383293914e-06, "loss": 0.06, "step": 17430 }, { "epoch": 2.17, "learning_rate": 9.590688410307483e-06, "loss": 0.0666, "step": 17440 }, { "epoch": 2.17, "learning_rate": 9.590439437321051e-06, "loss": 0.0649, "step": 17450 }, { "epoch": 2.17, "learning_rate": 9.59019046433462e-06, "loss": 0.0645, "step": 17460 }, { "epoch": 2.17, "learning_rate": 9.58994149134819e-06, "loss": 0.0692, "step": 17470 }, { "epoch": 2.17, "learning_rate": 9.589692518361758e-06, "loss": 0.0642, "step": 17480 }, { "epoch": 2.17, "learning_rate": 9.589443545375327e-06, "loss": 0.071, "step": 17490 }, { "epoch": 2.17, "learning_rate": 9.589194572388897e-06, "loss": 0.0785, "step": 17500 }, { "epoch": 2.17, "learning_rate": 9.588945599402466e-06, "loss": 0.0776, "step": 17510 }, { "epoch": 2.18, "learning_rate": 9.588696626416034e-06, "loss": 0.0772, "step": 17520 }, { "epoch": 2.18, "learning_rate": 9.588447653429603e-06, "loss": 0.0495, "step": 17530 }, { "epoch": 2.18, "learning_rate": 9.588198680443173e-06, "loss": 0.0616, "step": 17540 }, { "epoch": 2.18, "learning_rate": 9.587949707456741e-06, "loss": 0.0759, "step": 17550 }, { "epoch": 2.18, "learning_rate": 9.587700734470312e-06, "loss": 0.0805, "step": 17560 }, { "epoch": 2.18, "learning_rate": 9.58745176148388e-06, "loss": 0.0492, "step": 17570 }, { "epoch": 2.18, "learning_rate": 9.587202788497449e-06, "loss": 0.0725, "step": 17580 }, { "epoch": 2.18, "learning_rate": 9.586953815511017e-06, "loss": 0.1067, "step": 17590 }, { "epoch": 2.19, "learning_rate": 9.586704842524587e-06, "loss": 0.0441, "step": 17600 }, { "epoch": 2.19, "learning_rate": 9.586455869538156e-06, "loss": 0.0593, "step": 17610 }, { "epoch": 2.19, "learning_rate": 9.586206896551724e-06, "loss": 0.0672, "step": 17620 }, { "epoch": 2.19, "learning_rate": 9.585957923565295e-06, "loss": 0.0674, "step": 17630 }, { "epoch": 2.19, "learning_rate": 9.585708950578863e-06, "loss": 0.107, "step": 17640 }, { "epoch": 2.19, "learning_rate": 9.585459977592432e-06, "loss": 0.0881, "step": 17650 }, { "epoch": 2.19, "learning_rate": 9.585211004606e-06, "loss": 0.0541, "step": 17660 }, { "epoch": 2.19, "learning_rate": 9.58496203161957e-06, "loss": 0.0471, "step": 17670 }, { "epoch": 2.2, "learning_rate": 9.584713058633139e-06, "loss": 0.0805, "step": 17680 }, { "epoch": 2.2, "learning_rate": 9.58446408564671e-06, "loss": 0.0694, "step": 17690 }, { "epoch": 2.2, "learning_rate": 9.584215112660276e-06, "loss": 0.0482, "step": 17700 }, { "epoch": 2.2, "learning_rate": 9.583966139673846e-06, "loss": 0.0751, "step": 17710 }, { "epoch": 2.2, "learning_rate": 9.583717166687415e-06, "loss": 0.0672, "step": 17720 }, { "epoch": 2.2, "learning_rate": 9.583468193700985e-06, "loss": 0.0528, "step": 17730 }, { "epoch": 2.2, "learning_rate": 9.583219220714553e-06, "loss": 0.0434, "step": 17740 }, { "epoch": 2.2, "learning_rate": 9.582970247728122e-06, "loss": 0.0689, "step": 17750 }, { "epoch": 2.21, "learning_rate": 9.58272127474169e-06, "loss": 0.0635, "step": 17760 }, { "epoch": 2.21, "learning_rate": 9.58247230175526e-06, "loss": 0.0578, "step": 17770 }, { "epoch": 2.21, "learning_rate": 9.58222332876883e-06, "loss": 0.0693, "step": 17780 }, { "epoch": 2.21, "learning_rate": 9.581974355782398e-06, "loss": 0.0427, "step": 17790 }, { "epoch": 2.21, "learning_rate": 9.581725382795968e-06, "loss": 0.0765, "step": 17800 }, { "epoch": 2.21, "learning_rate": 9.581476409809536e-06, "loss": 0.0564, "step": 17810 }, { "epoch": 2.21, "learning_rate": 9.581227436823105e-06, "loss": 0.069, "step": 17820 }, { "epoch": 2.21, "learning_rate": 9.580978463836673e-06, "loss": 0.0693, "step": 17830 }, { "epoch": 2.22, "learning_rate": 9.580729490850244e-06, "loss": 0.0729, "step": 17840 }, { "epoch": 2.22, "learning_rate": 9.580480517863812e-06, "loss": 0.0461, "step": 17850 }, { "epoch": 2.22, "learning_rate": 9.580231544877382e-06, "loss": 0.0479, "step": 17860 }, { "epoch": 2.22, "learning_rate": 9.579982571890951e-06, "loss": 0.0938, "step": 17870 }, { "epoch": 2.22, "learning_rate": 9.57973359890452e-06, "loss": 0.0794, "step": 17880 }, { "epoch": 2.22, "learning_rate": 9.579484625918088e-06, "loss": 0.0691, "step": 17890 }, { "epoch": 2.22, "learning_rate": 9.579235652931658e-06, "loss": 0.0699, "step": 17900 }, { "epoch": 2.22, "learning_rate": 9.578986679945227e-06, "loss": 0.092, "step": 17910 }, { "epoch": 2.23, "learning_rate": 9.578737706958797e-06, "loss": 0.0625, "step": 17920 }, { "epoch": 2.23, "learning_rate": 9.578488733972364e-06, "loss": 0.067, "step": 17930 }, { "epoch": 2.23, "learning_rate": 9.578239760985934e-06, "loss": 0.0504, "step": 17940 }, { "epoch": 2.23, "learning_rate": 9.577990787999502e-06, "loss": 0.0334, "step": 17950 }, { "epoch": 2.23, "learning_rate": 9.577741815013073e-06, "loss": 0.0741, "step": 17960 }, { "epoch": 2.23, "learning_rate": 9.577492842026641e-06, "loss": 0.0617, "step": 17970 }, { "epoch": 2.23, "learning_rate": 9.57724386904021e-06, "loss": 0.0632, "step": 17980 }, { "epoch": 2.23, "learning_rate": 9.576994896053778e-06, "loss": 0.0494, "step": 17990 }, { "epoch": 2.24, "learning_rate": 9.576745923067348e-06, "loss": 0.0444, "step": 18000 }, { "epoch": 2.24, "learning_rate": 9.576496950080917e-06, "loss": 0.0771, "step": 18010 }, { "epoch": 2.24, "learning_rate": 9.576247977094485e-06, "loss": 0.0565, "step": 18020 }, { "epoch": 2.24, "learning_rate": 9.575999004108056e-06, "loss": 0.0514, "step": 18030 }, { "epoch": 2.24, "learning_rate": 9.575750031121624e-06, "loss": 0.0487, "step": 18040 }, { "epoch": 2.24, "learning_rate": 9.575501058135193e-06, "loss": 0.0439, "step": 18050 }, { "epoch": 2.24, "learning_rate": 9.575252085148761e-06, "loss": 0.0681, "step": 18060 }, { "epoch": 2.24, "learning_rate": 9.575003112162331e-06, "loss": 0.0636, "step": 18070 }, { "epoch": 2.25, "learning_rate": 9.5747541391759e-06, "loss": 0.0607, "step": 18080 }, { "epoch": 2.25, "learning_rate": 9.57450516618947e-06, "loss": 0.0449, "step": 18090 }, { "epoch": 2.25, "learning_rate": 9.574256193203039e-06, "loss": 0.0545, "step": 18100 }, { "epoch": 2.25, "learning_rate": 9.574007220216607e-06, "loss": 0.0552, "step": 18110 }, { "epoch": 2.25, "learning_rate": 9.573758247230176e-06, "loss": 0.0679, "step": 18120 }, { "epoch": 2.25, "learning_rate": 9.573509274243746e-06, "loss": 0.0816, "step": 18130 }, { "epoch": 2.25, "learning_rate": 9.573260301257314e-06, "loss": 0.0388, "step": 18140 }, { "epoch": 2.25, "learning_rate": 9.573011328270883e-06, "loss": 0.0658, "step": 18150 }, { "epoch": 2.26, "learning_rate": 9.572762355284453e-06, "loss": 0.0891, "step": 18160 }, { "epoch": 2.26, "learning_rate": 9.572513382298022e-06, "loss": 0.0818, "step": 18170 }, { "epoch": 2.26, "learning_rate": 9.57226440931159e-06, "loss": 0.0768, "step": 18180 }, { "epoch": 2.26, "learning_rate": 9.572015436325159e-06, "loss": 0.071, "step": 18190 }, { "epoch": 2.26, "learning_rate": 9.571766463338729e-06, "loss": 0.0578, "step": 18200 }, { "epoch": 2.26, "learning_rate": 9.571517490352297e-06, "loss": 0.0627, "step": 18210 }, { "epoch": 2.26, "learning_rate": 9.571268517365868e-06, "loss": 0.0504, "step": 18220 }, { "epoch": 2.26, "learning_rate": 9.571019544379434e-06, "loss": 0.0695, "step": 18230 }, { "epoch": 2.26, "learning_rate": 9.570770571393005e-06, "loss": 0.0495, "step": 18240 }, { "epoch": 2.27, "learning_rate": 9.570521598406573e-06, "loss": 0.0434, "step": 18250 }, { "epoch": 2.27, "learning_rate": 9.570272625420143e-06, "loss": 0.0534, "step": 18260 }, { "epoch": 2.27, "learning_rate": 9.570023652433712e-06, "loss": 0.088, "step": 18270 }, { "epoch": 2.27, "learning_rate": 9.56977467944728e-06, "loss": 0.0678, "step": 18280 }, { "epoch": 2.27, "learning_rate": 9.569525706460849e-06, "loss": 0.0521, "step": 18290 }, { "epoch": 2.27, "learning_rate": 9.569276733474419e-06, "loss": 0.0583, "step": 18300 }, { "epoch": 2.27, "learning_rate": 9.569027760487988e-06, "loss": 0.0492, "step": 18310 }, { "epoch": 2.27, "learning_rate": 9.568778787501556e-06, "loss": 0.0707, "step": 18320 }, { "epoch": 2.28, "learning_rate": 9.568529814515126e-06, "loss": 0.0627, "step": 18330 }, { "epoch": 2.28, "learning_rate": 9.568280841528695e-06, "loss": 0.0937, "step": 18340 }, { "epoch": 2.28, "learning_rate": 9.568031868542263e-06, "loss": 0.0586, "step": 18350 }, { "epoch": 2.28, "learning_rate": 9.567782895555832e-06, "loss": 0.0678, "step": 18360 }, { "epoch": 2.28, "learning_rate": 9.567533922569402e-06, "loss": 0.0442, "step": 18370 }, { "epoch": 2.28, "learning_rate": 9.56728494958297e-06, "loss": 0.1152, "step": 18380 }, { "epoch": 2.28, "learning_rate": 9.567035976596541e-06, "loss": 0.0457, "step": 18390 }, { "epoch": 2.28, "learning_rate": 9.56678700361011e-06, "loss": 0.0588, "step": 18400 }, { "epoch": 2.29, "learning_rate": 9.566538030623678e-06, "loss": 0.0789, "step": 18410 }, { "epoch": 2.29, "learning_rate": 9.566289057637246e-06, "loss": 0.0598, "step": 18420 }, { "epoch": 2.29, "learning_rate": 9.566040084650817e-06, "loss": 0.0754, "step": 18430 }, { "epoch": 2.29, "learning_rate": 9.565791111664385e-06, "loss": 0.0555, "step": 18440 }, { "epoch": 2.29, "learning_rate": 9.565542138677955e-06, "loss": 0.0591, "step": 18450 }, { "epoch": 2.29, "learning_rate": 9.565293165691524e-06, "loss": 0.0753, "step": 18460 }, { "epoch": 2.29, "learning_rate": 9.565044192705092e-06, "loss": 0.0593, "step": 18470 }, { "epoch": 2.29, "learning_rate": 9.564795219718661e-06, "loss": 0.0493, "step": 18480 }, { "epoch": 2.3, "learning_rate": 9.564546246732231e-06, "loss": 0.0914, "step": 18490 }, { "epoch": 2.3, "learning_rate": 9.5642972737458e-06, "loss": 0.0873, "step": 18500 }, { "epoch": 2.3, "learning_rate": 9.564048300759368e-06, "loss": 0.0357, "step": 18510 }, { "epoch": 2.3, "learning_rate": 9.563799327772938e-06, "loss": 0.0784, "step": 18520 }, { "epoch": 2.3, "learning_rate": 9.563550354786507e-06, "loss": 0.0648, "step": 18530 }, { "epoch": 2.3, "learning_rate": 9.563301381800075e-06, "loss": 0.0608, "step": 18540 }, { "epoch": 2.3, "learning_rate": 9.563052408813644e-06, "loss": 0.0883, "step": 18550 }, { "epoch": 2.3, "learning_rate": 9.562803435827214e-06, "loss": 0.0558, "step": 18560 }, { "epoch": 2.31, "learning_rate": 9.562554462840783e-06, "loss": 0.0549, "step": 18570 }, { "epoch": 2.31, "learning_rate": 9.562305489854351e-06, "loss": 0.0497, "step": 18580 }, { "epoch": 2.31, "learning_rate": 9.56205651686792e-06, "loss": 0.0501, "step": 18590 }, { "epoch": 2.31, "learning_rate": 9.56180754388149e-06, "loss": 0.0515, "step": 18600 }, { "epoch": 2.31, "learning_rate": 9.561558570895058e-06, "loss": 0.0612, "step": 18610 }, { "epoch": 2.31, "learning_rate": 9.561309597908629e-06, "loss": 0.0516, "step": 18620 }, { "epoch": 2.31, "learning_rate": 9.561060624922197e-06, "loss": 0.0617, "step": 18630 }, { "epoch": 2.31, "learning_rate": 9.560811651935766e-06, "loss": 0.0637, "step": 18640 }, { "epoch": 2.32, "learning_rate": 9.560562678949334e-06, "loss": 0.0474, "step": 18650 }, { "epoch": 2.32, "learning_rate": 9.560313705962904e-06, "loss": 0.0777, "step": 18660 }, { "epoch": 2.32, "learning_rate": 9.560064732976473e-06, "loss": 0.0502, "step": 18670 }, { "epoch": 2.32, "learning_rate": 9.559815759990041e-06, "loss": 0.0784, "step": 18680 }, { "epoch": 2.32, "learning_rate": 9.559566787003612e-06, "loss": 0.0668, "step": 18690 }, { "epoch": 2.32, "learning_rate": 9.55931781401718e-06, "loss": 0.0571, "step": 18700 }, { "epoch": 2.32, "learning_rate": 9.559068841030749e-06, "loss": 0.0523, "step": 18710 }, { "epoch": 2.32, "learning_rate": 9.558819868044317e-06, "loss": 0.0838, "step": 18720 }, { "epoch": 2.33, "learning_rate": 9.558570895057887e-06, "loss": 0.0723, "step": 18730 }, { "epoch": 2.33, "learning_rate": 9.558321922071456e-06, "loss": 0.077, "step": 18740 }, { "epoch": 2.33, "learning_rate": 9.558072949085026e-06, "loss": 0.0879, "step": 18750 }, { "epoch": 2.33, "learning_rate": 9.557823976098593e-06, "loss": 0.0848, "step": 18760 }, { "epoch": 2.33, "learning_rate": 9.557575003112163e-06, "loss": 0.0793, "step": 18770 }, { "epoch": 2.33, "learning_rate": 9.557326030125732e-06, "loss": 0.0565, "step": 18780 }, { "epoch": 2.33, "learning_rate": 9.557077057139302e-06, "loss": 0.083, "step": 18790 }, { "epoch": 2.33, "learning_rate": 9.55682808415287e-06, "loss": 0.0735, "step": 18800 }, { "epoch": 2.34, "learning_rate": 9.556579111166439e-06, "loss": 0.0577, "step": 18810 }, { "epoch": 2.34, "learning_rate": 9.556330138180007e-06, "loss": 0.1161, "step": 18820 }, { "epoch": 2.34, "learning_rate": 9.556081165193578e-06, "loss": 0.0639, "step": 18830 }, { "epoch": 2.34, "learning_rate": 9.555832192207146e-06, "loss": 0.0567, "step": 18840 }, { "epoch": 2.34, "learning_rate": 9.555583219220715e-06, "loss": 0.1004, "step": 18850 }, { "epoch": 2.34, "learning_rate": 9.555334246234285e-06, "loss": 0.0802, "step": 18860 }, { "epoch": 2.34, "learning_rate": 9.555085273247853e-06, "loss": 0.0723, "step": 18870 }, { "epoch": 2.34, "learning_rate": 9.554836300261422e-06, "loss": 0.0513, "step": 18880 }, { "epoch": 2.35, "learning_rate": 9.55458732727499e-06, "loss": 0.0692, "step": 18890 }, { "epoch": 2.35, "learning_rate": 9.55433835428856e-06, "loss": 0.0453, "step": 18900 }, { "epoch": 2.35, "learning_rate": 9.554089381302129e-06, "loss": 0.1042, "step": 18910 }, { "epoch": 2.35, "learning_rate": 9.5538404083157e-06, "loss": 0.0746, "step": 18920 }, { "epoch": 2.35, "learning_rate": 9.553591435329268e-06, "loss": 0.0767, "step": 18930 }, { "epoch": 2.35, "learning_rate": 9.553342462342836e-06, "loss": 0.0739, "step": 18940 }, { "epoch": 2.35, "learning_rate": 9.553093489356405e-06, "loss": 0.059, "step": 18950 }, { "epoch": 2.35, "learning_rate": 9.552844516369975e-06, "loss": 0.0593, "step": 18960 }, { "epoch": 2.36, "learning_rate": 9.552595543383544e-06, "loss": 0.0745, "step": 18970 }, { "epoch": 2.36, "learning_rate": 9.552346570397114e-06, "loss": 0.0425, "step": 18980 }, { "epoch": 2.36, "learning_rate": 9.552097597410682e-06, "loss": 0.071, "step": 18990 }, { "epoch": 2.36, "learning_rate": 9.55184862442425e-06, "loss": 0.0899, "step": 19000 }, { "epoch": 2.36, "learning_rate": 9.55159965143782e-06, "loss": 0.0835, "step": 19010 }, { "epoch": 2.36, "learning_rate": 9.55135067845139e-06, "loss": 0.083, "step": 19020 }, { "epoch": 2.36, "learning_rate": 9.551101705464958e-06, "loss": 0.0486, "step": 19030 }, { "epoch": 2.36, "learning_rate": 9.550852732478527e-06, "loss": 0.0581, "step": 19040 }, { "epoch": 2.37, "learning_rate": 9.550603759492097e-06, "loss": 0.0937, "step": 19050 }, { "epoch": 2.37, "learning_rate": 9.550354786505665e-06, "loss": 0.0591, "step": 19060 }, { "epoch": 2.37, "learning_rate": 9.550105813519234e-06, "loss": 0.0656, "step": 19070 }, { "epoch": 2.37, "learning_rate": 9.549856840532802e-06, "loss": 0.0706, "step": 19080 }, { "epoch": 2.37, "learning_rate": 9.549607867546373e-06, "loss": 0.088, "step": 19090 }, { "epoch": 2.37, "learning_rate": 9.549358894559941e-06, "loss": 0.055, "step": 19100 }, { "epoch": 2.37, "learning_rate": 9.549109921573511e-06, "loss": 0.0918, "step": 19110 }, { "epoch": 2.37, "learning_rate": 9.548860948587078e-06, "loss": 0.0621, "step": 19120 }, { "epoch": 2.38, "learning_rate": 9.548611975600648e-06, "loss": 0.0374, "step": 19130 }, { "epoch": 2.38, "learning_rate": 9.548363002614217e-06, "loss": 0.0536, "step": 19140 }, { "epoch": 2.38, "learning_rate": 9.548114029627787e-06, "loss": 0.0504, "step": 19150 }, { "epoch": 2.38, "learning_rate": 9.547865056641356e-06, "loss": 0.0709, "step": 19160 }, { "epoch": 2.38, "learning_rate": 9.547616083654924e-06, "loss": 0.0549, "step": 19170 }, { "epoch": 2.38, "learning_rate": 9.547367110668493e-06, "loss": 0.069, "step": 19180 }, { "epoch": 2.38, "learning_rate": 9.547118137682063e-06, "loss": 0.0463, "step": 19190 }, { "epoch": 2.38, "learning_rate": 9.546869164695631e-06, "loss": 0.043, "step": 19200 }, { "epoch": 2.39, "learning_rate": 9.5466201917092e-06, "loss": 0.0753, "step": 19210 }, { "epoch": 2.39, "learning_rate": 9.54637121872277e-06, "loss": 0.0672, "step": 19220 }, { "epoch": 2.39, "learning_rate": 9.546122245736339e-06, "loss": 0.0717, "step": 19230 }, { "epoch": 2.39, "learning_rate": 9.545873272749907e-06, "loss": 0.0691, "step": 19240 }, { "epoch": 2.39, "learning_rate": 9.545624299763476e-06, "loss": 0.0592, "step": 19250 }, { "epoch": 2.39, "learning_rate": 9.545375326777046e-06, "loss": 0.0765, "step": 19260 }, { "epoch": 2.39, "learning_rate": 9.545126353790614e-06, "loss": 0.0444, "step": 19270 }, { "epoch": 2.39, "learning_rate": 9.544877380804184e-06, "loss": 0.0545, "step": 19280 }, { "epoch": 2.4, "learning_rate": 9.544628407817751e-06, "loss": 0.0494, "step": 19290 }, { "epoch": 2.4, "learning_rate": 9.544379434831322e-06, "loss": 0.0537, "step": 19300 }, { "epoch": 2.4, "learning_rate": 9.54413046184489e-06, "loss": 0.0611, "step": 19310 }, { "epoch": 2.4, "learning_rate": 9.54388148885846e-06, "loss": 0.0615, "step": 19320 }, { "epoch": 2.4, "learning_rate": 9.543632515872029e-06, "loss": 0.0757, "step": 19330 }, { "epoch": 2.4, "learning_rate": 9.543383542885597e-06, "loss": 0.0575, "step": 19340 }, { "epoch": 2.4, "learning_rate": 9.543134569899166e-06, "loss": 0.055, "step": 19350 }, { "epoch": 2.4, "learning_rate": 9.542885596912736e-06, "loss": 0.0748, "step": 19360 }, { "epoch": 2.41, "learning_rate": 9.542636623926305e-06, "loss": 0.0589, "step": 19370 }, { "epoch": 2.41, "learning_rate": 9.542387650939873e-06, "loss": 0.0438, "step": 19380 }, { "epoch": 2.41, "learning_rate": 9.542138677953443e-06, "loss": 0.043, "step": 19390 }, { "epoch": 2.41, "learning_rate": 9.541889704967012e-06, "loss": 0.0606, "step": 19400 }, { "epoch": 2.41, "learning_rate": 9.54164073198058e-06, "loss": 0.0732, "step": 19410 }, { "epoch": 2.41, "learning_rate": 9.541391758994149e-06, "loss": 0.0575, "step": 19420 }, { "epoch": 2.41, "learning_rate": 9.541142786007719e-06, "loss": 0.0572, "step": 19430 }, { "epoch": 2.41, "learning_rate": 9.540893813021288e-06, "loss": 0.0665, "step": 19440 }, { "epoch": 2.42, "learning_rate": 9.540644840034858e-06, "loss": 0.0529, "step": 19450 }, { "epoch": 2.42, "learning_rate": 9.540395867048426e-06, "loss": 0.0597, "step": 19460 }, { "epoch": 2.42, "learning_rate": 9.540146894061995e-06, "loss": 0.0984, "step": 19470 }, { "epoch": 2.42, "learning_rate": 9.539897921075563e-06, "loss": 0.0674, "step": 19480 }, { "epoch": 2.42, "learning_rate": 9.539648948089133e-06, "loss": 0.0553, "step": 19490 }, { "epoch": 2.42, "learning_rate": 9.539399975102702e-06, "loss": 0.0711, "step": 19500 }, { "epoch": 2.42, "learning_rate": 9.539151002116272e-06, "loss": 0.0624, "step": 19510 }, { "epoch": 2.42, "learning_rate": 9.53890202912984e-06, "loss": 0.0485, "step": 19520 }, { "epoch": 2.43, "learning_rate": 9.53865305614341e-06, "loss": 0.0784, "step": 19530 }, { "epoch": 2.43, "learning_rate": 9.538404083156978e-06, "loss": 0.0444, "step": 19540 }, { "epoch": 2.43, "learning_rate": 9.538155110170548e-06, "loss": 0.0634, "step": 19550 }, { "epoch": 2.43, "learning_rate": 9.537906137184116e-06, "loss": 0.0722, "step": 19560 }, { "epoch": 2.43, "learning_rate": 9.537657164197685e-06, "loss": 0.0631, "step": 19570 }, { "epoch": 2.43, "learning_rate": 9.537408191211255e-06, "loss": 0.0594, "step": 19580 }, { "epoch": 2.43, "learning_rate": 9.537159218224824e-06, "loss": 0.0401, "step": 19590 }, { "epoch": 2.43, "learning_rate": 9.536910245238392e-06, "loss": 0.0584, "step": 19600 }, { "epoch": 2.44, "learning_rate": 9.53666127225196e-06, "loss": 0.0621, "step": 19610 }, { "epoch": 2.44, "learning_rate": 9.536412299265531e-06, "loss": 0.0557, "step": 19620 }, { "epoch": 2.44, "learning_rate": 9.5361633262791e-06, "loss": 0.0558, "step": 19630 }, { "epoch": 2.44, "learning_rate": 9.53591435329267e-06, "loss": 0.0755, "step": 19640 }, { "epoch": 2.44, "learning_rate": 9.535665380306237e-06, "loss": 0.0524, "step": 19650 }, { "epoch": 2.44, "learning_rate": 9.535416407319807e-06, "loss": 0.0659, "step": 19660 }, { "epoch": 2.44, "learning_rate": 9.535167434333375e-06, "loss": 0.0626, "step": 19670 }, { "epoch": 2.44, "learning_rate": 9.534918461346945e-06, "loss": 0.0426, "step": 19680 }, { "epoch": 2.45, "learning_rate": 9.534669488360514e-06, "loss": 0.0977, "step": 19690 }, { "epoch": 2.45, "learning_rate": 9.534420515374082e-06, "loss": 0.0575, "step": 19700 }, { "epoch": 2.45, "learning_rate": 9.534171542387651e-06, "loss": 0.0687, "step": 19710 }, { "epoch": 2.45, "learning_rate": 9.533922569401221e-06, "loss": 0.0885, "step": 19720 }, { "epoch": 2.45, "learning_rate": 9.53367359641479e-06, "loss": 0.0719, "step": 19730 }, { "epoch": 2.45, "learning_rate": 9.533424623428358e-06, "loss": 0.0716, "step": 19740 }, { "epoch": 2.45, "learning_rate": 9.533175650441928e-06, "loss": 0.0461, "step": 19750 }, { "epoch": 2.45, "learning_rate": 9.532926677455497e-06, "loss": 0.0864, "step": 19760 }, { "epoch": 2.45, "learning_rate": 9.532677704469065e-06, "loss": 0.1026, "step": 19770 }, { "epoch": 2.46, "learning_rate": 9.532428731482634e-06, "loss": 0.0465, "step": 19780 }, { "epoch": 2.46, "learning_rate": 9.532179758496204e-06, "loss": 0.0648, "step": 19790 }, { "epoch": 2.46, "learning_rate": 9.531930785509773e-06, "loss": 0.081, "step": 19800 }, { "epoch": 2.46, "learning_rate": 9.531681812523343e-06, "loss": 0.0573, "step": 19810 }, { "epoch": 2.46, "learning_rate": 9.531432839536911e-06, "loss": 0.0442, "step": 19820 }, { "epoch": 2.46, "learning_rate": 9.53118386655048e-06, "loss": 0.0891, "step": 19830 }, { "epoch": 2.46, "learning_rate": 9.530934893564048e-06, "loss": 0.0581, "step": 19840 }, { "epoch": 2.46, "learning_rate": 9.530685920577619e-06, "loss": 0.0616, "step": 19850 }, { "epoch": 2.47, "learning_rate": 9.530436947591187e-06, "loss": 0.0573, "step": 19860 }, { "epoch": 2.47, "learning_rate": 9.530187974604756e-06, "loss": 0.0658, "step": 19870 }, { "epoch": 2.47, "learning_rate": 9.529939001618324e-06, "loss": 0.0549, "step": 19880 }, { "epoch": 2.47, "learning_rate": 9.529690028631894e-06, "loss": 0.0956, "step": 19890 }, { "epoch": 2.47, "learning_rate": 9.529441055645463e-06, "loss": 0.0551, "step": 19900 }, { "epoch": 2.47, "learning_rate": 9.529192082659031e-06, "loss": 0.0799, "step": 19910 }, { "epoch": 2.47, "learning_rate": 9.528943109672602e-06, "loss": 0.0632, "step": 19920 }, { "epoch": 2.47, "learning_rate": 9.52869413668617e-06, "loss": 0.0563, "step": 19930 }, { "epoch": 2.48, "learning_rate": 9.528445163699739e-06, "loss": 0.0482, "step": 19940 }, { "epoch": 2.48, "learning_rate": 9.528196190713307e-06, "loss": 0.0384, "step": 19950 }, { "epoch": 2.48, "learning_rate": 9.527947217726877e-06, "loss": 0.0506, "step": 19960 }, { "epoch": 2.48, "learning_rate": 9.527698244740446e-06, "loss": 0.0572, "step": 19970 }, { "epoch": 2.48, "learning_rate": 9.527449271754016e-06, "loss": 0.065, "step": 19980 }, { "epoch": 2.48, "learning_rate": 9.527200298767585e-06, "loss": 0.0687, "step": 19990 }, { "epoch": 2.48, "learning_rate": 9.526951325781153e-06, "loss": 0.0495, "step": 20000 }, { "epoch": 2.48, "eval_bleu": 89.0871, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7482, "eval_has_error_f1": 0.641, "eval_loss": 0.055173203349113464, "eval_runtime": 1394.8864, "eval_samples_per_second": 2.866, "eval_steps_per_second": 0.717, "step": 20000 }, { "epoch": 2.48, "learning_rate": 9.526702352794722e-06, "loss": 0.0685, "step": 20010 }, { "epoch": 2.49, "learning_rate": 9.526453379808292e-06, "loss": 0.0688, "step": 20020 }, { "epoch": 2.49, "learning_rate": 9.52620440682186e-06, "loss": 0.054, "step": 20030 }, { "epoch": 2.49, "learning_rate": 9.52595543383543e-06, "loss": 0.0519, "step": 20040 }, { "epoch": 2.49, "learning_rate": 9.525706460849e-06, "loss": 0.0521, "step": 20050 }, { "epoch": 2.49, "learning_rate": 9.525457487862568e-06, "loss": 0.078, "step": 20060 }, { "epoch": 2.49, "learning_rate": 9.525208514876136e-06, "loss": 0.0381, "step": 20070 }, { "epoch": 2.49, "learning_rate": 9.524959541889706e-06, "loss": 0.0468, "step": 20080 }, { "epoch": 2.49, "learning_rate": 9.524710568903275e-06, "loss": 0.0622, "step": 20090 }, { "epoch": 2.5, "learning_rate": 9.524461595916843e-06, "loss": 0.0285, "step": 20100 }, { "epoch": 2.5, "learning_rate": 9.524212622930414e-06, "loss": 0.0589, "step": 20110 }, { "epoch": 2.5, "learning_rate": 9.523963649943982e-06, "loss": 0.0501, "step": 20120 }, { "epoch": 2.5, "learning_rate": 9.52371467695755e-06, "loss": 0.0867, "step": 20130 }, { "epoch": 2.5, "learning_rate": 9.52346570397112e-06, "loss": 0.0901, "step": 20140 }, { "epoch": 2.5, "learning_rate": 9.52321673098469e-06, "loss": 0.0701, "step": 20150 }, { "epoch": 2.5, "learning_rate": 9.522967757998258e-06, "loss": 0.0451, "step": 20160 }, { "epoch": 2.5, "learning_rate": 9.522718785011828e-06, "loss": 0.0922, "step": 20170 }, { "epoch": 2.51, "learning_rate": 9.522469812025395e-06, "loss": 0.0693, "step": 20180 }, { "epoch": 2.51, "learning_rate": 9.522220839038965e-06, "loss": 0.0495, "step": 20190 }, { "epoch": 2.51, "learning_rate": 9.521971866052534e-06, "loss": 0.038, "step": 20200 }, { "epoch": 2.51, "learning_rate": 9.521722893066104e-06, "loss": 0.0654, "step": 20210 }, { "epoch": 2.51, "learning_rate": 9.521473920079672e-06, "loss": 0.078, "step": 20220 }, { "epoch": 2.51, "learning_rate": 9.521224947093241e-06, "loss": 0.0369, "step": 20230 }, { "epoch": 2.51, "learning_rate": 9.52097597410681e-06, "loss": 0.0522, "step": 20240 }, { "epoch": 2.51, "learning_rate": 9.52072700112038e-06, "loss": 0.0524, "step": 20250 }, { "epoch": 2.52, "learning_rate": 9.520478028133948e-06, "loss": 0.0572, "step": 20260 }, { "epoch": 2.52, "learning_rate": 9.520229055147517e-06, "loss": 0.0562, "step": 20270 }, { "epoch": 2.52, "learning_rate": 9.519980082161087e-06, "loss": 0.0539, "step": 20280 }, { "epoch": 2.52, "learning_rate": 9.519731109174655e-06, "loss": 0.0663, "step": 20290 }, { "epoch": 2.52, "learning_rate": 9.519482136188224e-06, "loss": 0.0408, "step": 20300 }, { "epoch": 2.52, "learning_rate": 9.519233163201792e-06, "loss": 0.0686, "step": 20310 }, { "epoch": 2.52, "learning_rate": 9.518984190215363e-06, "loss": 0.0748, "step": 20320 }, { "epoch": 2.52, "learning_rate": 9.518735217228931e-06, "loss": 0.078, "step": 20330 }, { "epoch": 2.53, "learning_rate": 9.518486244242501e-06, "loss": 0.0633, "step": 20340 }, { "epoch": 2.53, "learning_rate": 9.51823727125607e-06, "loss": 0.0565, "step": 20350 }, { "epoch": 2.53, "learning_rate": 9.517988298269638e-06, "loss": 0.055, "step": 20360 }, { "epoch": 2.53, "learning_rate": 9.517739325283207e-06, "loss": 0.0858, "step": 20370 }, { "epoch": 2.53, "learning_rate": 9.517490352296777e-06, "loss": 0.0492, "step": 20380 }, { "epoch": 2.53, "learning_rate": 9.517241379310346e-06, "loss": 0.0432, "step": 20390 }, { "epoch": 2.53, "learning_rate": 9.516992406323914e-06, "loss": 0.0799, "step": 20400 }, { "epoch": 2.53, "learning_rate": 9.516743433337484e-06, "loss": 0.0814, "step": 20410 }, { "epoch": 2.54, "learning_rate": 9.516494460351053e-06, "loss": 0.0432, "step": 20420 }, { "epoch": 2.54, "learning_rate": 9.516245487364621e-06, "loss": 0.0913, "step": 20430 }, { "epoch": 2.54, "learning_rate": 9.51599651437819e-06, "loss": 0.063, "step": 20440 }, { "epoch": 2.54, "learning_rate": 9.51574754139176e-06, "loss": 0.0439, "step": 20450 }, { "epoch": 2.54, "learning_rate": 9.515498568405329e-06, "loss": 0.0526, "step": 20460 }, { "epoch": 2.54, "learning_rate": 9.515249595418899e-06, "loss": 0.065, "step": 20470 }, { "epoch": 2.54, "learning_rate": 9.515000622432466e-06, "loss": 0.0572, "step": 20480 }, { "epoch": 2.54, "learning_rate": 9.514751649446036e-06, "loss": 0.0506, "step": 20490 }, { "epoch": 2.55, "learning_rate": 9.514502676459604e-06, "loss": 0.0689, "step": 20500 }, { "epoch": 2.55, "learning_rate": 9.514253703473175e-06, "loss": 0.0735, "step": 20510 }, { "epoch": 2.55, "learning_rate": 9.514004730486743e-06, "loss": 0.0728, "step": 20520 }, { "epoch": 2.55, "learning_rate": 9.513755757500312e-06, "loss": 0.0642, "step": 20530 }, { "epoch": 2.55, "learning_rate": 9.51350678451388e-06, "loss": 0.0681, "step": 20540 }, { "epoch": 2.55, "learning_rate": 9.51325781152745e-06, "loss": 0.0463, "step": 20550 }, { "epoch": 2.55, "learning_rate": 9.513008838541019e-06, "loss": 0.0506, "step": 20560 }, { "epoch": 2.55, "learning_rate": 9.512759865554589e-06, "loss": 0.077, "step": 20570 }, { "epoch": 2.56, "learning_rate": 9.512510892568158e-06, "loss": 0.0604, "step": 20580 }, { "epoch": 2.56, "learning_rate": 9.512261919581726e-06, "loss": 0.0571, "step": 20590 }, { "epoch": 2.56, "learning_rate": 9.512012946595295e-06, "loss": 0.0449, "step": 20600 }, { "epoch": 2.56, "learning_rate": 9.511763973608865e-06, "loss": 0.0533, "step": 20610 }, { "epoch": 2.56, "learning_rate": 9.511515000622433e-06, "loss": 0.0757, "step": 20620 }, { "epoch": 2.56, "learning_rate": 9.511266027636002e-06, "loss": 0.0603, "step": 20630 }, { "epoch": 2.56, "learning_rate": 9.511017054649572e-06, "loss": 0.035, "step": 20640 }, { "epoch": 2.56, "learning_rate": 9.51076808166314e-06, "loss": 0.0558, "step": 20650 }, { "epoch": 2.57, "learning_rate": 9.510519108676709e-06, "loss": 0.059, "step": 20660 }, { "epoch": 2.57, "learning_rate": 9.510270135690278e-06, "loss": 0.0517, "step": 20670 }, { "epoch": 2.57, "learning_rate": 9.510021162703848e-06, "loss": 0.0335, "step": 20680 }, { "epoch": 2.57, "learning_rate": 9.509772189717416e-06, "loss": 0.0758, "step": 20690 }, { "epoch": 2.57, "learning_rate": 9.509523216730987e-06, "loss": 0.0913, "step": 20700 }, { "epoch": 2.57, "learning_rate": 9.509274243744553e-06, "loss": 0.0505, "step": 20710 }, { "epoch": 2.57, "learning_rate": 9.509025270758124e-06, "loss": 0.0493, "step": 20720 }, { "epoch": 2.57, "learning_rate": 9.508776297771692e-06, "loss": 0.0564, "step": 20730 }, { "epoch": 2.58, "learning_rate": 9.508527324785262e-06, "loss": 0.0534, "step": 20740 }, { "epoch": 2.58, "learning_rate": 9.508278351798831e-06, "loss": 0.0669, "step": 20750 }, { "epoch": 2.58, "learning_rate": 9.5080293788124e-06, "loss": 0.057, "step": 20760 }, { "epoch": 2.58, "learning_rate": 9.507780405825968e-06, "loss": 0.082, "step": 20770 }, { "epoch": 2.58, "learning_rate": 9.507531432839538e-06, "loss": 0.0314, "step": 20780 }, { "epoch": 2.58, "learning_rate": 9.507282459853107e-06, "loss": 0.0499, "step": 20790 }, { "epoch": 2.58, "learning_rate": 9.507033486866675e-06, "loss": 0.0677, "step": 20800 }, { "epoch": 2.58, "learning_rate": 9.506784513880245e-06, "loss": 0.0642, "step": 20810 }, { "epoch": 2.59, "learning_rate": 9.506535540893814e-06, "loss": 0.0461, "step": 20820 }, { "epoch": 2.59, "learning_rate": 9.506286567907382e-06, "loss": 0.0476, "step": 20830 }, { "epoch": 2.59, "learning_rate": 9.506037594920951e-06, "loss": 0.0748, "step": 20840 }, { "epoch": 2.59, "learning_rate": 9.505788621934521e-06, "loss": 0.0725, "step": 20850 }, { "epoch": 2.59, "learning_rate": 9.50553964894809e-06, "loss": 0.0837, "step": 20860 }, { "epoch": 2.59, "learning_rate": 9.50529067596166e-06, "loss": 0.0554, "step": 20870 }, { "epoch": 2.59, "learning_rate": 9.505041702975228e-06, "loss": 0.0418, "step": 20880 }, { "epoch": 2.59, "learning_rate": 9.504792729988797e-06, "loss": 0.0404, "step": 20890 }, { "epoch": 2.6, "learning_rate": 9.504543757002365e-06, "loss": 0.0487, "step": 20900 }, { "epoch": 2.6, "learning_rate": 9.504294784015936e-06, "loss": 0.0624, "step": 20910 }, { "epoch": 2.6, "learning_rate": 9.504045811029504e-06, "loss": 0.0725, "step": 20920 }, { "epoch": 2.6, "learning_rate": 9.503796838043073e-06, "loss": 0.0881, "step": 20930 }, { "epoch": 2.6, "learning_rate": 9.503547865056643e-06, "loss": 0.0882, "step": 20940 }, { "epoch": 2.6, "learning_rate": 9.503298892070211e-06, "loss": 0.0535, "step": 20950 }, { "epoch": 2.6, "learning_rate": 9.50304991908378e-06, "loss": 0.0849, "step": 20960 }, { "epoch": 2.6, "learning_rate": 9.502800946097348e-06, "loss": 0.064, "step": 20970 }, { "epoch": 2.61, "learning_rate": 9.502551973110919e-06, "loss": 0.0727, "step": 20980 }, { "epoch": 2.61, "learning_rate": 9.502303000124487e-06, "loss": 0.0398, "step": 20990 }, { "epoch": 2.61, "learning_rate": 9.502054027138057e-06, "loss": 0.0457, "step": 21000 }, { "epoch": 2.61, "learning_rate": 9.501805054151624e-06, "loss": 0.074, "step": 21010 }, { "epoch": 2.61, "learning_rate": 9.501556081165194e-06, "loss": 0.0819, "step": 21020 }, { "epoch": 2.61, "learning_rate": 9.501307108178763e-06, "loss": 0.1167, "step": 21030 }, { "epoch": 2.61, "learning_rate": 9.501058135192333e-06, "loss": 0.0427, "step": 21040 }, { "epoch": 2.61, "learning_rate": 9.500809162205902e-06, "loss": 0.041, "step": 21050 }, { "epoch": 2.62, "learning_rate": 9.500560189219472e-06, "loss": 0.075, "step": 21060 }, { "epoch": 2.62, "learning_rate": 9.500311216233039e-06, "loss": 0.0924, "step": 21070 }, { "epoch": 2.62, "learning_rate": 9.500062243246609e-06, "loss": 0.0467, "step": 21080 }, { "epoch": 2.62, "learning_rate": 9.499813270260177e-06, "loss": 0.0573, "step": 21090 }, { "epoch": 2.62, "learning_rate": 9.499564297273748e-06, "loss": 0.0745, "step": 21100 }, { "epoch": 2.62, "learning_rate": 9.499315324287316e-06, "loss": 0.0671, "step": 21110 }, { "epoch": 2.62, "learning_rate": 9.499066351300885e-06, "loss": 0.0666, "step": 21120 }, { "epoch": 2.62, "learning_rate": 9.498817378314453e-06, "loss": 0.085, "step": 21130 }, { "epoch": 2.63, "learning_rate": 9.498568405328023e-06, "loss": 0.0412, "step": 21140 }, { "epoch": 2.63, "learning_rate": 9.498319432341592e-06, "loss": 0.0702, "step": 21150 }, { "epoch": 2.63, "learning_rate": 9.49807045935516e-06, "loss": 0.0562, "step": 21160 }, { "epoch": 2.63, "learning_rate": 9.49782148636873e-06, "loss": 0.0649, "step": 21170 }, { "epoch": 2.63, "learning_rate": 9.497572513382299e-06, "loss": 0.0613, "step": 21180 }, { "epoch": 2.63, "learning_rate": 9.497323540395868e-06, "loss": 0.0519, "step": 21190 }, { "epoch": 2.63, "learning_rate": 9.497074567409436e-06, "loss": 0.0649, "step": 21200 }, { "epoch": 2.63, "learning_rate": 9.496825594423006e-06, "loss": 0.0643, "step": 21210 }, { "epoch": 2.64, "learning_rate": 9.496576621436575e-06, "loss": 0.0612, "step": 21220 }, { "epoch": 2.64, "learning_rate": 9.496327648450145e-06, "loss": 0.0603, "step": 21230 }, { "epoch": 2.64, "learning_rate": 9.496078675463712e-06, "loss": 0.0453, "step": 21240 }, { "epoch": 2.64, "learning_rate": 9.495829702477282e-06, "loss": 0.0735, "step": 21250 }, { "epoch": 2.64, "learning_rate": 9.49558072949085e-06, "loss": 0.0705, "step": 21260 }, { "epoch": 2.64, "learning_rate": 9.49533175650442e-06, "loss": 0.0811, "step": 21270 }, { "epoch": 2.64, "learning_rate": 9.49508278351799e-06, "loss": 0.0815, "step": 21280 }, { "epoch": 2.64, "learning_rate": 9.494833810531558e-06, "loss": 0.0907, "step": 21290 }, { "epoch": 2.64, "learning_rate": 9.494584837545126e-06, "loss": 0.0419, "step": 21300 }, { "epoch": 2.65, "learning_rate": 9.494335864558697e-06, "loss": 0.0699, "step": 21310 }, { "epoch": 2.65, "learning_rate": 9.494086891572265e-06, "loss": 0.0705, "step": 21320 }, { "epoch": 2.65, "learning_rate": 9.493837918585834e-06, "loss": 0.0633, "step": 21330 }, { "epoch": 2.65, "learning_rate": 9.493588945599404e-06, "loss": 0.0596, "step": 21340 }, { "epoch": 2.65, "learning_rate": 9.493339972612972e-06, "loss": 0.0597, "step": 21350 }, { "epoch": 2.65, "learning_rate": 9.49309099962654e-06, "loss": 0.0582, "step": 21360 }, { "epoch": 2.65, "learning_rate": 9.49284202664011e-06, "loss": 0.0709, "step": 21370 }, { "epoch": 2.65, "learning_rate": 9.49259305365368e-06, "loss": 0.0769, "step": 21380 }, { "epoch": 2.66, "learning_rate": 9.492344080667248e-06, "loss": 0.0631, "step": 21390 }, { "epoch": 2.66, "learning_rate": 9.492095107680818e-06, "loss": 0.0656, "step": 21400 }, { "epoch": 2.66, "learning_rate": 9.491846134694387e-06, "loss": 0.0795, "step": 21410 }, { "epoch": 2.66, "learning_rate": 9.491597161707955e-06, "loss": 0.0665, "step": 21420 }, { "epoch": 2.66, "learning_rate": 9.491348188721524e-06, "loss": 0.093, "step": 21430 }, { "epoch": 2.66, "learning_rate": 9.491099215735094e-06, "loss": 0.0946, "step": 21440 }, { "epoch": 2.66, "learning_rate": 9.490850242748663e-06, "loss": 0.0586, "step": 21450 }, { "epoch": 2.66, "learning_rate": 9.490601269762231e-06, "loss": 0.0641, "step": 21460 }, { "epoch": 2.67, "learning_rate": 9.490352296775801e-06, "loss": 0.0677, "step": 21470 }, { "epoch": 2.67, "learning_rate": 9.49010332378937e-06, "loss": 0.0749, "step": 21480 }, { "epoch": 2.67, "learning_rate": 9.489854350802938e-06, "loss": 0.059, "step": 21490 }, { "epoch": 2.67, "learning_rate": 9.489605377816507e-06, "loss": 0.068, "step": 21500 }, { "epoch": 2.67, "learning_rate": 9.489356404830077e-06, "loss": 0.1014, "step": 21510 }, { "epoch": 2.67, "learning_rate": 9.489107431843646e-06, "loss": 0.0847, "step": 21520 }, { "epoch": 2.67, "learning_rate": 9.488858458857216e-06, "loss": 0.0601, "step": 21530 }, { "epoch": 2.67, "learning_rate": 9.488609485870783e-06, "loss": 0.0606, "step": 21540 }, { "epoch": 2.68, "learning_rate": 9.488360512884353e-06, "loss": 0.0618, "step": 21550 }, { "epoch": 2.68, "learning_rate": 9.488111539897921e-06, "loss": 0.0827, "step": 21560 }, { "epoch": 2.68, "learning_rate": 9.487862566911492e-06, "loss": 0.0484, "step": 21570 }, { "epoch": 2.68, "learning_rate": 9.48761359392506e-06, "loss": 0.084, "step": 21580 }, { "epoch": 2.68, "learning_rate": 9.48736462093863e-06, "loss": 0.0739, "step": 21590 }, { "epoch": 2.68, "learning_rate": 9.487115647952197e-06, "loss": 0.0605, "step": 21600 }, { "epoch": 2.68, "learning_rate": 9.486866674965767e-06, "loss": 0.0503, "step": 21610 }, { "epoch": 2.68, "learning_rate": 9.486617701979336e-06, "loss": 0.0794, "step": 21620 }, { "epoch": 2.69, "learning_rate": 9.486368728992906e-06, "loss": 0.0798, "step": 21630 }, { "epoch": 2.69, "learning_rate": 9.486119756006475e-06, "loss": 0.0647, "step": 21640 }, { "epoch": 2.69, "learning_rate": 9.485870783020043e-06, "loss": 0.0914, "step": 21650 }, { "epoch": 2.69, "learning_rate": 9.485621810033612e-06, "loss": 0.0864, "step": 21660 }, { "epoch": 2.69, "learning_rate": 9.485372837047182e-06, "loss": 0.0691, "step": 21670 }, { "epoch": 2.69, "learning_rate": 9.48512386406075e-06, "loss": 0.0684, "step": 21680 }, { "epoch": 2.69, "learning_rate": 9.484874891074319e-06, "loss": 0.0822, "step": 21690 }, { "epoch": 2.69, "learning_rate": 9.484625918087889e-06, "loss": 0.093, "step": 21700 }, { "epoch": 2.7, "learning_rate": 9.484376945101457e-06, "loss": 0.071, "step": 21710 }, { "epoch": 2.7, "learning_rate": 9.484127972115026e-06, "loss": 0.0738, "step": 21720 }, { "epoch": 2.7, "learning_rate": 9.483878999128595e-06, "loss": 0.0757, "step": 21730 }, { "epoch": 2.7, "learning_rate": 9.483630026142165e-06, "loss": 0.0478, "step": 21740 }, { "epoch": 2.7, "learning_rate": 9.483381053155733e-06, "loss": 0.0544, "step": 21750 }, { "epoch": 2.7, "learning_rate": 9.483132080169303e-06, "loss": 0.0647, "step": 21760 }, { "epoch": 2.7, "learning_rate": 9.482883107182872e-06, "loss": 0.0514, "step": 21770 }, { "epoch": 2.7, "learning_rate": 9.48263413419644e-06, "loss": 0.0645, "step": 21780 }, { "epoch": 2.71, "learning_rate": 9.482385161210009e-06, "loss": 0.0721, "step": 21790 }, { "epoch": 2.71, "learning_rate": 9.48213618822358e-06, "loss": 0.0479, "step": 21800 }, { "epoch": 2.71, "learning_rate": 9.481887215237148e-06, "loss": 0.0509, "step": 21810 }, { "epoch": 2.71, "learning_rate": 9.481638242250716e-06, "loss": 0.0525, "step": 21820 }, { "epoch": 2.71, "learning_rate": 9.481389269264286e-06, "loss": 0.0521, "step": 21830 }, { "epoch": 2.71, "learning_rate": 9.481140296277855e-06, "loss": 0.0584, "step": 21840 }, { "epoch": 2.71, "learning_rate": 9.480891323291423e-06, "loss": 0.0447, "step": 21850 }, { "epoch": 2.71, "learning_rate": 9.480642350304992e-06, "loss": 0.0845, "step": 21860 }, { "epoch": 2.72, "learning_rate": 9.480393377318562e-06, "loss": 0.0736, "step": 21870 }, { "epoch": 2.72, "learning_rate": 9.48014440433213e-06, "loss": 0.088, "step": 21880 }, { "epoch": 2.72, "learning_rate": 9.4798954313457e-06, "loss": 0.0666, "step": 21890 }, { "epoch": 2.72, "learning_rate": 9.479646458359268e-06, "loss": 0.0462, "step": 21900 }, { "epoch": 2.72, "learning_rate": 9.479397485372838e-06, "loss": 0.0861, "step": 21910 }, { "epoch": 2.72, "learning_rate": 9.479148512386406e-06, "loss": 0.0728, "step": 21920 }, { "epoch": 2.72, "learning_rate": 9.478899539399977e-06, "loss": 0.0606, "step": 21930 }, { "epoch": 2.72, "learning_rate": 9.478650566413545e-06, "loss": 0.0477, "step": 21940 }, { "epoch": 2.73, "learning_rate": 9.478401593427114e-06, "loss": 0.0502, "step": 21950 }, { "epoch": 2.73, "learning_rate": 9.478152620440682e-06, "loss": 0.0678, "step": 21960 }, { "epoch": 2.73, "learning_rate": 9.477903647454252e-06, "loss": 0.0538, "step": 21970 }, { "epoch": 2.73, "learning_rate": 9.477654674467821e-06, "loss": 0.0815, "step": 21980 }, { "epoch": 2.73, "learning_rate": 9.47740570148139e-06, "loss": 0.068, "step": 21990 }, { "epoch": 2.73, "learning_rate": 9.47715672849496e-06, "loss": 0.093, "step": 22000 }, { "epoch": 2.73, "learning_rate": 9.476907755508528e-06, "loss": 0.0719, "step": 22010 }, { "epoch": 2.73, "learning_rate": 9.476658782522097e-06, "loss": 0.0765, "step": 22020 }, { "epoch": 2.74, "learning_rate": 9.476409809535665e-06, "loss": 0.0628, "step": 22030 }, { "epoch": 2.74, "learning_rate": 9.476160836549235e-06, "loss": 0.0574, "step": 22040 }, { "epoch": 2.74, "learning_rate": 9.475911863562804e-06, "loss": 0.0603, "step": 22050 }, { "epoch": 2.74, "learning_rate": 9.475662890576374e-06, "loss": 0.0664, "step": 22060 }, { "epoch": 2.74, "learning_rate": 9.475413917589941e-06, "loss": 0.0365, "step": 22070 }, { "epoch": 2.74, "learning_rate": 9.475164944603511e-06, "loss": 0.0577, "step": 22080 }, { "epoch": 2.74, "learning_rate": 9.47491597161708e-06, "loss": 0.0526, "step": 22090 }, { "epoch": 2.74, "learning_rate": 9.47466699863065e-06, "loss": 0.0714, "step": 22100 }, { "epoch": 2.75, "learning_rate": 9.474418025644218e-06, "loss": 0.0743, "step": 22110 }, { "epoch": 2.75, "learning_rate": 9.474169052657789e-06, "loss": 0.0535, "step": 22120 }, { "epoch": 2.75, "learning_rate": 9.473920079671355e-06, "loss": 0.0904, "step": 22130 }, { "epoch": 2.75, "learning_rate": 9.473671106684926e-06, "loss": 0.0654, "step": 22140 }, { "epoch": 2.75, "learning_rate": 9.473422133698494e-06, "loss": 0.0627, "step": 22150 }, { "epoch": 2.75, "learning_rate": 9.473173160712064e-06, "loss": 0.0932, "step": 22160 }, { "epoch": 2.75, "learning_rate": 9.472924187725633e-06, "loss": 0.0465, "step": 22170 }, { "epoch": 2.75, "learning_rate": 9.472675214739201e-06, "loss": 0.0592, "step": 22180 }, { "epoch": 2.76, "learning_rate": 9.47242624175277e-06, "loss": 0.0392, "step": 22190 }, { "epoch": 2.76, "learning_rate": 9.47217726876634e-06, "loss": 0.0548, "step": 22200 }, { "epoch": 2.76, "learning_rate": 9.471928295779909e-06, "loss": 0.0686, "step": 22210 }, { "epoch": 2.76, "learning_rate": 9.471679322793477e-06, "loss": 0.0473, "step": 22220 }, { "epoch": 2.76, "learning_rate": 9.471430349807047e-06, "loss": 0.0903, "step": 22230 }, { "epoch": 2.76, "learning_rate": 9.471181376820616e-06, "loss": 0.0426, "step": 22240 }, { "epoch": 2.76, "learning_rate": 9.470932403834184e-06, "loss": 0.0523, "step": 22250 }, { "epoch": 2.76, "learning_rate": 9.470683430847753e-06, "loss": 0.0675, "step": 22260 }, { "epoch": 2.77, "learning_rate": 9.470434457861323e-06, "loss": 0.0621, "step": 22270 }, { "epoch": 2.77, "learning_rate": 9.470185484874892e-06, "loss": 0.0628, "step": 22280 }, { "epoch": 2.77, "learning_rate": 9.469936511888462e-06, "loss": 0.0555, "step": 22290 }, { "epoch": 2.77, "learning_rate": 9.46968753890203e-06, "loss": 0.053, "step": 22300 }, { "epoch": 2.77, "learning_rate": 9.469438565915599e-06, "loss": 0.0534, "step": 22310 }, { "epoch": 2.77, "learning_rate": 9.469189592929167e-06, "loss": 0.0589, "step": 22320 }, { "epoch": 2.77, "learning_rate": 9.468940619942738e-06, "loss": 0.0567, "step": 22330 }, { "epoch": 2.77, "learning_rate": 9.468691646956306e-06, "loss": 0.0607, "step": 22340 }, { "epoch": 2.78, "learning_rate": 9.468442673969875e-06, "loss": 0.0699, "step": 22350 }, { "epoch": 2.78, "learning_rate": 9.468193700983445e-06, "loss": 0.109, "step": 22360 }, { "epoch": 2.78, "learning_rate": 9.467944727997013e-06, "loss": 0.0396, "step": 22370 }, { "epoch": 2.78, "learning_rate": 9.467695755010582e-06, "loss": 0.0424, "step": 22380 }, { "epoch": 2.78, "learning_rate": 9.46744678202415e-06, "loss": 0.066, "step": 22390 }, { "epoch": 2.78, "learning_rate": 9.46719780903772e-06, "loss": 0.0556, "step": 22400 }, { "epoch": 2.78, "learning_rate": 9.46694883605129e-06, "loss": 0.0623, "step": 22410 }, { "epoch": 2.78, "learning_rate": 9.46669986306486e-06, "loss": 0.0669, "step": 22420 }, { "epoch": 2.79, "learning_rate": 9.466450890078426e-06, "loss": 0.0957, "step": 22430 }, { "epoch": 2.79, "learning_rate": 9.466201917091996e-06, "loss": 0.083, "step": 22440 }, { "epoch": 2.79, "learning_rate": 9.465952944105565e-06, "loss": 0.0616, "step": 22450 }, { "epoch": 2.79, "learning_rate": 9.465703971119135e-06, "loss": 0.0653, "step": 22460 }, { "epoch": 2.79, "learning_rate": 9.465454998132704e-06, "loss": 0.0821, "step": 22470 }, { "epoch": 2.79, "learning_rate": 9.465206025146272e-06, "loss": 0.0632, "step": 22480 }, { "epoch": 2.79, "learning_rate": 9.46495705215984e-06, "loss": 0.0768, "step": 22490 }, { "epoch": 2.79, "learning_rate": 9.464708079173411e-06, "loss": 0.0786, "step": 22500 }, { "epoch": 2.8, "learning_rate": 9.46445910618698e-06, "loss": 0.0667, "step": 22510 }, { "epoch": 2.8, "learning_rate": 9.464210133200548e-06, "loss": 0.0601, "step": 22520 }, { "epoch": 2.8, "learning_rate": 9.463961160214118e-06, "loss": 0.0636, "step": 22530 }, { "epoch": 2.8, "learning_rate": 9.463712187227687e-06, "loss": 0.0601, "step": 22540 }, { "epoch": 2.8, "learning_rate": 9.463463214241255e-06, "loss": 0.0609, "step": 22550 }, { "epoch": 2.8, "learning_rate": 9.463214241254824e-06, "loss": 0.0748, "step": 22560 }, { "epoch": 2.8, "learning_rate": 9.462965268268394e-06, "loss": 0.0503, "step": 22570 }, { "epoch": 2.8, "learning_rate": 9.462716295281962e-06, "loss": 0.0582, "step": 22580 }, { "epoch": 2.81, "learning_rate": 9.462467322295533e-06, "loss": 0.0767, "step": 22590 }, { "epoch": 2.81, "learning_rate": 9.4622183493091e-06, "loss": 0.0823, "step": 22600 }, { "epoch": 2.81, "learning_rate": 9.46196937632267e-06, "loss": 0.1098, "step": 22610 }, { "epoch": 2.81, "learning_rate": 9.461720403336238e-06, "loss": 0.0741, "step": 22620 }, { "epoch": 2.81, "learning_rate": 9.461471430349808e-06, "loss": 0.0383, "step": 22630 }, { "epoch": 2.81, "learning_rate": 9.461222457363377e-06, "loss": 0.0942, "step": 22640 }, { "epoch": 2.81, "learning_rate": 9.460973484376947e-06, "loss": 0.056, "step": 22650 }, { "epoch": 2.81, "learning_rate": 9.460724511390514e-06, "loss": 0.0593, "step": 22660 }, { "epoch": 2.82, "learning_rate": 9.460475538404084e-06, "loss": 0.1037, "step": 22670 }, { "epoch": 2.82, "learning_rate": 9.460226565417653e-06, "loss": 0.0609, "step": 22680 }, { "epoch": 2.82, "learning_rate": 9.459977592431223e-06, "loss": 0.0561, "step": 22690 }, { "epoch": 2.82, "learning_rate": 9.459728619444791e-06, "loss": 0.051, "step": 22700 }, { "epoch": 2.82, "learning_rate": 9.45947964645836e-06, "loss": 0.0805, "step": 22710 }, { "epoch": 2.82, "learning_rate": 9.459230673471928e-06, "loss": 0.0764, "step": 22720 }, { "epoch": 2.82, "learning_rate": 9.458981700485499e-06, "loss": 0.0414, "step": 22730 }, { "epoch": 2.82, "learning_rate": 9.458732727499067e-06, "loss": 0.0799, "step": 22740 }, { "epoch": 2.82, "learning_rate": 9.458483754512636e-06, "loss": 0.0607, "step": 22750 }, { "epoch": 2.83, "learning_rate": 9.458234781526206e-06, "loss": 0.0549, "step": 22760 }, { "epoch": 2.83, "learning_rate": 9.457985808539774e-06, "loss": 0.0468, "step": 22770 }, { "epoch": 2.83, "learning_rate": 9.457736835553343e-06, "loss": 0.0661, "step": 22780 }, { "epoch": 2.83, "learning_rate": 9.457487862566911e-06, "loss": 0.0827, "step": 22790 }, { "epoch": 2.83, "learning_rate": 9.457238889580482e-06, "loss": 0.0642, "step": 22800 }, { "epoch": 2.83, "learning_rate": 9.45698991659405e-06, "loss": 0.077, "step": 22810 }, { "epoch": 2.83, "learning_rate": 9.45674094360762e-06, "loss": 0.0686, "step": 22820 }, { "epoch": 2.83, "learning_rate": 9.456491970621189e-06, "loss": 0.0631, "step": 22830 }, { "epoch": 2.84, "learning_rate": 9.456242997634757e-06, "loss": 0.0492, "step": 22840 }, { "epoch": 2.84, "learning_rate": 9.455994024648326e-06, "loss": 0.0694, "step": 22850 }, { "epoch": 2.84, "learning_rate": 9.455745051661896e-06, "loss": 0.0935, "step": 22860 }, { "epoch": 2.84, "learning_rate": 9.455496078675465e-06, "loss": 0.0828, "step": 22870 }, { "epoch": 2.84, "learning_rate": 9.455247105689033e-06, "loss": 0.0731, "step": 22880 }, { "epoch": 2.84, "learning_rate": 9.454998132702603e-06, "loss": 0.0591, "step": 22890 }, { "epoch": 2.84, "learning_rate": 9.454749159716172e-06, "loss": 0.0473, "step": 22900 }, { "epoch": 2.84, "learning_rate": 9.45450018672974e-06, "loss": 0.0687, "step": 22910 }, { "epoch": 2.85, "learning_rate": 9.454251213743309e-06, "loss": 0.0873, "step": 22920 }, { "epoch": 2.85, "learning_rate": 9.454002240756879e-06, "loss": 0.0671, "step": 22930 }, { "epoch": 2.85, "learning_rate": 9.453753267770448e-06, "loss": 0.0553, "step": 22940 }, { "epoch": 2.85, "learning_rate": 9.453504294784018e-06, "loss": 0.0603, "step": 22950 }, { "epoch": 2.85, "learning_rate": 9.453255321797585e-06, "loss": 0.1193, "step": 22960 }, { "epoch": 2.85, "learning_rate": 9.453006348811155e-06, "loss": 0.0777, "step": 22970 }, { "epoch": 2.85, "learning_rate": 9.452757375824723e-06, "loss": 0.0407, "step": 22980 }, { "epoch": 2.85, "learning_rate": 9.452508402838294e-06, "loss": 0.038, "step": 22990 }, { "epoch": 2.86, "learning_rate": 9.452259429851862e-06, "loss": 0.0697, "step": 23000 }, { "epoch": 2.86, "learning_rate": 9.45201045686543e-06, "loss": 0.067, "step": 23010 }, { "epoch": 2.86, "learning_rate": 9.451761483878999e-06, "loss": 0.0474, "step": 23020 }, { "epoch": 2.86, "learning_rate": 9.45151251089257e-06, "loss": 0.0621, "step": 23030 }, { "epoch": 2.86, "learning_rate": 9.451263537906138e-06, "loss": 0.0838, "step": 23040 }, { "epoch": 2.86, "learning_rate": 9.451014564919706e-06, "loss": 0.0468, "step": 23050 }, { "epoch": 2.86, "learning_rate": 9.450765591933277e-06, "loss": 0.07, "step": 23060 }, { "epoch": 2.86, "learning_rate": 9.450516618946845e-06, "loss": 0.064, "step": 23070 }, { "epoch": 2.87, "learning_rate": 9.450267645960414e-06, "loss": 0.0766, "step": 23080 }, { "epoch": 2.87, "learning_rate": 9.450018672973982e-06, "loss": 0.0731, "step": 23090 }, { "epoch": 2.87, "learning_rate": 9.449769699987552e-06, "loss": 0.0483, "step": 23100 }, { "epoch": 2.87, "learning_rate": 9.449520727001121e-06, "loss": 0.064, "step": 23110 }, { "epoch": 2.87, "learning_rate": 9.449271754014691e-06, "loss": 0.0595, "step": 23120 }, { "epoch": 2.87, "learning_rate": 9.44902278102826e-06, "loss": 0.0655, "step": 23130 }, { "epoch": 2.87, "learning_rate": 9.448773808041828e-06, "loss": 0.0952, "step": 23140 }, { "epoch": 2.87, "learning_rate": 9.448524835055397e-06, "loss": 0.0753, "step": 23150 }, { "epoch": 2.88, "learning_rate": 9.448275862068967e-06, "loss": 0.061, "step": 23160 }, { "epoch": 2.88, "learning_rate": 9.448026889082535e-06, "loss": 0.0582, "step": 23170 }, { "epoch": 2.88, "learning_rate": 9.447777916096106e-06, "loss": 0.0566, "step": 23180 }, { "epoch": 2.88, "learning_rate": 9.447528943109672e-06, "loss": 0.0588, "step": 23190 }, { "epoch": 2.88, "learning_rate": 9.447279970123243e-06, "loss": 0.0673, "step": 23200 }, { "epoch": 2.88, "learning_rate": 9.447030997136811e-06, "loss": 0.0689, "step": 23210 }, { "epoch": 2.88, "learning_rate": 9.446782024150381e-06, "loss": 0.0859, "step": 23220 }, { "epoch": 2.88, "learning_rate": 9.44653305116395e-06, "loss": 0.0776, "step": 23230 }, { "epoch": 2.89, "learning_rate": 9.446284078177518e-06, "loss": 0.0593, "step": 23240 }, { "epoch": 2.89, "learning_rate": 9.446035105191087e-06, "loss": 0.0618, "step": 23250 }, { "epoch": 2.89, "learning_rate": 9.445786132204657e-06, "loss": 0.0686, "step": 23260 }, { "epoch": 2.89, "learning_rate": 9.445537159218226e-06, "loss": 0.0608, "step": 23270 }, { "epoch": 2.89, "learning_rate": 9.445288186231794e-06, "loss": 0.0599, "step": 23280 }, { "epoch": 2.89, "learning_rate": 9.445039213245364e-06, "loss": 0.0798, "step": 23290 }, { "epoch": 2.89, "learning_rate": 9.444790240258933e-06, "loss": 0.0689, "step": 23300 }, { "epoch": 2.89, "learning_rate": 9.444541267272501e-06, "loss": 0.0978, "step": 23310 }, { "epoch": 2.9, "learning_rate": 9.44429229428607e-06, "loss": 0.0873, "step": 23320 }, { "epoch": 2.9, "learning_rate": 9.44404332129964e-06, "loss": 0.0699, "step": 23330 }, { "epoch": 2.9, "learning_rate": 9.443794348313209e-06, "loss": 0.0536, "step": 23340 }, { "epoch": 2.9, "learning_rate": 9.443545375326779e-06, "loss": 0.0594, "step": 23350 }, { "epoch": 2.9, "learning_rate": 9.443296402340347e-06, "loss": 0.0451, "step": 23360 }, { "epoch": 2.9, "learning_rate": 9.443047429353916e-06, "loss": 0.0497, "step": 23370 }, { "epoch": 2.9, "learning_rate": 9.442798456367484e-06, "loss": 0.088, "step": 23380 }, { "epoch": 2.9, "learning_rate": 9.442549483381055e-06, "loss": 0.0596, "step": 23390 }, { "epoch": 2.91, "learning_rate": 9.442300510394623e-06, "loss": 0.048, "step": 23400 }, { "epoch": 2.91, "learning_rate": 9.442051537408192e-06, "loss": 0.0777, "step": 23410 }, { "epoch": 2.91, "learning_rate": 9.441802564421762e-06, "loss": 0.0617, "step": 23420 }, { "epoch": 2.91, "learning_rate": 9.44155359143533e-06, "loss": 0.0742, "step": 23430 }, { "epoch": 2.91, "learning_rate": 9.441304618448899e-06, "loss": 0.0802, "step": 23440 }, { "epoch": 2.91, "learning_rate": 9.441055645462467e-06, "loss": 0.0576, "step": 23450 }, { "epoch": 2.91, "learning_rate": 9.440806672476038e-06, "loss": 0.0902, "step": 23460 }, { "epoch": 2.91, "learning_rate": 9.440557699489606e-06, "loss": 0.0691, "step": 23470 }, { "epoch": 2.92, "learning_rate": 9.440308726503176e-06, "loss": 0.0855, "step": 23480 }, { "epoch": 2.92, "learning_rate": 9.440059753516743e-06, "loss": 0.0643, "step": 23490 }, { "epoch": 2.92, "learning_rate": 9.439810780530313e-06, "loss": 0.0658, "step": 23500 }, { "epoch": 2.92, "learning_rate": 9.439561807543882e-06, "loss": 0.0607, "step": 23510 }, { "epoch": 2.92, "learning_rate": 9.439312834557452e-06, "loss": 0.0551, "step": 23520 }, { "epoch": 2.92, "learning_rate": 9.43906386157102e-06, "loss": 0.0595, "step": 23530 }, { "epoch": 2.92, "learning_rate": 9.438814888584589e-06, "loss": 0.0682, "step": 23540 }, { "epoch": 2.92, "learning_rate": 9.438565915598158e-06, "loss": 0.0602, "step": 23550 }, { "epoch": 2.93, "learning_rate": 9.438316942611728e-06, "loss": 0.0528, "step": 23560 }, { "epoch": 2.93, "learning_rate": 9.438067969625296e-06, "loss": 0.0707, "step": 23570 }, { "epoch": 2.93, "learning_rate": 9.437818996638865e-06, "loss": 0.0443, "step": 23580 }, { "epoch": 2.93, "learning_rate": 9.437570023652435e-06, "loss": 0.0618, "step": 23590 }, { "epoch": 2.93, "learning_rate": 9.437321050666004e-06, "loss": 0.0537, "step": 23600 }, { "epoch": 2.93, "learning_rate": 9.437072077679572e-06, "loss": 0.0768, "step": 23610 }, { "epoch": 2.93, "learning_rate": 9.43682310469314e-06, "loss": 0.0799, "step": 23620 }, { "epoch": 2.93, "learning_rate": 9.43657413170671e-06, "loss": 0.0538, "step": 23630 }, { "epoch": 2.94, "learning_rate": 9.43632515872028e-06, "loss": 0.1028, "step": 23640 }, { "epoch": 2.94, "learning_rate": 9.43607618573385e-06, "loss": 0.0456, "step": 23650 }, { "epoch": 2.94, "learning_rate": 9.435827212747418e-06, "loss": 0.0597, "step": 23660 }, { "epoch": 2.94, "learning_rate": 9.435578239760987e-06, "loss": 0.0805, "step": 23670 }, { "epoch": 2.94, "learning_rate": 9.435329266774555e-06, "loss": 0.066, "step": 23680 }, { "epoch": 2.94, "learning_rate": 9.435080293788125e-06, "loss": 0.0615, "step": 23690 }, { "epoch": 2.94, "learning_rate": 9.434831320801694e-06, "loss": 0.0891, "step": 23700 }, { "epoch": 2.94, "learning_rate": 9.434582347815264e-06, "loss": 0.0571, "step": 23710 }, { "epoch": 2.95, "learning_rate": 9.434333374828833e-06, "loss": 0.0559, "step": 23720 }, { "epoch": 2.95, "learning_rate": 9.434084401842401e-06, "loss": 0.0438, "step": 23730 }, { "epoch": 2.95, "learning_rate": 9.43383542885597e-06, "loss": 0.0491, "step": 23740 }, { "epoch": 2.95, "learning_rate": 9.43358645586954e-06, "loss": 0.0492, "step": 23750 }, { "epoch": 2.95, "learning_rate": 9.433337482883108e-06, "loss": 0.0507, "step": 23760 }, { "epoch": 2.95, "learning_rate": 9.433088509896677e-06, "loss": 0.0763, "step": 23770 }, { "epoch": 2.95, "learning_rate": 9.432839536910247e-06, "loss": 0.0606, "step": 23780 }, { "epoch": 2.95, "learning_rate": 9.432590563923816e-06, "loss": 0.0704, "step": 23790 }, { "epoch": 2.96, "learning_rate": 9.432341590937384e-06, "loss": 0.0414, "step": 23800 }, { "epoch": 2.96, "learning_rate": 9.432092617950953e-06, "loss": 0.0648, "step": 23810 }, { "epoch": 2.96, "learning_rate": 9.431843644964523e-06, "loss": 0.0574, "step": 23820 }, { "epoch": 2.96, "learning_rate": 9.431594671978091e-06, "loss": 0.0306, "step": 23830 }, { "epoch": 2.96, "learning_rate": 9.43134569899166e-06, "loss": 0.0522, "step": 23840 }, { "epoch": 2.96, "learning_rate": 9.431096726005228e-06, "loss": 0.0683, "step": 23850 }, { "epoch": 2.96, "learning_rate": 9.430847753018799e-06, "loss": 0.0747, "step": 23860 }, { "epoch": 2.96, "learning_rate": 9.430598780032367e-06, "loss": 0.0658, "step": 23870 }, { "epoch": 2.97, "learning_rate": 9.430349807045937e-06, "loss": 0.0687, "step": 23880 }, { "epoch": 2.97, "learning_rate": 9.430100834059506e-06, "loss": 0.069, "step": 23890 }, { "epoch": 2.97, "learning_rate": 9.429851861073074e-06, "loss": 0.0431, "step": 23900 }, { "epoch": 2.97, "learning_rate": 9.429602888086643e-06, "loss": 0.0812, "step": 23910 }, { "epoch": 2.97, "learning_rate": 9.429353915100213e-06, "loss": 0.061, "step": 23920 }, { "epoch": 2.97, "learning_rate": 9.429104942113782e-06, "loss": 0.0585, "step": 23930 }, { "epoch": 2.97, "learning_rate": 9.42885596912735e-06, "loss": 0.0526, "step": 23940 }, { "epoch": 2.97, "learning_rate": 9.42860699614092e-06, "loss": 0.0579, "step": 23950 }, { "epoch": 2.98, "learning_rate": 9.428358023154489e-06, "loss": 0.0646, "step": 23960 }, { "epoch": 2.98, "learning_rate": 9.428109050168057e-06, "loss": 0.0401, "step": 23970 }, { "epoch": 2.98, "learning_rate": 9.427860077181626e-06, "loss": 0.0648, "step": 23980 }, { "epoch": 2.98, "learning_rate": 9.427611104195196e-06, "loss": 0.0611, "step": 23990 }, { "epoch": 2.98, "learning_rate": 9.427362131208765e-06, "loss": 0.0461, "step": 24000 }, { "epoch": 2.98, "learning_rate": 9.427113158222335e-06, "loss": 0.061, "step": 24010 }, { "epoch": 2.98, "learning_rate": 9.426864185235902e-06, "loss": 0.0724, "step": 24020 }, { "epoch": 2.98, "learning_rate": 9.426615212249472e-06, "loss": 0.059, "step": 24030 }, { "epoch": 2.99, "learning_rate": 9.42636623926304e-06, "loss": 0.0573, "step": 24040 }, { "epoch": 2.99, "learning_rate": 9.42611726627661e-06, "loss": 0.062, "step": 24050 }, { "epoch": 2.99, "learning_rate": 9.425868293290179e-06, "loss": 0.0502, "step": 24060 }, { "epoch": 2.99, "learning_rate": 9.425619320303748e-06, "loss": 0.0913, "step": 24070 }, { "epoch": 2.99, "learning_rate": 9.425370347317316e-06, "loss": 0.0713, "step": 24080 }, { "epoch": 2.99, "learning_rate": 9.425121374330886e-06, "loss": 0.0607, "step": 24090 }, { "epoch": 2.99, "learning_rate": 9.424872401344455e-06, "loss": 0.0565, "step": 24100 }, { "epoch": 2.99, "learning_rate": 9.424623428358023e-06, "loss": 0.0756, "step": 24110 }, { "epoch": 3.0, "learning_rate": 9.424374455371593e-06, "loss": 0.0594, "step": 24120 }, { "epoch": 3.0, "learning_rate": 9.424125482385162e-06, "loss": 0.0773, "step": 24130 }, { "epoch": 3.0, "learning_rate": 9.42387650939873e-06, "loss": 0.0627, "step": 24140 }, { "epoch": 3.0, "learning_rate": 9.423627536412299e-06, "loss": 0.0457, "step": 24150 }, { "epoch": 3.0, "learning_rate": 9.42337856342587e-06, "loss": 0.0566, "step": 24160 }, { "epoch": 3.0, "learning_rate": 9.423129590439438e-06, "loss": 0.078, "step": 24170 }, { "epoch": 3.0, "learning_rate": 9.422880617453008e-06, "loss": 0.0536, "step": 24180 }, { "epoch": 3.0, "learning_rate": 9.422631644466576e-06, "loss": 0.0838, "step": 24190 }, { "epoch": 3.01, "learning_rate": 9.422382671480145e-06, "loss": 0.0585, "step": 24200 }, { "epoch": 3.01, "learning_rate": 9.422133698493714e-06, "loss": 0.0549, "step": 24210 }, { "epoch": 3.01, "learning_rate": 9.421884725507284e-06, "loss": 0.0997, "step": 24220 }, { "epoch": 3.01, "learning_rate": 9.421635752520852e-06, "loss": 0.0676, "step": 24230 }, { "epoch": 3.01, "learning_rate": 9.421386779534422e-06, "loss": 0.0769, "step": 24240 }, { "epoch": 3.01, "learning_rate": 9.421137806547991e-06, "loss": 0.0502, "step": 24250 }, { "epoch": 3.01, "learning_rate": 9.42088883356156e-06, "loss": 0.0675, "step": 24260 }, { "epoch": 3.01, "learning_rate": 9.420639860575128e-06, "loss": 0.0657, "step": 24270 }, { "epoch": 3.02, "learning_rate": 9.420390887588698e-06, "loss": 0.0609, "step": 24280 }, { "epoch": 3.02, "learning_rate": 9.420141914602267e-06, "loss": 0.0535, "step": 24290 }, { "epoch": 3.02, "learning_rate": 9.419892941615835e-06, "loss": 0.0577, "step": 24300 }, { "epoch": 3.02, "learning_rate": 9.419643968629405e-06, "loss": 0.0681, "step": 24310 }, { "epoch": 3.02, "learning_rate": 9.419394995642974e-06, "loss": 0.0461, "step": 24320 }, { "epoch": 3.02, "learning_rate": 9.419146022656542e-06, "loss": 0.0548, "step": 24330 }, { "epoch": 3.02, "learning_rate": 9.418897049670111e-06, "loss": 0.0633, "step": 24340 }, { "epoch": 3.02, "learning_rate": 9.418648076683681e-06, "loss": 0.0644, "step": 24350 }, { "epoch": 3.02, "learning_rate": 9.41839910369725e-06, "loss": 0.0544, "step": 24360 }, { "epoch": 3.03, "learning_rate": 9.41815013071082e-06, "loss": 0.0638, "step": 24370 }, { "epoch": 3.03, "learning_rate": 9.417901157724387e-06, "loss": 0.061, "step": 24380 }, { "epoch": 3.03, "learning_rate": 9.417652184737957e-06, "loss": 0.0729, "step": 24390 }, { "epoch": 3.03, "learning_rate": 9.417403211751525e-06, "loss": 0.0595, "step": 24400 }, { "epoch": 3.03, "learning_rate": 9.417154238765096e-06, "loss": 0.0574, "step": 24410 }, { "epoch": 3.03, "learning_rate": 9.416905265778664e-06, "loss": 0.0854, "step": 24420 }, { "epoch": 3.03, "learning_rate": 9.416656292792233e-06, "loss": 0.0565, "step": 24430 }, { "epoch": 3.03, "learning_rate": 9.416407319805801e-06, "loss": 0.0647, "step": 24440 }, { "epoch": 3.04, "learning_rate": 9.416158346819371e-06, "loss": 0.069, "step": 24450 }, { "epoch": 3.04, "learning_rate": 9.41590937383294e-06, "loss": 0.0636, "step": 24460 }, { "epoch": 3.04, "learning_rate": 9.415660400846508e-06, "loss": 0.0827, "step": 24470 }, { "epoch": 3.04, "learning_rate": 9.415411427860079e-06, "loss": 0.0495, "step": 24480 }, { "epoch": 3.04, "learning_rate": 9.415162454873647e-06, "loss": 0.0523, "step": 24490 }, { "epoch": 3.04, "learning_rate": 9.414913481887216e-06, "loss": 0.0453, "step": 24500 }, { "epoch": 3.04, "learning_rate": 9.414664508900784e-06, "loss": 0.0679, "step": 24510 }, { "epoch": 3.04, "learning_rate": 9.414415535914354e-06, "loss": 0.0581, "step": 24520 }, { "epoch": 3.05, "learning_rate": 9.414166562927923e-06, "loss": 0.0501, "step": 24530 }, { "epoch": 3.05, "learning_rate": 9.413917589941493e-06, "loss": 0.0541, "step": 24540 }, { "epoch": 3.05, "learning_rate": 9.41366861695506e-06, "loss": 0.0491, "step": 24550 }, { "epoch": 3.05, "learning_rate": 9.41341964396863e-06, "loss": 0.068, "step": 24560 }, { "epoch": 3.05, "learning_rate": 9.413170670982199e-06, "loss": 0.0496, "step": 24570 }, { "epoch": 3.05, "learning_rate": 9.412921697995769e-06, "loss": 0.048, "step": 24580 }, { "epoch": 3.05, "learning_rate": 9.412672725009337e-06, "loss": 0.1, "step": 24590 }, { "epoch": 3.05, "learning_rate": 9.412423752022906e-06, "loss": 0.0564, "step": 24600 }, { "epoch": 3.06, "learning_rate": 9.412174779036474e-06, "loss": 0.0729, "step": 24610 }, { "epoch": 3.06, "learning_rate": 9.411925806050045e-06, "loss": 0.0553, "step": 24620 }, { "epoch": 3.06, "learning_rate": 9.411676833063613e-06, "loss": 0.0612, "step": 24630 }, { "epoch": 3.06, "learning_rate": 9.411427860077182e-06, "loss": 0.0742, "step": 24640 }, { "epoch": 3.06, "learning_rate": 9.411178887090752e-06, "loss": 0.0664, "step": 24650 }, { "epoch": 3.06, "learning_rate": 9.41092991410432e-06, "loss": 0.0692, "step": 24660 }, { "epoch": 3.06, "learning_rate": 9.410680941117889e-06, "loss": 0.0619, "step": 24670 }, { "epoch": 3.06, "learning_rate": 9.410431968131457e-06, "loss": 0.0713, "step": 24680 }, { "epoch": 3.07, "learning_rate": 9.410182995145028e-06, "loss": 0.0483, "step": 24690 }, { "epoch": 3.07, "learning_rate": 9.409934022158596e-06, "loss": 0.0613, "step": 24700 }, { "epoch": 3.07, "learning_rate": 9.409685049172166e-06, "loss": 0.0445, "step": 24710 }, { "epoch": 3.07, "learning_rate": 9.409436076185735e-06, "loss": 0.0371, "step": 24720 }, { "epoch": 3.07, "learning_rate": 9.409187103199303e-06, "loss": 0.0532, "step": 24730 }, { "epoch": 3.07, "learning_rate": 9.408938130212872e-06, "loss": 0.0404, "step": 24740 }, { "epoch": 3.07, "learning_rate": 9.408689157226442e-06, "loss": 0.0732, "step": 24750 }, { "epoch": 3.07, "learning_rate": 9.40844018424001e-06, "loss": 0.0541, "step": 24760 }, { "epoch": 3.08, "learning_rate": 9.408191211253581e-06, "loss": 0.0804, "step": 24770 }, { "epoch": 3.08, "learning_rate": 9.40794223826715e-06, "loss": 0.0551, "step": 24780 }, { "epoch": 3.08, "learning_rate": 9.407693265280718e-06, "loss": 0.0678, "step": 24790 }, { "epoch": 3.08, "learning_rate": 9.407444292294286e-06, "loss": 0.0523, "step": 24800 }, { "epoch": 3.08, "learning_rate": 9.407195319307857e-06, "loss": 0.0489, "step": 24810 }, { "epoch": 3.08, "learning_rate": 9.406946346321425e-06, "loss": 0.0477, "step": 24820 }, { "epoch": 3.08, "learning_rate": 9.406697373334994e-06, "loss": 0.0606, "step": 24830 }, { "epoch": 3.08, "learning_rate": 9.406448400348564e-06, "loss": 0.0621, "step": 24840 }, { "epoch": 3.09, "learning_rate": 9.40619942736213e-06, "loss": 0.0532, "step": 24850 }, { "epoch": 3.09, "learning_rate": 9.405950454375701e-06, "loss": 0.0573, "step": 24860 }, { "epoch": 3.09, "learning_rate": 9.40570148138927e-06, "loss": 0.0722, "step": 24870 }, { "epoch": 3.09, "learning_rate": 9.40545250840284e-06, "loss": 0.0791, "step": 24880 }, { "epoch": 3.09, "learning_rate": 9.405203535416408e-06, "loss": 0.0602, "step": 24890 }, { "epoch": 3.09, "learning_rate": 9.404954562429978e-06, "loss": 0.0392, "step": 24900 }, { "epoch": 3.09, "learning_rate": 9.404705589443545e-06, "loss": 0.0454, "step": 24910 }, { "epoch": 3.09, "learning_rate": 9.404456616457115e-06, "loss": 0.0886, "step": 24920 }, { "epoch": 3.1, "learning_rate": 9.404207643470684e-06, "loss": 0.0437, "step": 24930 }, { "epoch": 3.1, "learning_rate": 9.403958670484254e-06, "loss": 0.0576, "step": 24940 }, { "epoch": 3.1, "learning_rate": 9.403709697497823e-06, "loss": 0.0596, "step": 24950 }, { "epoch": 3.1, "learning_rate": 9.403460724511391e-06, "loss": 0.0555, "step": 24960 }, { "epoch": 3.1, "learning_rate": 9.40321175152496e-06, "loss": 0.0669, "step": 24970 }, { "epoch": 3.1, "learning_rate": 9.40296277853853e-06, "loss": 0.0625, "step": 24980 }, { "epoch": 3.1, "learning_rate": 9.402713805552098e-06, "loss": 0.0755, "step": 24990 }, { "epoch": 3.1, "learning_rate": 9.402464832565667e-06, "loss": 0.0487, "step": 25000 }, { "epoch": 3.1, "eval_bleu": 89.1639, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7598, "eval_has_error_f1": 0.6752, "eval_loss": 0.054084647446870804, "eval_runtime": 1372.2556, "eval_samples_per_second": 2.913, "eval_steps_per_second": 0.729, "step": 25000 }, { "epoch": 3.11, "learning_rate": 9.402215859579237e-06, "loss": 0.0517, "step": 25010 }, { "epoch": 3.11, "learning_rate": 9.401966886592806e-06, "loss": 0.0583, "step": 25020 }, { "epoch": 3.11, "learning_rate": 9.401717913606374e-06, "loss": 0.0826, "step": 25030 }, { "epoch": 3.11, "learning_rate": 9.401468940619943e-06, "loss": 0.0703, "step": 25040 }, { "epoch": 3.11, "learning_rate": 9.401219967633513e-06, "loss": 0.0477, "step": 25050 }, { "epoch": 3.11, "learning_rate": 9.400970994647081e-06, "loss": 0.0552, "step": 25060 }, { "epoch": 3.11, "learning_rate": 9.400722021660652e-06, "loss": 0.0494, "step": 25070 }, { "epoch": 3.11, "learning_rate": 9.40047304867422e-06, "loss": 0.0791, "step": 25080 }, { "epoch": 3.12, "learning_rate": 9.400224075687789e-06, "loss": 0.0609, "step": 25090 }, { "epoch": 3.12, "learning_rate": 9.399975102701357e-06, "loss": 0.065, "step": 25100 }, { "epoch": 3.12, "learning_rate": 9.399726129714927e-06, "loss": 0.0612, "step": 25110 }, { "epoch": 3.12, "learning_rate": 9.399477156728496e-06, "loss": 0.0676, "step": 25120 }, { "epoch": 3.12, "learning_rate": 9.399228183742064e-06, "loss": 0.0686, "step": 25130 }, { "epoch": 3.12, "learning_rate": 9.398979210755633e-06, "loss": 0.0644, "step": 25140 }, { "epoch": 3.12, "learning_rate": 9.398730237769203e-06, "loss": 0.0655, "step": 25150 }, { "epoch": 3.12, "learning_rate": 9.398481264782772e-06, "loss": 0.0723, "step": 25160 }, { "epoch": 3.13, "learning_rate": 9.39823229179634e-06, "loss": 0.0657, "step": 25170 }, { "epoch": 3.13, "learning_rate": 9.39798331880991e-06, "loss": 0.0836, "step": 25180 }, { "epoch": 3.13, "learning_rate": 9.397734345823479e-06, "loss": 0.0586, "step": 25190 }, { "epoch": 3.13, "learning_rate": 9.397485372837047e-06, "loss": 0.0596, "step": 25200 }, { "epoch": 3.13, "learning_rate": 9.397236399850616e-06, "loss": 0.0593, "step": 25210 }, { "epoch": 3.13, "learning_rate": 9.396987426864186e-06, "loss": 0.0696, "step": 25220 }, { "epoch": 3.13, "learning_rate": 9.396738453877755e-06, "loss": 0.0681, "step": 25230 }, { "epoch": 3.13, "learning_rate": 9.396489480891325e-06, "loss": 0.0632, "step": 25240 }, { "epoch": 3.14, "learning_rate": 9.396240507904893e-06, "loss": 0.0591, "step": 25250 }, { "epoch": 3.14, "learning_rate": 9.395991534918462e-06, "loss": 0.0306, "step": 25260 }, { "epoch": 3.14, "learning_rate": 9.39574256193203e-06, "loss": 0.0502, "step": 25270 }, { "epoch": 3.14, "learning_rate": 9.3954935889456e-06, "loss": 0.0748, "step": 25280 }, { "epoch": 3.14, "learning_rate": 9.395244615959169e-06, "loss": 0.0687, "step": 25290 }, { "epoch": 3.14, "learning_rate": 9.394995642972738e-06, "loss": 0.0475, "step": 25300 }, { "epoch": 3.14, "learning_rate": 9.394746669986308e-06, "loss": 0.0585, "step": 25310 }, { "epoch": 3.14, "learning_rate": 9.394497696999876e-06, "loss": 0.0652, "step": 25320 }, { "epoch": 3.15, "learning_rate": 9.394248724013445e-06, "loss": 0.079, "step": 25330 }, { "epoch": 3.15, "learning_rate": 9.393999751027013e-06, "loss": 0.056, "step": 25340 }, { "epoch": 3.15, "learning_rate": 9.393750778040584e-06, "loss": 0.0537, "step": 25350 }, { "epoch": 3.15, "learning_rate": 9.393501805054152e-06, "loss": 0.0762, "step": 25360 }, { "epoch": 3.15, "learning_rate": 9.393252832067722e-06, "loss": 0.0716, "step": 25370 }, { "epoch": 3.15, "learning_rate": 9.393003859081289e-06, "loss": 0.0835, "step": 25380 }, { "epoch": 3.15, "learning_rate": 9.39275488609486e-06, "loss": 0.0514, "step": 25390 }, { "epoch": 3.15, "learning_rate": 9.392505913108428e-06, "loss": 0.0526, "step": 25400 }, { "epoch": 3.16, "learning_rate": 9.392256940121998e-06, "loss": 0.0673, "step": 25410 }, { "epoch": 3.16, "learning_rate": 9.392007967135567e-06, "loss": 0.0744, "step": 25420 }, { "epoch": 3.16, "learning_rate": 9.391758994149137e-06, "loss": 0.0819, "step": 25430 }, { "epoch": 3.16, "learning_rate": 9.391510021162704e-06, "loss": 0.1093, "step": 25440 }, { "epoch": 3.16, "learning_rate": 9.391261048176274e-06, "loss": 0.0667, "step": 25450 }, { "epoch": 3.16, "learning_rate": 9.391012075189842e-06, "loss": 0.0489, "step": 25460 }, { "epoch": 3.16, "learning_rate": 9.390763102203413e-06, "loss": 0.0871, "step": 25470 }, { "epoch": 3.16, "learning_rate": 9.390514129216981e-06, "loss": 0.043, "step": 25480 }, { "epoch": 3.17, "learning_rate": 9.39026515623055e-06, "loss": 0.0482, "step": 25490 }, { "epoch": 3.17, "learning_rate": 9.390016183244118e-06, "loss": 0.0509, "step": 25500 }, { "epoch": 3.17, "learning_rate": 9.389767210257688e-06, "loss": 0.0663, "step": 25510 }, { "epoch": 3.17, "learning_rate": 9.389518237271257e-06, "loss": 0.051, "step": 25520 }, { "epoch": 3.17, "learning_rate": 9.389269264284825e-06, "loss": 0.055, "step": 25530 }, { "epoch": 3.17, "learning_rate": 9.389020291298396e-06, "loss": 0.0629, "step": 25540 }, { "epoch": 3.17, "learning_rate": 9.388771318311964e-06, "loss": 0.0908, "step": 25550 }, { "epoch": 3.17, "learning_rate": 9.388522345325533e-06, "loss": 0.0612, "step": 25560 }, { "epoch": 3.18, "learning_rate": 9.388273372339101e-06, "loss": 0.0872, "step": 25570 }, { "epoch": 3.18, "learning_rate": 9.388024399352671e-06, "loss": 0.0554, "step": 25580 }, { "epoch": 3.18, "learning_rate": 9.38777542636624e-06, "loss": 0.0566, "step": 25590 }, { "epoch": 3.18, "learning_rate": 9.38752645337981e-06, "loss": 0.0553, "step": 25600 }, { "epoch": 3.18, "learning_rate": 9.387277480393379e-06, "loss": 0.0727, "step": 25610 }, { "epoch": 3.18, "learning_rate": 9.387028507406947e-06, "loss": 0.053, "step": 25620 }, { "epoch": 3.18, "learning_rate": 9.386779534420516e-06, "loss": 0.0552, "step": 25630 }, { "epoch": 3.18, "learning_rate": 9.386530561434086e-06, "loss": 0.0714, "step": 25640 }, { "epoch": 3.19, "learning_rate": 9.386281588447654e-06, "loss": 0.0573, "step": 25650 }, { "epoch": 3.19, "learning_rate": 9.386032615461223e-06, "loss": 0.0458, "step": 25660 }, { "epoch": 3.19, "learning_rate": 9.385783642474793e-06, "loss": 0.066, "step": 25670 }, { "epoch": 3.19, "learning_rate": 9.385534669488362e-06, "loss": 0.0884, "step": 25680 }, { "epoch": 3.19, "learning_rate": 9.38528569650193e-06, "loss": 0.0317, "step": 25690 }, { "epoch": 3.19, "learning_rate": 9.385036723515499e-06, "loss": 0.0477, "step": 25700 }, { "epoch": 3.19, "learning_rate": 9.384787750529069e-06, "loss": 0.0533, "step": 25710 }, { "epoch": 3.19, "learning_rate": 9.384538777542637e-06, "loss": 0.0433, "step": 25720 }, { "epoch": 3.2, "learning_rate": 9.384289804556208e-06, "loss": 0.0588, "step": 25730 }, { "epoch": 3.2, "learning_rate": 9.384040831569774e-06, "loss": 0.0421, "step": 25740 }, { "epoch": 3.2, "learning_rate": 9.383791858583345e-06, "loss": 0.043, "step": 25750 }, { "epoch": 3.2, "learning_rate": 9.383542885596913e-06, "loss": 0.0885, "step": 25760 }, { "epoch": 3.2, "learning_rate": 9.383293912610483e-06, "loss": 0.0814, "step": 25770 }, { "epoch": 3.2, "learning_rate": 9.383044939624052e-06, "loss": 0.0573, "step": 25780 }, { "epoch": 3.2, "learning_rate": 9.38279596663762e-06, "loss": 0.0455, "step": 25790 }, { "epoch": 3.2, "learning_rate": 9.382546993651189e-06, "loss": 0.0441, "step": 25800 }, { "epoch": 3.21, "learning_rate": 9.382298020664759e-06, "loss": 0.0384, "step": 25810 }, { "epoch": 3.21, "learning_rate": 9.382049047678328e-06, "loss": 0.0629, "step": 25820 }, { "epoch": 3.21, "learning_rate": 9.381800074691896e-06, "loss": 0.0852, "step": 25830 }, { "epoch": 3.21, "learning_rate": 9.381551101705466e-06, "loss": 0.0776, "step": 25840 }, { "epoch": 3.21, "learning_rate": 9.381302128719035e-06, "loss": 0.0514, "step": 25850 }, { "epoch": 3.21, "learning_rate": 9.381053155732603e-06, "loss": 0.051, "step": 25860 }, { "epoch": 3.21, "learning_rate": 9.380804182746172e-06, "loss": 0.078, "step": 25870 }, { "epoch": 3.21, "learning_rate": 9.380555209759742e-06, "loss": 0.0641, "step": 25880 }, { "epoch": 3.21, "learning_rate": 9.38030623677331e-06, "loss": 0.0406, "step": 25890 }, { "epoch": 3.22, "learning_rate": 9.38005726378688e-06, "loss": 0.0515, "step": 25900 }, { "epoch": 3.22, "learning_rate": 9.379808290800448e-06, "loss": 0.0506, "step": 25910 }, { "epoch": 3.22, "learning_rate": 9.379559317814018e-06, "loss": 0.0977, "step": 25920 }, { "epoch": 3.22, "learning_rate": 9.379310344827586e-06, "loss": 0.0423, "step": 25930 }, { "epoch": 3.22, "learning_rate": 9.379061371841157e-06, "loss": 0.0608, "step": 25940 }, { "epoch": 3.22, "learning_rate": 9.378812398854725e-06, "loss": 0.0704, "step": 25950 }, { "epoch": 3.22, "learning_rate": 9.378563425868295e-06, "loss": 0.0727, "step": 25960 }, { "epoch": 3.22, "learning_rate": 9.378314452881862e-06, "loss": 0.0652, "step": 25970 }, { "epoch": 3.23, "learning_rate": 9.378065479895432e-06, "loss": 0.079, "step": 25980 }, { "epoch": 3.23, "learning_rate": 9.377816506909e-06, "loss": 0.0808, "step": 25990 }, { "epoch": 3.23, "learning_rate": 9.377567533922571e-06, "loss": 0.0823, "step": 26000 }, { "epoch": 3.23, "learning_rate": 9.37731856093614e-06, "loss": 0.0609, "step": 26010 }, { "epoch": 3.23, "learning_rate": 9.377069587949708e-06, "loss": 0.0656, "step": 26020 }, { "epoch": 3.23, "learning_rate": 9.376820614963277e-06, "loss": 0.0416, "step": 26030 }, { "epoch": 3.23, "learning_rate": 9.376571641976847e-06, "loss": 0.0543, "step": 26040 }, { "epoch": 3.23, "learning_rate": 9.376322668990415e-06, "loss": 0.0661, "step": 26050 }, { "epoch": 3.24, "learning_rate": 9.376073696003984e-06, "loss": 0.0549, "step": 26060 }, { "epoch": 3.24, "learning_rate": 9.375824723017554e-06, "loss": 0.0503, "step": 26070 }, { "epoch": 3.24, "learning_rate": 9.375575750031123e-06, "loss": 0.0551, "step": 26080 }, { "epoch": 3.24, "learning_rate": 9.375326777044691e-06, "loss": 0.0653, "step": 26090 }, { "epoch": 3.24, "learning_rate": 9.37507780405826e-06, "loss": 0.0489, "step": 26100 }, { "epoch": 3.24, "learning_rate": 9.37482883107183e-06, "loss": 0.0573, "step": 26110 }, { "epoch": 3.24, "learning_rate": 9.374579858085398e-06, "loss": 0.0546, "step": 26120 }, { "epoch": 3.24, "learning_rate": 9.374330885098968e-06, "loss": 0.0737, "step": 26130 }, { "epoch": 3.25, "learning_rate": 9.374081912112537e-06, "loss": 0.0506, "step": 26140 }, { "epoch": 3.25, "learning_rate": 9.373832939126106e-06, "loss": 0.0827, "step": 26150 }, { "epoch": 3.25, "learning_rate": 9.373583966139674e-06, "loss": 0.0827, "step": 26160 }, { "epoch": 3.25, "learning_rate": 9.373334993153244e-06, "loss": 0.0982, "step": 26170 }, { "epoch": 3.25, "learning_rate": 9.373086020166813e-06, "loss": 0.0522, "step": 26180 }, { "epoch": 3.25, "learning_rate": 9.372837047180381e-06, "loss": 0.047, "step": 26190 }, { "epoch": 3.25, "learning_rate": 9.372588074193951e-06, "loss": 0.0737, "step": 26200 }, { "epoch": 3.25, "learning_rate": 9.37233910120752e-06, "loss": 0.0768, "step": 26210 }, { "epoch": 3.26, "learning_rate": 9.372090128221089e-06, "loss": 0.0669, "step": 26220 }, { "epoch": 3.26, "learning_rate": 9.371841155234657e-06, "loss": 0.0577, "step": 26230 }, { "epoch": 3.26, "learning_rate": 9.371592182248227e-06, "loss": 0.0814, "step": 26240 }, { "epoch": 3.26, "learning_rate": 9.371343209261796e-06, "loss": 0.0594, "step": 26250 }, { "epoch": 3.26, "learning_rate": 9.371094236275366e-06, "loss": 0.0557, "step": 26260 }, { "epoch": 3.26, "learning_rate": 9.370845263288933e-06, "loss": 0.0728, "step": 26270 }, { "epoch": 3.26, "learning_rate": 9.370596290302503e-06, "loss": 0.0828, "step": 26280 }, { "epoch": 3.26, "learning_rate": 9.370347317316072e-06, "loss": 0.053, "step": 26290 }, { "epoch": 3.27, "learning_rate": 9.370098344329642e-06, "loss": 0.0588, "step": 26300 }, { "epoch": 3.27, "learning_rate": 9.36984937134321e-06, "loss": 0.073, "step": 26310 }, { "epoch": 3.27, "learning_rate": 9.369600398356779e-06, "loss": 0.0586, "step": 26320 }, { "epoch": 3.27, "learning_rate": 9.369351425370347e-06, "loss": 0.0627, "step": 26330 }, { "epoch": 3.27, "learning_rate": 9.369102452383917e-06, "loss": 0.0495, "step": 26340 }, { "epoch": 3.27, "learning_rate": 9.368853479397486e-06, "loss": 0.0612, "step": 26350 }, { "epoch": 3.27, "learning_rate": 9.368604506411055e-06, "loss": 0.0524, "step": 26360 }, { "epoch": 3.27, "learning_rate": 9.368355533424625e-06, "loss": 0.066, "step": 26370 }, { "epoch": 3.28, "learning_rate": 9.368106560438193e-06, "loss": 0.0727, "step": 26380 }, { "epoch": 3.28, "learning_rate": 9.367857587451762e-06, "loss": 0.081, "step": 26390 }, { "epoch": 3.28, "learning_rate": 9.36760861446533e-06, "loss": 0.0787, "step": 26400 }, { "epoch": 3.28, "learning_rate": 9.3673596414789e-06, "loss": 0.0431, "step": 26410 }, { "epoch": 3.28, "learning_rate": 9.367110668492469e-06, "loss": 0.0649, "step": 26420 }, { "epoch": 3.28, "learning_rate": 9.36686169550604e-06, "loss": 0.0591, "step": 26430 }, { "epoch": 3.28, "learning_rate": 9.366612722519606e-06, "loss": 0.0525, "step": 26440 }, { "epoch": 3.28, "learning_rate": 9.366363749533176e-06, "loss": 0.0792, "step": 26450 }, { "epoch": 3.29, "learning_rate": 9.366114776546745e-06, "loss": 0.0675, "step": 26460 }, { "epoch": 3.29, "learning_rate": 9.365865803560315e-06, "loss": 0.082, "step": 26470 }, { "epoch": 3.29, "learning_rate": 9.365616830573883e-06, "loss": 0.0648, "step": 26480 }, { "epoch": 3.29, "learning_rate": 9.365367857587454e-06, "loss": 0.0658, "step": 26490 }, { "epoch": 3.29, "learning_rate": 9.36511888460102e-06, "loss": 0.0698, "step": 26500 }, { "epoch": 3.29, "learning_rate": 9.36486991161459e-06, "loss": 0.052, "step": 26510 }, { "epoch": 3.29, "learning_rate": 9.36462093862816e-06, "loss": 0.0553, "step": 26520 }, { "epoch": 3.29, "learning_rate": 9.36437196564173e-06, "loss": 0.0535, "step": 26530 }, { "epoch": 3.3, "learning_rate": 9.364122992655298e-06, "loss": 0.0698, "step": 26540 }, { "epoch": 3.3, "learning_rate": 9.363874019668866e-06, "loss": 0.0348, "step": 26550 }, { "epoch": 3.3, "learning_rate": 9.363625046682435e-06, "loss": 0.06, "step": 26560 }, { "epoch": 3.3, "learning_rate": 9.363376073696005e-06, "loss": 0.0578, "step": 26570 }, { "epoch": 3.3, "learning_rate": 9.363127100709574e-06, "loss": 0.0679, "step": 26580 }, { "epoch": 3.3, "learning_rate": 9.362878127723142e-06, "loss": 0.0507, "step": 26590 }, { "epoch": 3.3, "learning_rate": 9.362629154736712e-06, "loss": 0.0522, "step": 26600 }, { "epoch": 3.3, "learning_rate": 9.362380181750281e-06, "loss": 0.0412, "step": 26610 }, { "epoch": 3.31, "learning_rate": 9.36213120876385e-06, "loss": 0.0603, "step": 26620 }, { "epoch": 3.31, "learning_rate": 9.361882235777418e-06, "loss": 0.0669, "step": 26630 }, { "epoch": 3.31, "learning_rate": 9.361633262790988e-06, "loss": 0.0565, "step": 26640 }, { "epoch": 3.31, "learning_rate": 9.361384289804557e-06, "loss": 0.044, "step": 26650 }, { "epoch": 3.31, "learning_rate": 9.361135316818127e-06, "loss": 0.072, "step": 26660 }, { "epoch": 3.31, "learning_rate": 9.360886343831695e-06, "loss": 0.0706, "step": 26670 }, { "epoch": 3.31, "learning_rate": 9.360637370845264e-06, "loss": 0.0531, "step": 26680 }, { "epoch": 3.31, "learning_rate": 9.360388397858832e-06, "loss": 0.0391, "step": 26690 }, { "epoch": 3.32, "learning_rate": 9.360139424872403e-06, "loss": 0.0786, "step": 26700 }, { "epoch": 3.32, "learning_rate": 9.359890451885971e-06, "loss": 0.0557, "step": 26710 }, { "epoch": 3.32, "learning_rate": 9.35964147889954e-06, "loss": 0.061, "step": 26720 }, { "epoch": 3.32, "learning_rate": 9.35939250591311e-06, "loss": 0.0638, "step": 26730 }, { "epoch": 3.32, "learning_rate": 9.359143532926678e-06, "loss": 0.0476, "step": 26740 }, { "epoch": 3.32, "learning_rate": 9.358894559940247e-06, "loss": 0.0499, "step": 26750 }, { "epoch": 3.32, "learning_rate": 9.358645586953815e-06, "loss": 0.0458, "step": 26760 }, { "epoch": 3.32, "learning_rate": 9.358396613967386e-06, "loss": 0.0853, "step": 26770 }, { "epoch": 3.33, "learning_rate": 9.358147640980954e-06, "loss": 0.0714, "step": 26780 }, { "epoch": 3.33, "learning_rate": 9.357898667994524e-06, "loss": 0.0311, "step": 26790 }, { "epoch": 3.33, "learning_rate": 9.357649695008091e-06, "loss": 0.0496, "step": 26800 }, { "epoch": 3.33, "learning_rate": 9.357400722021661e-06, "loss": 0.044, "step": 26810 }, { "epoch": 3.33, "learning_rate": 9.35715174903523e-06, "loss": 0.0973, "step": 26820 }, { "epoch": 3.33, "learning_rate": 9.3569027760488e-06, "loss": 0.0457, "step": 26830 }, { "epoch": 3.33, "learning_rate": 9.356653803062369e-06, "loss": 0.0687, "step": 26840 }, { "epoch": 3.33, "learning_rate": 9.356404830075937e-06, "loss": 0.0414, "step": 26850 }, { "epoch": 3.34, "learning_rate": 9.356155857089506e-06, "loss": 0.0542, "step": 26860 }, { "epoch": 3.34, "learning_rate": 9.355906884103076e-06, "loss": 0.0643, "step": 26870 }, { "epoch": 3.34, "learning_rate": 9.355657911116644e-06, "loss": 0.058, "step": 26880 }, { "epoch": 3.34, "learning_rate": 9.355408938130213e-06, "loss": 0.0625, "step": 26890 }, { "epoch": 3.34, "learning_rate": 9.355159965143783e-06, "loss": 0.0582, "step": 26900 }, { "epoch": 3.34, "learning_rate": 9.354910992157352e-06, "loss": 0.074, "step": 26910 }, { "epoch": 3.34, "learning_rate": 9.35466201917092e-06, "loss": 0.0553, "step": 26920 }, { "epoch": 3.34, "learning_rate": 9.354413046184489e-06, "loss": 0.0719, "step": 26930 }, { "epoch": 3.35, "learning_rate": 9.354164073198059e-06, "loss": 0.0608, "step": 26940 }, { "epoch": 3.35, "learning_rate": 9.353915100211627e-06, "loss": 0.0753, "step": 26950 }, { "epoch": 3.35, "learning_rate": 9.353666127225198e-06, "loss": 0.0418, "step": 26960 }, { "epoch": 3.35, "learning_rate": 9.353417154238766e-06, "loss": 0.0787, "step": 26970 }, { "epoch": 3.35, "learning_rate": 9.353168181252335e-06, "loss": 0.0692, "step": 26980 }, { "epoch": 3.35, "learning_rate": 9.352919208265903e-06, "loss": 0.0727, "step": 26990 }, { "epoch": 3.35, "learning_rate": 9.352670235279473e-06, "loss": 0.0485, "step": 27000 }, { "epoch": 3.35, "learning_rate": 9.352421262293042e-06, "loss": 0.0435, "step": 27010 }, { "epoch": 3.36, "learning_rate": 9.352172289306612e-06, "loss": 0.0597, "step": 27020 }, { "epoch": 3.36, "learning_rate": 9.35192331632018e-06, "loss": 0.0601, "step": 27030 }, { "epoch": 3.36, "learning_rate": 9.35167434333375e-06, "loss": 0.0668, "step": 27040 }, { "epoch": 3.36, "learning_rate": 9.351425370347318e-06, "loss": 0.0572, "step": 27050 }, { "epoch": 3.36, "learning_rate": 9.351176397360888e-06, "loss": 0.0605, "step": 27060 }, { "epoch": 3.36, "learning_rate": 9.350927424374456e-06, "loss": 0.0636, "step": 27070 }, { "epoch": 3.36, "learning_rate": 9.350678451388025e-06, "loss": 0.0692, "step": 27080 }, { "epoch": 3.36, "learning_rate": 9.350429478401593e-06, "loss": 0.0648, "step": 27090 }, { "epoch": 3.37, "learning_rate": 9.350180505415164e-06, "loss": 0.0565, "step": 27100 }, { "epoch": 3.37, "learning_rate": 9.349931532428732e-06, "loss": 0.0681, "step": 27110 }, { "epoch": 3.37, "learning_rate": 9.3496825594423e-06, "loss": 0.0641, "step": 27120 }, { "epoch": 3.37, "learning_rate": 9.349433586455871e-06, "loss": 0.0658, "step": 27130 }, { "epoch": 3.37, "learning_rate": 9.34918461346944e-06, "loss": 0.0476, "step": 27140 }, { "epoch": 3.37, "learning_rate": 9.348935640483008e-06, "loss": 0.0597, "step": 27150 }, { "epoch": 3.37, "learning_rate": 9.348686667496576e-06, "loss": 0.0843, "step": 27160 }, { "epoch": 3.37, "learning_rate": 9.348437694510147e-06, "loss": 0.0648, "step": 27170 }, { "epoch": 3.38, "learning_rate": 9.348188721523715e-06, "loss": 0.0563, "step": 27180 }, { "epoch": 3.38, "learning_rate": 9.347939748537285e-06, "loss": 0.0471, "step": 27190 }, { "epoch": 3.38, "learning_rate": 9.347690775550854e-06, "loss": 0.0396, "step": 27200 }, { "epoch": 3.38, "learning_rate": 9.347441802564422e-06, "loss": 0.0523, "step": 27210 }, { "epoch": 3.38, "learning_rate": 9.347192829577991e-06, "loss": 0.0707, "step": 27220 }, { "epoch": 3.38, "learning_rate": 9.346943856591561e-06, "loss": 0.0456, "step": 27230 }, { "epoch": 3.38, "learning_rate": 9.34669488360513e-06, "loss": 0.0414, "step": 27240 }, { "epoch": 3.38, "learning_rate": 9.346445910618698e-06, "loss": 0.0465, "step": 27250 }, { "epoch": 3.39, "learning_rate": 9.346196937632268e-06, "loss": 0.0862, "step": 27260 }, { "epoch": 3.39, "learning_rate": 9.345947964645837e-06, "loss": 0.0594, "step": 27270 }, { "epoch": 3.39, "learning_rate": 9.345698991659405e-06, "loss": 0.0469, "step": 27280 }, { "epoch": 3.39, "learning_rate": 9.345450018672974e-06, "loss": 0.0832, "step": 27290 }, { "epoch": 3.39, "learning_rate": 9.345201045686544e-06, "loss": 0.0547, "step": 27300 }, { "epoch": 3.39, "learning_rate": 9.344952072700113e-06, "loss": 0.0528, "step": 27310 }, { "epoch": 3.39, "learning_rate": 9.344703099713683e-06, "loss": 0.0565, "step": 27320 }, { "epoch": 3.39, "learning_rate": 9.34445412672725e-06, "loss": 0.0653, "step": 27330 }, { "epoch": 3.39, "learning_rate": 9.34420515374082e-06, "loss": 0.0501, "step": 27340 }, { "epoch": 3.4, "learning_rate": 9.343956180754388e-06, "loss": 0.061, "step": 27350 }, { "epoch": 3.4, "learning_rate": 9.343707207767959e-06, "loss": 0.0532, "step": 27360 }, { "epoch": 3.4, "learning_rate": 9.343458234781527e-06, "loss": 0.0558, "step": 27370 }, { "epoch": 3.4, "learning_rate": 9.343209261795096e-06, "loss": 0.0501, "step": 27380 }, { "epoch": 3.4, "learning_rate": 9.342960288808664e-06, "loss": 0.0516, "step": 27390 }, { "epoch": 3.4, "learning_rate": 9.342711315822234e-06, "loss": 0.0486, "step": 27400 }, { "epoch": 3.4, "learning_rate": 9.342462342835803e-06, "loss": 0.0477, "step": 27410 }, { "epoch": 3.4, "learning_rate": 9.342213369849371e-06, "loss": 0.0806, "step": 27420 }, { "epoch": 3.41, "learning_rate": 9.341964396862942e-06, "loss": 0.0477, "step": 27430 }, { "epoch": 3.41, "learning_rate": 9.34171542387651e-06, "loss": 0.075, "step": 27440 }, { "epoch": 3.41, "learning_rate": 9.341466450890079e-06, "loss": 0.0482, "step": 27450 }, { "epoch": 3.41, "learning_rate": 9.341217477903647e-06, "loss": 0.0637, "step": 27460 }, { "epoch": 3.41, "learning_rate": 9.340968504917217e-06, "loss": 0.0686, "step": 27470 }, { "epoch": 3.41, "learning_rate": 9.340719531930786e-06, "loss": 0.062, "step": 27480 }, { "epoch": 3.41, "learning_rate": 9.340470558944356e-06, "loss": 0.0598, "step": 27490 }, { "epoch": 3.41, "learning_rate": 9.340221585957925e-06, "loss": 0.0559, "step": 27500 }, { "epoch": 3.42, "learning_rate": 9.339972612971493e-06, "loss": 0.0377, "step": 27510 }, { "epoch": 3.42, "learning_rate": 9.339723639985062e-06, "loss": 0.0533, "step": 27520 }, { "epoch": 3.42, "learning_rate": 9.339474666998632e-06, "loss": 0.0769, "step": 27530 }, { "epoch": 3.42, "learning_rate": 9.3392256940122e-06, "loss": 0.0483, "step": 27540 }, { "epoch": 3.42, "learning_rate": 9.33897672102577e-06, "loss": 0.0711, "step": 27550 }, { "epoch": 3.42, "learning_rate": 9.338727748039339e-06, "loss": 0.057, "step": 27560 }, { "epoch": 3.42, "learning_rate": 9.338478775052908e-06, "loss": 0.0546, "step": 27570 }, { "epoch": 3.42, "learning_rate": 9.338229802066476e-06, "loss": 0.0677, "step": 27580 }, { "epoch": 3.43, "learning_rate": 9.337980829080046e-06, "loss": 0.0482, "step": 27590 }, { "epoch": 3.43, "learning_rate": 9.337731856093615e-06, "loss": 0.0624, "step": 27600 }, { "epoch": 3.43, "learning_rate": 9.337482883107183e-06, "loss": 0.0557, "step": 27610 }, { "epoch": 3.43, "learning_rate": 9.337233910120754e-06, "loss": 0.0912, "step": 27620 }, { "epoch": 3.43, "learning_rate": 9.336984937134322e-06, "loss": 0.056, "step": 27630 }, { "epoch": 3.43, "learning_rate": 9.33673596414789e-06, "loss": 0.0582, "step": 27640 }, { "epoch": 3.43, "learning_rate": 9.336486991161459e-06, "loss": 0.0551, "step": 27650 }, { "epoch": 3.43, "learning_rate": 9.33623801817503e-06, "loss": 0.0367, "step": 27660 }, { "epoch": 3.44, "learning_rate": 9.335989045188598e-06, "loss": 0.0612, "step": 27670 }, { "epoch": 3.44, "learning_rate": 9.335740072202168e-06, "loss": 0.0543, "step": 27680 }, { "epoch": 3.44, "learning_rate": 9.335491099215735e-06, "loss": 0.0632, "step": 27690 }, { "epoch": 3.44, "learning_rate": 9.335242126229305e-06, "loss": 0.0526, "step": 27700 }, { "epoch": 3.44, "learning_rate": 9.334993153242874e-06, "loss": 0.0521, "step": 27710 }, { "epoch": 3.44, "learning_rate": 9.334744180256444e-06, "loss": 0.0548, "step": 27720 }, { "epoch": 3.44, "learning_rate": 9.334495207270012e-06, "loss": 0.0735, "step": 27730 }, { "epoch": 3.44, "learning_rate": 9.33424623428358e-06, "loss": 0.0515, "step": 27740 }, { "epoch": 3.45, "learning_rate": 9.33399726129715e-06, "loss": 0.0365, "step": 27750 }, { "epoch": 3.45, "learning_rate": 9.33374828831072e-06, "loss": 0.0565, "step": 27760 }, { "epoch": 3.45, "learning_rate": 9.333499315324288e-06, "loss": 0.0764, "step": 27770 }, { "epoch": 3.45, "learning_rate": 9.333250342337857e-06, "loss": 0.0808, "step": 27780 }, { "epoch": 3.45, "learning_rate": 9.333001369351427e-06, "loss": 0.0613, "step": 27790 }, { "epoch": 3.45, "learning_rate": 9.332752396364995e-06, "loss": 0.0377, "step": 27800 }, { "epoch": 3.45, "learning_rate": 9.332503423378564e-06, "loss": 0.0631, "step": 27810 }, { "epoch": 3.45, "learning_rate": 9.332254450392132e-06, "loss": 0.0584, "step": 27820 }, { "epoch": 3.46, "learning_rate": 9.332005477405703e-06, "loss": 0.0647, "step": 27830 }, { "epoch": 3.46, "learning_rate": 9.331756504419271e-06, "loss": 0.0551, "step": 27840 }, { "epoch": 3.46, "learning_rate": 9.331507531432841e-06, "loss": 0.0397, "step": 27850 }, { "epoch": 3.46, "learning_rate": 9.331258558446408e-06, "loss": 0.0439, "step": 27860 }, { "epoch": 3.46, "learning_rate": 9.331009585459978e-06, "loss": 0.0752, "step": 27870 }, { "epoch": 3.46, "learning_rate": 9.330760612473547e-06, "loss": 0.063, "step": 27880 }, { "epoch": 3.46, "learning_rate": 9.330511639487117e-06, "loss": 0.0675, "step": 27890 }, { "epoch": 3.46, "learning_rate": 9.330262666500686e-06, "loss": 0.047, "step": 27900 }, { "epoch": 3.47, "learning_rate": 9.330013693514254e-06, "loss": 0.0816, "step": 27910 }, { "epoch": 3.47, "learning_rate": 9.329764720527823e-06, "loss": 0.0629, "step": 27920 }, { "epoch": 3.47, "learning_rate": 9.329515747541393e-06, "loss": 0.0802, "step": 27930 }, { "epoch": 3.47, "learning_rate": 9.329266774554961e-06, "loss": 0.035, "step": 27940 }, { "epoch": 3.47, "learning_rate": 9.32901780156853e-06, "loss": 0.045, "step": 27950 }, { "epoch": 3.47, "learning_rate": 9.3287688285821e-06, "loss": 0.055, "step": 27960 }, { "epoch": 3.47, "learning_rate": 9.328519855595669e-06, "loss": 0.0562, "step": 27970 }, { "epoch": 3.47, "learning_rate": 9.328270882609237e-06, "loss": 0.082, "step": 27980 }, { "epoch": 3.48, "learning_rate": 9.328021909622806e-06, "loss": 0.0645, "step": 27990 }, { "epoch": 3.48, "learning_rate": 9.327772936636376e-06, "loss": 0.0661, "step": 28000 }, { "epoch": 3.48, "learning_rate": 9.327523963649944e-06, "loss": 0.0692, "step": 28010 }, { "epoch": 3.48, "learning_rate": 9.327274990663515e-06, "loss": 0.0669, "step": 28020 }, { "epoch": 3.48, "learning_rate": 9.327026017677083e-06, "loss": 0.0551, "step": 28030 }, { "epoch": 3.48, "learning_rate": 9.326777044690652e-06, "loss": 0.0813, "step": 28040 }, { "epoch": 3.48, "learning_rate": 9.32652807170422e-06, "loss": 0.0615, "step": 28050 }, { "epoch": 3.48, "learning_rate": 9.32627909871779e-06, "loss": 0.0845, "step": 28060 }, { "epoch": 3.49, "learning_rate": 9.326030125731359e-06, "loss": 0.0751, "step": 28070 }, { "epoch": 3.49, "learning_rate": 9.325781152744929e-06, "loss": 0.1086, "step": 28080 }, { "epoch": 3.49, "learning_rate": 9.325532179758498e-06, "loss": 0.0607, "step": 28090 }, { "epoch": 3.49, "learning_rate": 9.325283206772066e-06, "loss": 0.0463, "step": 28100 }, { "epoch": 3.49, "learning_rate": 9.325034233785635e-06, "loss": 0.0693, "step": 28110 }, { "epoch": 3.49, "learning_rate": 9.324785260799205e-06, "loss": 0.0945, "step": 28120 }, { "epoch": 3.49, "learning_rate": 9.324536287812773e-06, "loss": 0.066, "step": 28130 }, { "epoch": 3.49, "learning_rate": 9.324287314826342e-06, "loss": 0.0734, "step": 28140 }, { "epoch": 3.5, "learning_rate": 9.324038341839912e-06, "loss": 0.0431, "step": 28150 }, { "epoch": 3.5, "learning_rate": 9.32378936885348e-06, "loss": 0.0602, "step": 28160 }, { "epoch": 3.5, "learning_rate": 9.323540395867049e-06, "loss": 0.0513, "step": 28170 }, { "epoch": 3.5, "learning_rate": 9.323291422880618e-06, "loss": 0.0581, "step": 28180 }, { "epoch": 3.5, "learning_rate": 9.323042449894188e-06, "loss": 0.0708, "step": 28190 }, { "epoch": 3.5, "learning_rate": 9.322793476907756e-06, "loss": 0.0823, "step": 28200 }, { "epoch": 3.5, "learning_rate": 9.322544503921326e-06, "loss": 0.057, "step": 28210 }, { "epoch": 3.5, "learning_rate": 9.322295530934893e-06, "loss": 0.0837, "step": 28220 }, { "epoch": 3.51, "learning_rate": 9.322046557948464e-06, "loss": 0.0853, "step": 28230 }, { "epoch": 3.51, "learning_rate": 9.321797584962032e-06, "loss": 0.0766, "step": 28240 }, { "epoch": 3.51, "learning_rate": 9.321548611975602e-06, "loss": 0.0732, "step": 28250 }, { "epoch": 3.51, "learning_rate": 9.32129963898917e-06, "loss": 0.0448, "step": 28260 }, { "epoch": 3.51, "learning_rate": 9.32105066600274e-06, "loss": 0.0734, "step": 28270 }, { "epoch": 3.51, "learning_rate": 9.320801693016308e-06, "loss": 0.0775, "step": 28280 }, { "epoch": 3.51, "learning_rate": 9.320552720029878e-06, "loss": 0.0632, "step": 28290 }, { "epoch": 3.51, "learning_rate": 9.320303747043447e-06, "loss": 0.0471, "step": 28300 }, { "epoch": 3.52, "learning_rate": 9.320054774057015e-06, "loss": 0.0721, "step": 28310 }, { "epoch": 3.52, "learning_rate": 9.319805801070585e-06, "loss": 0.0593, "step": 28320 }, { "epoch": 3.52, "learning_rate": 9.319556828084154e-06, "loss": 0.0492, "step": 28330 }, { "epoch": 3.52, "learning_rate": 9.319307855097722e-06, "loss": 0.0481, "step": 28340 }, { "epoch": 3.52, "learning_rate": 9.31905888211129e-06, "loss": 0.0752, "step": 28350 }, { "epoch": 3.52, "learning_rate": 9.318809909124861e-06, "loss": 0.0797, "step": 28360 }, { "epoch": 3.52, "learning_rate": 9.31856093613843e-06, "loss": 0.0799, "step": 28370 }, { "epoch": 3.52, "learning_rate": 9.318311963152e-06, "loss": 0.11, "step": 28380 }, { "epoch": 3.53, "learning_rate": 9.318062990165567e-06, "loss": 0.0563, "step": 28390 }, { "epoch": 3.53, "learning_rate": 9.317814017179137e-06, "loss": 0.0496, "step": 28400 }, { "epoch": 3.53, "learning_rate": 9.317565044192705e-06, "loss": 0.0524, "step": 28410 }, { "epoch": 3.53, "learning_rate": 9.317316071206275e-06, "loss": 0.0922, "step": 28420 }, { "epoch": 3.53, "learning_rate": 9.317067098219844e-06, "loss": 0.0348, "step": 28430 }, { "epoch": 3.53, "learning_rate": 9.316818125233413e-06, "loss": 0.0498, "step": 28440 }, { "epoch": 3.53, "learning_rate": 9.316569152246981e-06, "loss": 0.0564, "step": 28450 }, { "epoch": 3.53, "learning_rate": 9.316320179260551e-06, "loss": 0.0467, "step": 28460 }, { "epoch": 3.54, "learning_rate": 9.31607120627412e-06, "loss": 0.0564, "step": 28470 }, { "epoch": 3.54, "learning_rate": 9.315822233287688e-06, "loss": 0.0421, "step": 28480 }, { "epoch": 3.54, "learning_rate": 9.315573260301258e-06, "loss": 0.0587, "step": 28490 }, { "epoch": 3.54, "learning_rate": 9.315324287314827e-06, "loss": 0.0482, "step": 28500 }, { "epoch": 3.54, "learning_rate": 9.315075314328396e-06, "loss": 0.0573, "step": 28510 }, { "epoch": 3.54, "learning_rate": 9.314826341341964e-06, "loss": 0.0646, "step": 28520 }, { "epoch": 3.54, "learning_rate": 9.314577368355534e-06, "loss": 0.071, "step": 28530 }, { "epoch": 3.54, "learning_rate": 9.314328395369103e-06, "loss": 0.0436, "step": 28540 }, { "epoch": 3.55, "learning_rate": 9.314079422382673e-06, "loss": 0.0696, "step": 28550 }, { "epoch": 3.55, "learning_rate": 9.313830449396241e-06, "loss": 0.0677, "step": 28560 }, { "epoch": 3.55, "learning_rate": 9.31358147640981e-06, "loss": 0.0465, "step": 28570 }, { "epoch": 3.55, "learning_rate": 9.313332503423379e-06, "loss": 0.061, "step": 28580 }, { "epoch": 3.55, "learning_rate": 9.313083530436949e-06, "loss": 0.0594, "step": 28590 }, { "epoch": 3.55, "learning_rate": 9.312834557450517e-06, "loss": 0.0547, "step": 28600 }, { "epoch": 3.55, "learning_rate": 9.312585584464087e-06, "loss": 0.0963, "step": 28610 }, { "epoch": 3.55, "learning_rate": 9.312336611477656e-06, "loss": 0.059, "step": 28620 }, { "epoch": 3.56, "learning_rate": 9.312087638491224e-06, "loss": 0.0456, "step": 28630 }, { "epoch": 3.56, "learning_rate": 9.311838665504793e-06, "loss": 0.0661, "step": 28640 }, { "epoch": 3.56, "learning_rate": 9.311589692518363e-06, "loss": 0.0525, "step": 28650 }, { "epoch": 3.56, "learning_rate": 9.311340719531932e-06, "loss": 0.0473, "step": 28660 }, { "epoch": 3.56, "learning_rate": 9.3110917465455e-06, "loss": 0.0446, "step": 28670 }, { "epoch": 3.56, "learning_rate": 9.31084277355907e-06, "loss": 0.0611, "step": 28680 }, { "epoch": 3.56, "learning_rate": 9.310593800572639e-06, "loss": 0.0538, "step": 28690 }, { "epoch": 3.56, "learning_rate": 9.310344827586207e-06, "loss": 0.0628, "step": 28700 }, { "epoch": 3.57, "learning_rate": 9.310095854599776e-06, "loss": 0.0699, "step": 28710 }, { "epoch": 3.57, "learning_rate": 9.309846881613346e-06, "loss": 0.082, "step": 28720 }, { "epoch": 3.57, "learning_rate": 9.309597908626915e-06, "loss": 0.0845, "step": 28730 }, { "epoch": 3.57, "learning_rate": 9.309348935640485e-06, "loss": 0.0592, "step": 28740 }, { "epoch": 3.57, "learning_rate": 9.309099962654052e-06, "loss": 0.0759, "step": 28750 }, { "epoch": 3.57, "learning_rate": 9.308850989667622e-06, "loss": 0.0776, "step": 28760 }, { "epoch": 3.57, "learning_rate": 9.30860201668119e-06, "loss": 0.0711, "step": 28770 }, { "epoch": 3.57, "learning_rate": 9.30835304369476e-06, "loss": 0.0482, "step": 28780 }, { "epoch": 3.58, "learning_rate": 9.30810407070833e-06, "loss": 0.037, "step": 28790 }, { "epoch": 3.58, "learning_rate": 9.307855097721898e-06, "loss": 0.0603, "step": 28800 }, { "epoch": 3.58, "learning_rate": 9.307606124735466e-06, "loss": 0.0375, "step": 28810 }, { "epoch": 3.58, "learning_rate": 9.307357151749036e-06, "loss": 0.0521, "step": 28820 }, { "epoch": 3.58, "learning_rate": 9.307108178762605e-06, "loss": 0.0598, "step": 28830 }, { "epoch": 3.58, "learning_rate": 9.306859205776173e-06, "loss": 0.0444, "step": 28840 }, { "epoch": 3.58, "learning_rate": 9.306610232789744e-06, "loss": 0.0691, "step": 28850 }, { "epoch": 3.58, "learning_rate": 9.306361259803312e-06, "loss": 0.0476, "step": 28860 }, { "epoch": 3.58, "learning_rate": 9.30611228681688e-06, "loss": 0.0426, "step": 28870 }, { "epoch": 3.59, "learning_rate": 9.30586331383045e-06, "loss": 0.0697, "step": 28880 }, { "epoch": 3.59, "learning_rate": 9.30561434084402e-06, "loss": 0.0614, "step": 28890 }, { "epoch": 3.59, "learning_rate": 9.305365367857588e-06, "loss": 0.0789, "step": 28900 }, { "epoch": 3.59, "learning_rate": 9.305116394871158e-06, "loss": 0.0563, "step": 28910 }, { "epoch": 3.59, "learning_rate": 9.304867421884727e-06, "loss": 0.0838, "step": 28920 }, { "epoch": 3.59, "learning_rate": 9.304618448898295e-06, "loss": 0.0812, "step": 28930 }, { "epoch": 3.59, "learning_rate": 9.304369475911864e-06, "loss": 0.0413, "step": 28940 }, { "epoch": 3.59, "learning_rate": 9.304120502925434e-06, "loss": 0.0744, "step": 28950 }, { "epoch": 3.6, "learning_rate": 9.303871529939002e-06, "loss": 0.061, "step": 28960 }, { "epoch": 3.6, "learning_rate": 9.303622556952571e-06, "loss": 0.073, "step": 28970 }, { "epoch": 3.6, "learning_rate": 9.303373583966141e-06, "loss": 0.085, "step": 28980 }, { "epoch": 3.6, "learning_rate": 9.30312461097971e-06, "loss": 0.08, "step": 28990 }, { "epoch": 3.6, "learning_rate": 9.302875637993278e-06, "loss": 0.0582, "step": 29000 }, { "epoch": 3.6, "learning_rate": 9.302626665006847e-06, "loss": 0.0665, "step": 29010 }, { "epoch": 3.6, "learning_rate": 9.302377692020417e-06, "loss": 0.0784, "step": 29020 }, { "epoch": 3.6, "learning_rate": 9.302128719033985e-06, "loss": 0.0642, "step": 29030 }, { "epoch": 3.61, "learning_rate": 9.301879746047554e-06, "loss": 0.0501, "step": 29040 }, { "epoch": 3.61, "learning_rate": 9.301630773061122e-06, "loss": 0.0442, "step": 29050 }, { "epoch": 3.61, "learning_rate": 9.301381800074693e-06, "loss": 0.0592, "step": 29060 }, { "epoch": 3.61, "learning_rate": 9.301132827088261e-06, "loss": 0.0771, "step": 29070 }, { "epoch": 3.61, "learning_rate": 9.300883854101831e-06, "loss": 0.0493, "step": 29080 }, { "epoch": 3.61, "learning_rate": 9.3006348811154e-06, "loss": 0.0473, "step": 29090 }, { "epoch": 3.61, "learning_rate": 9.300385908128968e-06, "loss": 0.0523, "step": 29100 }, { "epoch": 3.61, "learning_rate": 9.300136935142537e-06, "loss": 0.0602, "step": 29110 }, { "epoch": 3.62, "learning_rate": 9.299887962156107e-06, "loss": 0.0788, "step": 29120 }, { "epoch": 3.62, "learning_rate": 9.299638989169676e-06, "loss": 0.0467, "step": 29130 }, { "epoch": 3.62, "learning_rate": 9.299390016183246e-06, "loss": 0.0533, "step": 29140 }, { "epoch": 3.62, "learning_rate": 9.299141043196814e-06, "loss": 0.0617, "step": 29150 }, { "epoch": 3.62, "learning_rate": 9.298892070210383e-06, "loss": 0.0881, "step": 29160 }, { "epoch": 3.62, "learning_rate": 9.298643097223951e-06, "loss": 0.052, "step": 29170 }, { "epoch": 3.62, "learning_rate": 9.298394124237522e-06, "loss": 0.0571, "step": 29180 }, { "epoch": 3.62, "learning_rate": 9.29814515125109e-06, "loss": 0.0496, "step": 29190 }, { "epoch": 3.63, "learning_rate": 9.297896178264659e-06, "loss": 0.0611, "step": 29200 }, { "epoch": 3.63, "learning_rate": 9.297647205278229e-06, "loss": 0.0572, "step": 29210 }, { "epoch": 3.63, "learning_rate": 9.297398232291797e-06, "loss": 0.05, "step": 29220 }, { "epoch": 3.63, "learning_rate": 9.297149259305366e-06, "loss": 0.04, "step": 29230 }, { "epoch": 3.63, "learning_rate": 9.296900286318934e-06, "loss": 0.0455, "step": 29240 }, { "epoch": 3.63, "learning_rate": 9.296651313332505e-06, "loss": 0.0623, "step": 29250 }, { "epoch": 3.63, "learning_rate": 9.296402340346073e-06, "loss": 0.0643, "step": 29260 }, { "epoch": 3.63, "learning_rate": 9.296153367359643e-06, "loss": 0.0505, "step": 29270 }, { "epoch": 3.64, "learning_rate": 9.29590439437321e-06, "loss": 0.0518, "step": 29280 }, { "epoch": 3.64, "learning_rate": 9.29565542138678e-06, "loss": 0.0582, "step": 29290 }, { "epoch": 3.64, "learning_rate": 9.295406448400349e-06, "loss": 0.067, "step": 29300 }, { "epoch": 3.64, "learning_rate": 9.295157475413919e-06, "loss": 0.0526, "step": 29310 }, { "epoch": 3.64, "learning_rate": 9.294908502427488e-06, "loss": 0.0649, "step": 29320 }, { "epoch": 3.64, "learning_rate": 9.294659529441056e-06, "loss": 0.0735, "step": 29330 }, { "epoch": 3.64, "learning_rate": 9.294410556454625e-06, "loss": 0.0643, "step": 29340 }, { "epoch": 3.64, "learning_rate": 9.294161583468195e-06, "loss": 0.0635, "step": 29350 }, { "epoch": 3.65, "learning_rate": 9.293912610481763e-06, "loss": 0.0517, "step": 29360 }, { "epoch": 3.65, "learning_rate": 9.293663637495332e-06, "loss": 0.0592, "step": 29370 }, { "epoch": 3.65, "learning_rate": 9.293414664508902e-06, "loss": 0.0818, "step": 29380 }, { "epoch": 3.65, "learning_rate": 9.29316569152247e-06, "loss": 0.0726, "step": 29390 }, { "epoch": 3.65, "learning_rate": 9.29291671853604e-06, "loss": 0.0653, "step": 29400 }, { "epoch": 3.65, "learning_rate": 9.292667745549608e-06, "loss": 0.0572, "step": 29410 }, { "epoch": 3.65, "learning_rate": 9.292418772563178e-06, "loss": 0.0702, "step": 29420 }, { "epoch": 3.65, "learning_rate": 9.292169799576746e-06, "loss": 0.0839, "step": 29430 }, { "epoch": 3.66, "learning_rate": 9.291920826590317e-06, "loss": 0.0878, "step": 29440 }, { "epoch": 3.66, "learning_rate": 9.291671853603885e-06, "loss": 0.0644, "step": 29450 }, { "epoch": 3.66, "learning_rate": 9.291422880617454e-06, "loss": 0.0798, "step": 29460 }, { "epoch": 3.66, "learning_rate": 9.291173907631022e-06, "loss": 0.0678, "step": 29470 }, { "epoch": 3.66, "learning_rate": 9.290924934644592e-06, "loss": 0.0521, "step": 29480 }, { "epoch": 3.66, "learning_rate": 9.290675961658161e-06, "loss": 0.0491, "step": 29490 }, { "epoch": 3.66, "learning_rate": 9.29042698867173e-06, "loss": 0.0381, "step": 29500 }, { "epoch": 3.66, "learning_rate": 9.2901780156853e-06, "loss": 0.0449, "step": 29510 }, { "epoch": 3.67, "learning_rate": 9.289929042698868e-06, "loss": 0.0535, "step": 29520 }, { "epoch": 3.67, "learning_rate": 9.289680069712437e-06, "loss": 0.0617, "step": 29530 }, { "epoch": 3.67, "learning_rate": 9.289431096726005e-06, "loss": 0.0626, "step": 29540 }, { "epoch": 3.67, "learning_rate": 9.289182123739575e-06, "loss": 0.0543, "step": 29550 }, { "epoch": 3.67, "learning_rate": 9.288933150753144e-06, "loss": 0.0422, "step": 29560 }, { "epoch": 3.67, "learning_rate": 9.288684177766714e-06, "loss": 0.0488, "step": 29570 }, { "epoch": 3.67, "learning_rate": 9.288435204780281e-06, "loss": 0.0498, "step": 29580 }, { "epoch": 3.67, "learning_rate": 9.288186231793851e-06, "loss": 0.0578, "step": 29590 }, { "epoch": 3.68, "learning_rate": 9.28793725880742e-06, "loss": 0.0752, "step": 29600 }, { "epoch": 3.68, "learning_rate": 9.28768828582099e-06, "loss": 0.0544, "step": 29610 }, { "epoch": 3.68, "learning_rate": 9.287439312834558e-06, "loss": 0.0676, "step": 29620 }, { "epoch": 3.68, "learning_rate": 9.287190339848129e-06, "loss": 0.0689, "step": 29630 }, { "epoch": 3.68, "learning_rate": 9.286941366861695e-06, "loss": 0.0536, "step": 29640 }, { "epoch": 3.68, "learning_rate": 9.286692393875266e-06, "loss": 0.0595, "step": 29650 }, { "epoch": 3.68, "learning_rate": 9.286443420888834e-06, "loss": 0.0567, "step": 29660 }, { "epoch": 3.68, "learning_rate": 9.286194447902404e-06, "loss": 0.0638, "step": 29670 }, { "epoch": 3.69, "learning_rate": 9.285945474915973e-06, "loss": 0.0483, "step": 29680 }, { "epoch": 3.69, "learning_rate": 9.285696501929541e-06, "loss": 0.0658, "step": 29690 }, { "epoch": 3.69, "learning_rate": 9.28544752894311e-06, "loss": 0.0315, "step": 29700 }, { "epoch": 3.69, "learning_rate": 9.28519855595668e-06, "loss": 0.0681, "step": 29710 }, { "epoch": 3.69, "learning_rate": 9.284949582970249e-06, "loss": 0.0592, "step": 29720 }, { "epoch": 3.69, "learning_rate": 9.284700609983817e-06, "loss": 0.0591, "step": 29730 }, { "epoch": 3.69, "learning_rate": 9.284451636997387e-06, "loss": 0.0589, "step": 29740 }, { "epoch": 3.69, "learning_rate": 9.284202664010956e-06, "loss": 0.06, "step": 29750 }, { "epoch": 3.7, "learning_rate": 9.283953691024524e-06, "loss": 0.0356, "step": 29760 }, { "epoch": 3.7, "learning_rate": 9.283704718038093e-06, "loss": 0.0681, "step": 29770 }, { "epoch": 3.7, "learning_rate": 9.283455745051663e-06, "loss": 0.0701, "step": 29780 }, { "epoch": 3.7, "learning_rate": 9.283206772065232e-06, "loss": 0.068, "step": 29790 }, { "epoch": 3.7, "learning_rate": 9.282957799078802e-06, "loss": 0.0595, "step": 29800 }, { "epoch": 3.7, "learning_rate": 9.282708826092369e-06, "loss": 0.0575, "step": 29810 }, { "epoch": 3.7, "learning_rate": 9.282459853105939e-06, "loss": 0.0773, "step": 29820 }, { "epoch": 3.7, "learning_rate": 9.282210880119507e-06, "loss": 0.0602, "step": 29830 }, { "epoch": 3.71, "learning_rate": 9.281961907133078e-06, "loss": 0.038, "step": 29840 }, { "epoch": 3.71, "learning_rate": 9.281712934146646e-06, "loss": 0.0261, "step": 29850 }, { "epoch": 3.71, "learning_rate": 9.281463961160215e-06, "loss": 0.0427, "step": 29860 }, { "epoch": 3.71, "learning_rate": 9.281214988173783e-06, "loss": 0.06, "step": 29870 }, { "epoch": 3.71, "learning_rate": 9.280966015187353e-06, "loss": 0.063, "step": 29880 }, { "epoch": 3.71, "learning_rate": 9.280717042200922e-06, "loss": 0.0782, "step": 29890 }, { "epoch": 3.71, "learning_rate": 9.28046806921449e-06, "loss": 0.0696, "step": 29900 }, { "epoch": 3.71, "learning_rate": 9.28021909622806e-06, "loss": 0.0389, "step": 29910 }, { "epoch": 3.72, "learning_rate": 9.279970123241629e-06, "loss": 0.0855, "step": 29920 }, { "epoch": 3.72, "learning_rate": 9.279721150255198e-06, "loss": 0.0513, "step": 29930 }, { "epoch": 3.72, "learning_rate": 9.279472177268766e-06, "loss": 0.082, "step": 29940 }, { "epoch": 3.72, "learning_rate": 9.279223204282336e-06, "loss": 0.0882, "step": 29950 }, { "epoch": 3.72, "learning_rate": 9.278974231295905e-06, "loss": 0.0418, "step": 29960 }, { "epoch": 3.72, "learning_rate": 9.278725258309475e-06, "loss": 0.056, "step": 29970 }, { "epoch": 3.72, "learning_rate": 9.278476285323044e-06, "loss": 0.0657, "step": 29980 }, { "epoch": 3.72, "learning_rate": 9.278227312336612e-06, "loss": 0.0776, "step": 29990 }, { "epoch": 3.73, "learning_rate": 9.27797833935018e-06, "loss": 0.0326, "step": 30000 }, { "epoch": 3.73, "eval_bleu": 89.2582, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7452, "eval_has_error_f1": 0.6199, "eval_loss": 0.054089099168777466, "eval_runtime": 1323.2748, "eval_samples_per_second": 3.021, "eval_steps_per_second": 0.756, "step": 30000 }, { "epoch": 3.73, "learning_rate": 9.27772936636375e-06, "loss": 0.0532, "step": 30010 }, { "epoch": 3.73, "learning_rate": 9.27748039337732e-06, "loss": 0.0848, "step": 30020 }, { "epoch": 3.73, "learning_rate": 9.277231420390888e-06, "loss": 0.0544, "step": 30030 }, { "epoch": 3.73, "learning_rate": 9.276982447404458e-06, "loss": 0.0606, "step": 30040 }, { "epoch": 3.73, "learning_rate": 9.276733474418027e-06, "loss": 0.0729, "step": 30050 }, { "epoch": 3.73, "learning_rate": 9.276484501431595e-06, "loss": 0.0594, "step": 30060 }, { "epoch": 3.73, "learning_rate": 9.276235528445164e-06, "loss": 0.0627, "step": 30070 }, { "epoch": 3.74, "learning_rate": 9.275986555458734e-06, "loss": 0.0517, "step": 30080 }, { "epoch": 3.74, "learning_rate": 9.275737582472302e-06, "loss": 0.0469, "step": 30090 }, { "epoch": 3.74, "learning_rate": 9.275488609485873e-06, "loss": 0.0532, "step": 30100 }, { "epoch": 3.74, "learning_rate": 9.27523963649944e-06, "loss": 0.0528, "step": 30110 }, { "epoch": 3.74, "learning_rate": 9.27499066351301e-06, "loss": 0.0571, "step": 30120 }, { "epoch": 3.74, "learning_rate": 9.274741690526578e-06, "loss": 0.0633, "step": 30130 }, { "epoch": 3.74, "learning_rate": 9.274492717540148e-06, "loss": 0.0568, "step": 30140 }, { "epoch": 3.74, "learning_rate": 9.274243744553717e-06, "loss": 0.0542, "step": 30150 }, { "epoch": 3.75, "learning_rate": 9.273994771567287e-06, "loss": 0.0798, "step": 30160 }, { "epoch": 3.75, "learning_rate": 9.273745798580854e-06, "loss": 0.0863, "step": 30170 }, { "epoch": 3.75, "learning_rate": 9.273496825594424e-06, "loss": 0.0548, "step": 30180 }, { "epoch": 3.75, "learning_rate": 9.273247852607993e-06, "loss": 0.0633, "step": 30190 }, { "epoch": 3.75, "learning_rate": 9.272998879621563e-06, "loss": 0.0569, "step": 30200 }, { "epoch": 3.75, "learning_rate": 9.272749906635131e-06, "loss": 0.0553, "step": 30210 }, { "epoch": 3.75, "learning_rate": 9.2725009336487e-06, "loss": 0.0506, "step": 30220 }, { "epoch": 3.75, "learning_rate": 9.272251960662268e-06, "loss": 0.0637, "step": 30230 }, { "epoch": 3.76, "learning_rate": 9.272002987675839e-06, "loss": 0.0496, "step": 30240 }, { "epoch": 3.76, "learning_rate": 9.271754014689407e-06, "loss": 0.0684, "step": 30250 }, { "epoch": 3.76, "learning_rate": 9.271505041702976e-06, "loss": 0.0558, "step": 30260 }, { "epoch": 3.76, "learning_rate": 9.271256068716546e-06, "loss": 0.0701, "step": 30270 }, { "epoch": 3.76, "learning_rate": 9.271007095730114e-06, "loss": 0.0671, "step": 30280 }, { "epoch": 3.76, "learning_rate": 9.270758122743683e-06, "loss": 0.0499, "step": 30290 }, { "epoch": 3.76, "learning_rate": 9.270509149757251e-06, "loss": 0.0637, "step": 30300 }, { "epoch": 3.76, "learning_rate": 9.270260176770822e-06, "loss": 0.0812, "step": 30310 }, { "epoch": 3.77, "learning_rate": 9.27001120378439e-06, "loss": 0.0838, "step": 30320 }, { "epoch": 3.77, "learning_rate": 9.26976223079796e-06, "loss": 0.0762, "step": 30330 }, { "epoch": 3.77, "learning_rate": 9.269513257811527e-06, "loss": 0.0708, "step": 30340 }, { "epoch": 3.77, "learning_rate": 9.269264284825097e-06, "loss": 0.042, "step": 30350 }, { "epoch": 3.77, "learning_rate": 9.269015311838666e-06, "loss": 0.0511, "step": 30360 }, { "epoch": 3.77, "learning_rate": 9.268766338852236e-06, "loss": 0.0909, "step": 30370 }, { "epoch": 3.77, "learning_rate": 9.268517365865805e-06, "loss": 0.046, "step": 30380 }, { "epoch": 3.77, "learning_rate": 9.268268392879373e-06, "loss": 0.0599, "step": 30390 }, { "epoch": 3.77, "learning_rate": 9.268019419892942e-06, "loss": 0.0496, "step": 30400 }, { "epoch": 3.78, "learning_rate": 9.267770446906512e-06, "loss": 0.0487, "step": 30410 }, { "epoch": 3.78, "learning_rate": 9.26752147392008e-06, "loss": 0.0652, "step": 30420 }, { "epoch": 3.78, "learning_rate": 9.267272500933649e-06, "loss": 0.0495, "step": 30430 }, { "epoch": 3.78, "learning_rate": 9.267023527947219e-06, "loss": 0.0545, "step": 30440 }, { "epoch": 3.78, "learning_rate": 9.266774554960788e-06, "loss": 0.0662, "step": 30450 }, { "epoch": 3.78, "learning_rate": 9.266525581974356e-06, "loss": 0.0418, "step": 30460 }, { "epoch": 3.78, "learning_rate": 9.266276608987925e-06, "loss": 0.0455, "step": 30470 }, { "epoch": 3.78, "learning_rate": 9.266027636001495e-06, "loss": 0.0704, "step": 30480 }, { "epoch": 3.79, "learning_rate": 9.265778663015063e-06, "loss": 0.0572, "step": 30490 }, { "epoch": 3.79, "learning_rate": 9.265529690028633e-06, "loss": 0.0534, "step": 30500 }, { "epoch": 3.79, "learning_rate": 9.265280717042202e-06, "loss": 0.0518, "step": 30510 }, { "epoch": 3.79, "learning_rate": 9.26503174405577e-06, "loss": 0.0574, "step": 30520 }, { "epoch": 3.79, "learning_rate": 9.264782771069339e-06, "loss": 0.0568, "step": 30530 }, { "epoch": 3.79, "learning_rate": 9.26453379808291e-06, "loss": 0.07, "step": 30540 }, { "epoch": 3.79, "learning_rate": 9.264284825096478e-06, "loss": 0.0627, "step": 30550 }, { "epoch": 3.79, "learning_rate": 9.264035852110046e-06, "loss": 0.0587, "step": 30560 }, { "epoch": 3.8, "learning_rate": 9.263786879123616e-06, "loss": 0.0607, "step": 30570 }, { "epoch": 3.8, "learning_rate": 9.263537906137185e-06, "loss": 0.096, "step": 30580 }, { "epoch": 3.8, "learning_rate": 9.263288933150754e-06, "loss": 0.0648, "step": 30590 }, { "epoch": 3.8, "learning_rate": 9.263039960164322e-06, "loss": 0.0282, "step": 30600 }, { "epoch": 3.8, "learning_rate": 9.262790987177892e-06, "loss": 0.0604, "step": 30610 }, { "epoch": 3.8, "learning_rate": 9.26254201419146e-06, "loss": 0.056, "step": 30620 }, { "epoch": 3.8, "learning_rate": 9.262293041205031e-06, "loss": 0.054, "step": 30630 }, { "epoch": 3.8, "learning_rate": 9.262044068218598e-06, "loss": 0.0855, "step": 30640 }, { "epoch": 3.81, "learning_rate": 9.261795095232168e-06, "loss": 0.0676, "step": 30650 }, { "epoch": 3.81, "learning_rate": 9.261546122245737e-06, "loss": 0.0409, "step": 30660 }, { "epoch": 3.81, "learning_rate": 9.261297149259307e-06, "loss": 0.0805, "step": 30670 }, { "epoch": 3.81, "learning_rate": 9.261048176272875e-06, "loss": 0.0846, "step": 30680 }, { "epoch": 3.81, "learning_rate": 9.260799203286445e-06, "loss": 0.0497, "step": 30690 }, { "epoch": 3.81, "learning_rate": 9.260550230300012e-06, "loss": 0.0528, "step": 30700 }, { "epoch": 3.81, "learning_rate": 9.260301257313582e-06, "loss": 0.0652, "step": 30710 }, { "epoch": 3.81, "learning_rate": 9.260052284327151e-06, "loss": 0.0536, "step": 30720 }, { "epoch": 3.82, "learning_rate": 9.259803311340721e-06, "loss": 0.0628, "step": 30730 }, { "epoch": 3.82, "learning_rate": 9.25955433835429e-06, "loss": 0.0709, "step": 30740 }, { "epoch": 3.82, "learning_rate": 9.259305365367858e-06, "loss": 0.0548, "step": 30750 }, { "epoch": 3.82, "learning_rate": 9.259056392381427e-06, "loss": 0.0573, "step": 30760 }, { "epoch": 3.82, "learning_rate": 9.258807419394997e-06, "loss": 0.0567, "step": 30770 }, { "epoch": 3.82, "learning_rate": 9.258558446408565e-06, "loss": 0.0662, "step": 30780 }, { "epoch": 3.82, "learning_rate": 9.258309473422134e-06, "loss": 0.0401, "step": 30790 }, { "epoch": 3.82, "learning_rate": 9.258060500435704e-06, "loss": 0.0562, "step": 30800 }, { "epoch": 3.83, "learning_rate": 9.257811527449273e-06, "loss": 0.0381, "step": 30810 }, { "epoch": 3.83, "learning_rate": 9.257562554462841e-06, "loss": 0.0828, "step": 30820 }, { "epoch": 3.83, "learning_rate": 9.25731358147641e-06, "loss": 0.079, "step": 30830 }, { "epoch": 3.83, "learning_rate": 9.25706460848998e-06, "loss": 0.0662, "step": 30840 }, { "epoch": 3.83, "learning_rate": 9.256815635503548e-06, "loss": 0.0365, "step": 30850 }, { "epoch": 3.83, "learning_rate": 9.256566662517119e-06, "loss": 0.0501, "step": 30860 }, { "epoch": 3.83, "learning_rate": 9.256317689530687e-06, "loss": 0.0592, "step": 30870 }, { "epoch": 3.83, "learning_rate": 9.256068716544256e-06, "loss": 0.0649, "step": 30880 }, { "epoch": 3.84, "learning_rate": 9.255819743557824e-06, "loss": 0.0511, "step": 30890 }, { "epoch": 3.84, "learning_rate": 9.255570770571394e-06, "loss": 0.0689, "step": 30900 }, { "epoch": 3.84, "learning_rate": 9.255321797584963e-06, "loss": 0.0639, "step": 30910 }, { "epoch": 3.84, "learning_rate": 9.255072824598531e-06, "loss": 0.0734, "step": 30920 }, { "epoch": 3.84, "learning_rate": 9.254823851612102e-06, "loss": 0.0559, "step": 30930 }, { "epoch": 3.84, "learning_rate": 9.25457487862567e-06, "loss": 0.0654, "step": 30940 }, { "epoch": 3.84, "learning_rate": 9.254325905639239e-06, "loss": 0.0521, "step": 30950 }, { "epoch": 3.84, "learning_rate": 9.254076932652807e-06, "loss": 0.0573, "step": 30960 }, { "epoch": 3.85, "learning_rate": 9.253827959666377e-06, "loss": 0.0638, "step": 30970 }, { "epoch": 3.85, "learning_rate": 9.253578986679946e-06, "loss": 0.0407, "step": 30980 }, { "epoch": 3.85, "learning_rate": 9.253330013693514e-06, "loss": 0.0739, "step": 30990 }, { "epoch": 3.85, "learning_rate": 9.253081040707083e-06, "loss": 0.0515, "step": 31000 }, { "epoch": 3.85, "learning_rate": 9.252832067720653e-06, "loss": 0.0398, "step": 31010 }, { "epoch": 3.85, "learning_rate": 9.252583094734222e-06, "loss": 0.0995, "step": 31020 }, { "epoch": 3.85, "learning_rate": 9.252334121747792e-06, "loss": 0.0518, "step": 31030 }, { "epoch": 3.85, "learning_rate": 9.25208514876136e-06, "loss": 0.0599, "step": 31040 }, { "epoch": 3.86, "learning_rate": 9.251836175774929e-06, "loss": 0.0412, "step": 31050 }, { "epoch": 3.86, "learning_rate": 9.251587202788497e-06, "loss": 0.0577, "step": 31060 }, { "epoch": 3.86, "learning_rate": 9.251338229802068e-06, "loss": 0.0792, "step": 31070 }, { "epoch": 3.86, "learning_rate": 9.251089256815636e-06, "loss": 0.0667, "step": 31080 }, { "epoch": 3.86, "learning_rate": 9.250840283829205e-06, "loss": 0.0338, "step": 31090 }, { "epoch": 3.86, "learning_rate": 9.250591310842775e-06, "loss": 0.0473, "step": 31100 }, { "epoch": 3.86, "learning_rate": 9.250342337856343e-06, "loss": 0.0787, "step": 31110 }, { "epoch": 3.86, "learning_rate": 9.250093364869912e-06, "loss": 0.0761, "step": 31120 }, { "epoch": 3.87, "learning_rate": 9.24984439188348e-06, "loss": 0.0642, "step": 31130 }, { "epoch": 3.87, "learning_rate": 9.24959541889705e-06, "loss": 0.0562, "step": 31140 }, { "epoch": 3.87, "learning_rate": 9.24934644591062e-06, "loss": 0.0593, "step": 31150 }, { "epoch": 3.87, "learning_rate": 9.24909747292419e-06, "loss": 0.0663, "step": 31160 }, { "epoch": 3.87, "learning_rate": 9.248848499937756e-06, "loss": 0.0431, "step": 31170 }, { "epoch": 3.87, "learning_rate": 9.248599526951326e-06, "loss": 0.0629, "step": 31180 }, { "epoch": 3.87, "learning_rate": 9.248350553964895e-06, "loss": 0.0618, "step": 31190 }, { "epoch": 3.87, "learning_rate": 9.248101580978465e-06, "loss": 0.0471, "step": 31200 }, { "epoch": 3.88, "learning_rate": 9.247852607992034e-06, "loss": 0.0498, "step": 31210 }, { "epoch": 3.88, "learning_rate": 9.247603635005604e-06, "loss": 0.0574, "step": 31220 }, { "epoch": 3.88, "learning_rate": 9.24735466201917e-06, "loss": 0.0718, "step": 31230 }, { "epoch": 3.88, "learning_rate": 9.247105689032741e-06, "loss": 0.0448, "step": 31240 }, { "epoch": 3.88, "learning_rate": 9.24685671604631e-06, "loss": 0.0625, "step": 31250 }, { "epoch": 3.88, "learning_rate": 9.24660774305988e-06, "loss": 0.078, "step": 31260 }, { "epoch": 3.88, "learning_rate": 9.246358770073448e-06, "loss": 0.097, "step": 31270 }, { "epoch": 3.88, "learning_rate": 9.246109797087017e-06, "loss": 0.0612, "step": 31280 }, { "epoch": 3.89, "learning_rate": 9.245860824100585e-06, "loss": 0.0632, "step": 31290 }, { "epoch": 3.89, "learning_rate": 9.245611851114155e-06, "loss": 0.039, "step": 31300 }, { "epoch": 3.89, "learning_rate": 9.245362878127724e-06, "loss": 0.0317, "step": 31310 }, { "epoch": 3.89, "learning_rate": 9.245113905141292e-06, "loss": 0.0712, "step": 31320 }, { "epoch": 3.89, "learning_rate": 9.244864932154863e-06, "loss": 0.0591, "step": 31330 }, { "epoch": 3.89, "learning_rate": 9.244615959168431e-06, "loss": 0.0409, "step": 31340 }, { "epoch": 3.89, "learning_rate": 9.244366986182e-06, "loss": 0.0407, "step": 31350 }, { "epoch": 3.89, "learning_rate": 9.244118013195568e-06, "loss": 0.0489, "step": 31360 }, { "epoch": 3.9, "learning_rate": 9.243869040209138e-06, "loss": 0.0719, "step": 31370 }, { "epoch": 3.9, "learning_rate": 9.243620067222707e-06, "loss": 0.0856, "step": 31380 }, { "epoch": 3.9, "learning_rate": 9.243371094236277e-06, "loss": 0.0447, "step": 31390 }, { "epoch": 3.9, "learning_rate": 9.243122121249846e-06, "loss": 0.0609, "step": 31400 }, { "epoch": 3.9, "learning_rate": 9.242873148263414e-06, "loss": 0.1003, "step": 31410 }, { "epoch": 3.9, "learning_rate": 9.242624175276983e-06, "loss": 0.0725, "step": 31420 }, { "epoch": 3.9, "learning_rate": 9.242375202290553e-06, "loss": 0.0522, "step": 31430 }, { "epoch": 3.9, "learning_rate": 9.242126229304121e-06, "loss": 0.0366, "step": 31440 }, { "epoch": 3.91, "learning_rate": 9.24187725631769e-06, "loss": 0.0363, "step": 31450 }, { "epoch": 3.91, "learning_rate": 9.24162828333126e-06, "loss": 0.0717, "step": 31460 }, { "epoch": 3.91, "learning_rate": 9.241379310344829e-06, "loss": 0.0741, "step": 31470 }, { "epoch": 3.91, "learning_rate": 9.241130337358397e-06, "loss": 0.0679, "step": 31480 }, { "epoch": 3.91, "learning_rate": 9.240881364371966e-06, "loss": 0.0608, "step": 31490 }, { "epoch": 3.91, "learning_rate": 9.240632391385536e-06, "loss": 0.0671, "step": 31500 }, { "epoch": 3.91, "learning_rate": 9.240383418399104e-06, "loss": 0.0323, "step": 31510 }, { "epoch": 3.91, "learning_rate": 9.240134445412675e-06, "loss": 0.0702, "step": 31520 }, { "epoch": 3.92, "learning_rate": 9.239885472426241e-06, "loss": 0.0899, "step": 31530 }, { "epoch": 3.92, "learning_rate": 9.239636499439812e-06, "loss": 0.0486, "step": 31540 }, { "epoch": 3.92, "learning_rate": 9.23938752645338e-06, "loss": 0.0381, "step": 31550 }, { "epoch": 3.92, "learning_rate": 9.23913855346695e-06, "loss": 0.061, "step": 31560 }, { "epoch": 3.92, "learning_rate": 9.238889580480519e-06, "loss": 0.0683, "step": 31570 }, { "epoch": 3.92, "learning_rate": 9.238640607494087e-06, "loss": 0.0894, "step": 31580 }, { "epoch": 3.92, "learning_rate": 9.238391634507656e-06, "loss": 0.0507, "step": 31590 }, { "epoch": 3.92, "learning_rate": 9.238142661521226e-06, "loss": 0.091, "step": 31600 }, { "epoch": 3.93, "learning_rate": 9.237893688534795e-06, "loss": 0.0662, "step": 31610 }, { "epoch": 3.93, "learning_rate": 9.237644715548363e-06, "loss": 0.1009, "step": 31620 }, { "epoch": 3.93, "learning_rate": 9.237395742561933e-06, "loss": 0.0389, "step": 31630 }, { "epoch": 3.93, "learning_rate": 9.237146769575502e-06, "loss": 0.0736, "step": 31640 }, { "epoch": 3.93, "learning_rate": 9.23689779658907e-06, "loss": 0.0518, "step": 31650 }, { "epoch": 3.93, "learning_rate": 9.236648823602639e-06, "loss": 0.0461, "step": 31660 }, { "epoch": 3.93, "learning_rate": 9.236399850616209e-06, "loss": 0.069, "step": 31670 }, { "epoch": 3.93, "learning_rate": 9.236150877629778e-06, "loss": 0.0659, "step": 31680 }, { "epoch": 3.94, "learning_rate": 9.235901904643348e-06, "loss": 0.0737, "step": 31690 }, { "epoch": 3.94, "learning_rate": 9.235652931656915e-06, "loss": 0.0546, "step": 31700 }, { "epoch": 3.94, "learning_rate": 9.235403958670485e-06, "loss": 0.0657, "step": 31710 }, { "epoch": 3.94, "learning_rate": 9.235154985684053e-06, "loss": 0.0831, "step": 31720 }, { "epoch": 3.94, "learning_rate": 9.234906012697624e-06, "loss": 0.1026, "step": 31730 }, { "epoch": 3.94, "learning_rate": 9.234657039711192e-06, "loss": 0.0789, "step": 31740 }, { "epoch": 3.94, "learning_rate": 9.234408066724762e-06, "loss": 0.0644, "step": 31750 }, { "epoch": 3.94, "learning_rate": 9.23415909373833e-06, "loss": 0.0528, "step": 31760 }, { "epoch": 3.95, "learning_rate": 9.2339101207519e-06, "loss": 0.0809, "step": 31770 }, { "epoch": 3.95, "learning_rate": 9.233661147765468e-06, "loss": 0.0559, "step": 31780 }, { "epoch": 3.95, "learning_rate": 9.233412174779038e-06, "loss": 0.0438, "step": 31790 }, { "epoch": 3.95, "learning_rate": 9.233163201792607e-06, "loss": 0.0525, "step": 31800 }, { "epoch": 3.95, "learning_rate": 9.232914228806175e-06, "loss": 0.053, "step": 31810 }, { "epoch": 3.95, "learning_rate": 9.232665255819744e-06, "loss": 0.0828, "step": 31820 }, { "epoch": 3.95, "learning_rate": 9.232416282833314e-06, "loss": 0.0872, "step": 31830 }, { "epoch": 3.95, "learning_rate": 9.232167309846882e-06, "loss": 0.0641, "step": 31840 }, { "epoch": 3.95, "learning_rate": 9.231918336860451e-06, "loss": 0.0397, "step": 31850 }, { "epoch": 3.96, "learning_rate": 9.231669363874021e-06, "loss": 0.0739, "step": 31860 }, { "epoch": 3.96, "learning_rate": 9.23142039088759e-06, "loss": 0.0745, "step": 31870 }, { "epoch": 3.96, "learning_rate": 9.231171417901158e-06, "loss": 0.09, "step": 31880 }, { "epoch": 3.96, "learning_rate": 9.230922444914727e-06, "loss": 0.0568, "step": 31890 }, { "epoch": 3.96, "learning_rate": 9.230673471928297e-06, "loss": 0.0441, "step": 31900 }, { "epoch": 3.96, "learning_rate": 9.230424498941865e-06, "loss": 0.0623, "step": 31910 }, { "epoch": 3.96, "learning_rate": 9.230175525955436e-06, "loss": 0.0792, "step": 31920 }, { "epoch": 3.96, "learning_rate": 9.229926552969004e-06, "loss": 0.0441, "step": 31930 }, { "epoch": 3.97, "learning_rate": 9.229677579982573e-06, "loss": 0.0524, "step": 31940 }, { "epoch": 3.97, "learning_rate": 9.229428606996141e-06, "loss": 0.0689, "step": 31950 }, { "epoch": 3.97, "learning_rate": 9.229179634009711e-06, "loss": 0.0867, "step": 31960 }, { "epoch": 3.97, "learning_rate": 9.22893066102328e-06, "loss": 0.0777, "step": 31970 }, { "epoch": 3.97, "learning_rate": 9.228681688036848e-06, "loss": 0.095, "step": 31980 }, { "epoch": 3.97, "learning_rate": 9.228432715050419e-06, "loss": 0.0618, "step": 31990 }, { "epoch": 3.97, "learning_rate": 9.228183742063987e-06, "loss": 0.0286, "step": 32000 }, { "epoch": 3.97, "learning_rate": 9.227934769077556e-06, "loss": 0.0421, "step": 32010 }, { "epoch": 3.98, "learning_rate": 9.227685796091124e-06, "loss": 0.0645, "step": 32020 }, { "epoch": 3.98, "learning_rate": 9.227436823104694e-06, "loss": 0.0491, "step": 32030 }, { "epoch": 3.98, "learning_rate": 9.227187850118263e-06, "loss": 0.0557, "step": 32040 }, { "epoch": 3.98, "learning_rate": 9.226938877131833e-06, "loss": 0.0777, "step": 32050 }, { "epoch": 3.98, "learning_rate": 9.2266899041454e-06, "loss": 0.0956, "step": 32060 }, { "epoch": 3.98, "learning_rate": 9.22644093115897e-06, "loss": 0.073, "step": 32070 }, { "epoch": 3.98, "learning_rate": 9.226191958172539e-06, "loss": 0.0612, "step": 32080 }, { "epoch": 3.98, "learning_rate": 9.225942985186109e-06, "loss": 0.0724, "step": 32090 }, { "epoch": 3.99, "learning_rate": 9.225694012199677e-06, "loss": 0.0793, "step": 32100 }, { "epoch": 3.99, "learning_rate": 9.225445039213246e-06, "loss": 0.0684, "step": 32110 }, { "epoch": 3.99, "learning_rate": 9.225196066226814e-06, "loss": 0.0498, "step": 32120 }, { "epoch": 3.99, "learning_rate": 9.224947093240385e-06, "loss": 0.0439, "step": 32130 }, { "epoch": 3.99, "learning_rate": 9.224698120253953e-06, "loss": 0.0548, "step": 32140 }, { "epoch": 3.99, "learning_rate": 9.224449147267522e-06, "loss": 0.0523, "step": 32150 }, { "epoch": 3.99, "learning_rate": 9.224200174281092e-06, "loss": 0.0489, "step": 32160 }, { "epoch": 3.99, "learning_rate": 9.22395120129466e-06, "loss": 0.0721, "step": 32170 }, { "epoch": 4.0, "learning_rate": 9.223702228308229e-06, "loss": 0.0584, "step": 32180 }, { "epoch": 4.0, "learning_rate": 9.223453255321797e-06, "loss": 0.0615, "step": 32190 }, { "epoch": 4.0, "learning_rate": 9.223204282335368e-06, "loss": 0.0538, "step": 32200 }, { "epoch": 4.0, "learning_rate": 9.222955309348936e-06, "loss": 0.0714, "step": 32210 }, { "epoch": 4.0, "learning_rate": 9.222706336362506e-06, "loss": 0.0678, "step": 32220 }, { "epoch": 4.0, "learning_rate": 9.222457363376075e-06, "loss": 0.044, "step": 32230 }, { "epoch": 4.0, "learning_rate": 9.222208390389643e-06, "loss": 0.0571, "step": 32240 }, { "epoch": 4.0, "learning_rate": 9.221959417403212e-06, "loss": 0.0471, "step": 32250 }, { "epoch": 4.01, "learning_rate": 9.221710444416782e-06, "loss": 0.0621, "step": 32260 }, { "epoch": 4.01, "learning_rate": 9.22146147143035e-06, "loss": 0.0791, "step": 32270 }, { "epoch": 4.01, "learning_rate": 9.22121249844392e-06, "loss": 0.0509, "step": 32280 }, { "epoch": 4.01, "learning_rate": 9.220963525457488e-06, "loss": 0.0457, "step": 32290 }, { "epoch": 4.01, "learning_rate": 9.220714552471058e-06, "loss": 0.0463, "step": 32300 }, { "epoch": 4.01, "learning_rate": 9.220465579484626e-06, "loss": 0.0584, "step": 32310 }, { "epoch": 4.01, "learning_rate": 9.220216606498197e-06, "loss": 0.0563, "step": 32320 }, { "epoch": 4.01, "learning_rate": 9.219967633511765e-06, "loss": 0.0877, "step": 32330 }, { "epoch": 4.02, "learning_rate": 9.219718660525334e-06, "loss": 0.0574, "step": 32340 }, { "epoch": 4.02, "learning_rate": 9.219469687538902e-06, "loss": 0.0416, "step": 32350 }, { "epoch": 4.02, "learning_rate": 9.219220714552472e-06, "loss": 0.0673, "step": 32360 }, { "epoch": 4.02, "learning_rate": 9.21897174156604e-06, "loss": 0.0627, "step": 32370 }, { "epoch": 4.02, "learning_rate": 9.21872276857961e-06, "loss": 0.0656, "step": 32380 }, { "epoch": 4.02, "learning_rate": 9.21847379559318e-06, "loss": 0.0477, "step": 32390 }, { "epoch": 4.02, "learning_rate": 9.218224822606748e-06, "loss": 0.0668, "step": 32400 }, { "epoch": 4.02, "learning_rate": 9.217975849620317e-06, "loss": 0.0485, "step": 32410 }, { "epoch": 4.03, "learning_rate": 9.217726876633885e-06, "loss": 0.0762, "step": 32420 }, { "epoch": 4.03, "learning_rate": 9.217477903647455e-06, "loss": 0.0842, "step": 32430 }, { "epoch": 4.03, "learning_rate": 9.217228930661024e-06, "loss": 0.0478, "step": 32440 }, { "epoch": 4.03, "learning_rate": 9.216979957674594e-06, "loss": 0.0406, "step": 32450 }, { "epoch": 4.03, "learning_rate": 9.216730984688163e-06, "loss": 0.0677, "step": 32460 }, { "epoch": 4.03, "learning_rate": 9.216482011701731e-06, "loss": 0.0571, "step": 32470 }, { "epoch": 4.03, "learning_rate": 9.2162330387153e-06, "loss": 0.0572, "step": 32480 }, { "epoch": 4.03, "learning_rate": 9.21598406572887e-06, "loss": 0.0564, "step": 32490 }, { "epoch": 4.04, "learning_rate": 9.215735092742438e-06, "loss": 0.0508, "step": 32500 }, { "epoch": 4.04, "learning_rate": 9.215486119756007e-06, "loss": 0.044, "step": 32510 }, { "epoch": 4.04, "learning_rate": 9.215237146769577e-06, "loss": 0.0621, "step": 32520 }, { "epoch": 4.04, "learning_rate": 9.214988173783146e-06, "loss": 0.0349, "step": 32530 }, { "epoch": 4.04, "learning_rate": 9.214739200796714e-06, "loss": 0.0493, "step": 32540 }, { "epoch": 4.04, "learning_rate": 9.214490227810283e-06, "loss": 0.0471, "step": 32550 }, { "epoch": 4.04, "learning_rate": 9.214241254823853e-06, "loss": 0.0343, "step": 32560 }, { "epoch": 4.04, "learning_rate": 9.213992281837421e-06, "loss": 0.0654, "step": 32570 }, { "epoch": 4.05, "learning_rate": 9.213743308850992e-06, "loss": 0.071, "step": 32580 }, { "epoch": 4.05, "learning_rate": 9.213494335864558e-06, "loss": 0.0717, "step": 32590 }, { "epoch": 4.05, "learning_rate": 9.213245362878129e-06, "loss": 0.0466, "step": 32600 }, { "epoch": 4.05, "learning_rate": 9.212996389891697e-06, "loss": 0.0443, "step": 32610 }, { "epoch": 4.05, "learning_rate": 9.212747416905267e-06, "loss": 0.0478, "step": 32620 }, { "epoch": 4.05, "learning_rate": 9.212498443918836e-06, "loss": 0.0567, "step": 32630 }, { "epoch": 4.05, "learning_rate": 9.212249470932404e-06, "loss": 0.1062, "step": 32640 }, { "epoch": 4.05, "learning_rate": 9.212000497945973e-06, "loss": 0.0631, "step": 32650 }, { "epoch": 4.06, "learning_rate": 9.211751524959543e-06, "loss": 0.041, "step": 32660 }, { "epoch": 4.06, "learning_rate": 9.211502551973112e-06, "loss": 0.0862, "step": 32670 }, { "epoch": 4.06, "learning_rate": 9.21125357898668e-06, "loss": 0.0804, "step": 32680 }, { "epoch": 4.06, "learning_rate": 9.21100460600025e-06, "loss": 0.0502, "step": 32690 }, { "epoch": 4.06, "learning_rate": 9.210755633013819e-06, "loss": 0.0585, "step": 32700 }, { "epoch": 4.06, "learning_rate": 9.210506660027387e-06, "loss": 0.0721, "step": 32710 }, { "epoch": 4.06, "learning_rate": 9.210257687040956e-06, "loss": 0.0574, "step": 32720 }, { "epoch": 4.06, "learning_rate": 9.210008714054526e-06, "loss": 0.0382, "step": 32730 }, { "epoch": 4.07, "learning_rate": 9.209759741068095e-06, "loss": 0.0529, "step": 32740 }, { "epoch": 4.07, "learning_rate": 9.209510768081665e-06, "loss": 0.063, "step": 32750 }, { "epoch": 4.07, "learning_rate": 9.209261795095233e-06, "loss": 0.0406, "step": 32760 }, { "epoch": 4.07, "learning_rate": 9.209012822108802e-06, "loss": 0.0765, "step": 32770 }, { "epoch": 4.07, "learning_rate": 9.20876384912237e-06, "loss": 0.0602, "step": 32780 }, { "epoch": 4.07, "learning_rate": 9.20851487613594e-06, "loss": 0.0497, "step": 32790 }, { "epoch": 4.07, "learning_rate": 9.208265903149509e-06, "loss": 0.037, "step": 32800 }, { "epoch": 4.07, "learning_rate": 9.20801693016308e-06, "loss": 0.0396, "step": 32810 }, { "epoch": 4.08, "learning_rate": 9.207767957176648e-06, "loss": 0.0739, "step": 32820 }, { "epoch": 4.08, "learning_rate": 9.207518984190216e-06, "loss": 0.071, "step": 32830 }, { "epoch": 4.08, "learning_rate": 9.207270011203785e-06, "loss": 0.0598, "step": 32840 }, { "epoch": 4.08, "learning_rate": 9.207021038217355e-06, "loss": 0.0523, "step": 32850 }, { "epoch": 4.08, "learning_rate": 9.206772065230924e-06, "loss": 0.0833, "step": 32860 }, { "epoch": 4.08, "learning_rate": 9.206523092244492e-06, "loss": 0.0522, "step": 32870 }, { "epoch": 4.08, "learning_rate": 9.206274119258062e-06, "loss": 0.0613, "step": 32880 }, { "epoch": 4.08, "learning_rate": 9.20602514627163e-06, "loss": 0.0516, "step": 32890 }, { "epoch": 4.09, "learning_rate": 9.2057761732852e-06, "loss": 0.0684, "step": 32900 }, { "epoch": 4.09, "learning_rate": 9.205527200298768e-06, "loss": 0.0382, "step": 32910 }, { "epoch": 4.09, "learning_rate": 9.205278227312338e-06, "loss": 0.0662, "step": 32920 }, { "epoch": 4.09, "learning_rate": 9.205029254325907e-06, "loss": 0.073, "step": 32930 }, { "epoch": 4.09, "learning_rate": 9.204780281339475e-06, "loss": 0.0572, "step": 32940 }, { "epoch": 4.09, "learning_rate": 9.204531308353044e-06, "loss": 0.0938, "step": 32950 }, { "epoch": 4.09, "learning_rate": 9.204282335366614e-06, "loss": 0.0459, "step": 32960 }, { "epoch": 4.09, "learning_rate": 9.204033362380182e-06, "loss": 0.0617, "step": 32970 }, { "epoch": 4.1, "learning_rate": 9.203784389393752e-06, "loss": 0.0538, "step": 32980 }, { "epoch": 4.1, "learning_rate": 9.203535416407321e-06, "loss": 0.0567, "step": 32990 }, { "epoch": 4.1, "learning_rate": 9.20328644342089e-06, "loss": 0.0505, "step": 33000 }, { "epoch": 4.1, "learning_rate": 9.203037470434458e-06, "loss": 0.0718, "step": 33010 }, { "epoch": 4.1, "learning_rate": 9.202788497448028e-06, "loss": 0.0733, "step": 33020 }, { "epoch": 4.1, "learning_rate": 9.202539524461597e-06, "loss": 0.0504, "step": 33030 }, { "epoch": 4.1, "learning_rate": 9.202290551475165e-06, "loss": 0.0466, "step": 33040 }, { "epoch": 4.1, "learning_rate": 9.202041578488735e-06, "loss": 0.0397, "step": 33050 }, { "epoch": 4.11, "learning_rate": 9.201792605502304e-06, "loss": 0.0606, "step": 33060 }, { "epoch": 4.11, "learning_rate": 9.201543632515872e-06, "loss": 0.059, "step": 33070 }, { "epoch": 4.11, "learning_rate": 9.201294659529441e-06, "loss": 0.0475, "step": 33080 }, { "epoch": 4.11, "learning_rate": 9.201045686543011e-06, "loss": 0.0651, "step": 33090 }, { "epoch": 4.11, "learning_rate": 9.20079671355658e-06, "loss": 0.0836, "step": 33100 }, { "epoch": 4.11, "learning_rate": 9.20054774057015e-06, "loss": 0.0332, "step": 33110 }, { "epoch": 4.11, "learning_rate": 9.200298767583717e-06, "loss": 0.0772, "step": 33120 }, { "epoch": 4.11, "learning_rate": 9.200049794597287e-06, "loss": 0.0433, "step": 33130 }, { "epoch": 4.12, "learning_rate": 9.199800821610855e-06, "loss": 0.0448, "step": 33140 }, { "epoch": 4.12, "learning_rate": 9.199551848624426e-06, "loss": 0.0712, "step": 33150 }, { "epoch": 4.12, "learning_rate": 9.199302875637994e-06, "loss": 0.0532, "step": 33160 }, { "epoch": 4.12, "learning_rate": 9.199053902651563e-06, "loss": 0.0589, "step": 33170 }, { "epoch": 4.12, "learning_rate": 9.198804929665131e-06, "loss": 0.0821, "step": 33180 }, { "epoch": 4.12, "learning_rate": 9.198555956678701e-06, "loss": 0.0461, "step": 33190 }, { "epoch": 4.12, "learning_rate": 9.19830698369227e-06, "loss": 0.0702, "step": 33200 }, { "epoch": 4.12, "learning_rate": 9.198058010705838e-06, "loss": 0.0691, "step": 33210 }, { "epoch": 4.13, "learning_rate": 9.197809037719409e-06, "loss": 0.042, "step": 33220 }, { "epoch": 4.13, "learning_rate": 9.197560064732977e-06, "loss": 0.0559, "step": 33230 }, { "epoch": 4.13, "learning_rate": 9.197311091746546e-06, "loss": 0.0533, "step": 33240 }, { "epoch": 4.13, "learning_rate": 9.197062118760114e-06, "loss": 0.0454, "step": 33250 }, { "epoch": 4.13, "learning_rate": 9.196813145773684e-06, "loss": 0.0458, "step": 33260 }, { "epoch": 4.13, "learning_rate": 9.196564172787253e-06, "loss": 0.059, "step": 33270 }, { "epoch": 4.13, "learning_rate": 9.196315199800823e-06, "loss": 0.0932, "step": 33280 }, { "epoch": 4.13, "learning_rate": 9.196066226814392e-06, "loss": 0.0709, "step": 33290 }, { "epoch": 4.14, "learning_rate": 9.19581725382796e-06, "loss": 0.0377, "step": 33300 }, { "epoch": 4.14, "learning_rate": 9.195568280841529e-06, "loss": 0.0516, "step": 33310 }, { "epoch": 4.14, "learning_rate": 9.195319307855099e-06, "loss": 0.0773, "step": 33320 }, { "epoch": 4.14, "learning_rate": 9.195070334868667e-06, "loss": 0.0523, "step": 33330 }, { "epoch": 4.14, "learning_rate": 9.194821361882238e-06, "loss": 0.0492, "step": 33340 }, { "epoch": 4.14, "learning_rate": 9.194572388895806e-06, "loss": 0.0445, "step": 33350 }, { "epoch": 4.14, "learning_rate": 9.194323415909375e-06, "loss": 0.0605, "step": 33360 }, { "epoch": 4.14, "learning_rate": 9.194074442922943e-06, "loss": 0.0693, "step": 33370 }, { "epoch": 4.15, "learning_rate": 9.193825469936513e-06, "loss": 0.0696, "step": 33380 }, { "epoch": 4.15, "learning_rate": 9.193576496950082e-06, "loss": 0.0738, "step": 33390 }, { "epoch": 4.15, "learning_rate": 9.19332752396365e-06, "loss": 0.0543, "step": 33400 }, { "epoch": 4.15, "learning_rate": 9.19307855097722e-06, "loss": 0.0411, "step": 33410 }, { "epoch": 4.15, "learning_rate": 9.19282957799079e-06, "loss": 0.0573, "step": 33420 }, { "epoch": 4.15, "learning_rate": 9.192580605004358e-06, "loss": 0.0861, "step": 33430 }, { "epoch": 4.15, "learning_rate": 9.192331632017926e-06, "loss": 0.0551, "step": 33440 }, { "epoch": 4.15, "learning_rate": 9.192082659031496e-06, "loss": 0.0393, "step": 33450 }, { "epoch": 4.15, "learning_rate": 9.191833686045065e-06, "loss": 0.0439, "step": 33460 }, { "epoch": 4.16, "learning_rate": 9.191584713058635e-06, "loss": 0.0455, "step": 33470 }, { "epoch": 4.16, "learning_rate": 9.191335740072202e-06, "loss": 0.0562, "step": 33480 }, { "epoch": 4.16, "learning_rate": 9.191086767085772e-06, "loss": 0.0449, "step": 33490 }, { "epoch": 4.16, "learning_rate": 9.19083779409934e-06, "loss": 0.0378, "step": 33500 }, { "epoch": 4.16, "learning_rate": 9.190588821112911e-06, "loss": 0.047, "step": 33510 }, { "epoch": 4.16, "learning_rate": 9.19033984812648e-06, "loss": 0.0689, "step": 33520 }, { "epoch": 4.16, "learning_rate": 9.190090875140048e-06, "loss": 0.0694, "step": 33530 }, { "epoch": 4.16, "learning_rate": 9.189841902153616e-06, "loss": 0.0433, "step": 33540 }, { "epoch": 4.17, "learning_rate": 9.189592929167187e-06, "loss": 0.0429, "step": 33550 }, { "epoch": 4.17, "learning_rate": 9.189343956180755e-06, "loss": 0.0716, "step": 33560 }, { "epoch": 4.17, "learning_rate": 9.189094983194324e-06, "loss": 0.0581, "step": 33570 }, { "epoch": 4.17, "learning_rate": 9.188846010207894e-06, "loss": 0.0486, "step": 33580 }, { "epoch": 4.17, "learning_rate": 9.188597037221462e-06, "loss": 0.0575, "step": 33590 }, { "epoch": 4.17, "learning_rate": 9.188348064235031e-06, "loss": 0.0582, "step": 33600 }, { "epoch": 4.17, "learning_rate": 9.1880990912486e-06, "loss": 0.0697, "step": 33610 }, { "epoch": 4.17, "learning_rate": 9.18785011826217e-06, "loss": 0.0649, "step": 33620 }, { "epoch": 4.18, "learning_rate": 9.187601145275738e-06, "loss": 0.051, "step": 33630 }, { "epoch": 4.18, "learning_rate": 9.187352172289308e-06, "loss": 0.0499, "step": 33640 }, { "epoch": 4.18, "learning_rate": 9.187103199302875e-06, "loss": 0.0763, "step": 33650 }, { "epoch": 4.18, "learning_rate": 9.186854226316445e-06, "loss": 0.0509, "step": 33660 }, { "epoch": 4.18, "learning_rate": 9.186605253330014e-06, "loss": 0.064, "step": 33670 }, { "epoch": 4.18, "learning_rate": 9.186356280343584e-06, "loss": 0.0452, "step": 33680 }, { "epoch": 4.18, "learning_rate": 9.186107307357153e-06, "loss": 0.0512, "step": 33690 }, { "epoch": 4.18, "learning_rate": 9.185858334370721e-06, "loss": 0.0596, "step": 33700 }, { "epoch": 4.19, "learning_rate": 9.18560936138429e-06, "loss": 0.08, "step": 33710 }, { "epoch": 4.19, "learning_rate": 9.18536038839786e-06, "loss": 0.0749, "step": 33720 }, { "epoch": 4.19, "learning_rate": 9.185111415411428e-06, "loss": 0.0595, "step": 33730 }, { "epoch": 4.19, "learning_rate": 9.184862442424997e-06, "loss": 0.0405, "step": 33740 }, { "epoch": 4.19, "learning_rate": 9.184613469438567e-06, "loss": 0.0631, "step": 33750 }, { "epoch": 4.19, "learning_rate": 9.184364496452136e-06, "loss": 0.0506, "step": 33760 }, { "epoch": 4.19, "learning_rate": 9.184115523465704e-06, "loss": 0.069, "step": 33770 }, { "epoch": 4.19, "learning_rate": 9.183866550479273e-06, "loss": 0.0519, "step": 33780 }, { "epoch": 4.2, "learning_rate": 9.183617577492843e-06, "loss": 0.0601, "step": 33790 }, { "epoch": 4.2, "learning_rate": 9.183368604506411e-06, "loss": 0.0622, "step": 33800 }, { "epoch": 4.2, "learning_rate": 9.183119631519982e-06, "loss": 0.0291, "step": 33810 }, { "epoch": 4.2, "learning_rate": 9.18287065853355e-06, "loss": 0.0521, "step": 33820 }, { "epoch": 4.2, "learning_rate": 9.182621685547119e-06, "loss": 0.0635, "step": 33830 }, { "epoch": 4.2, "learning_rate": 9.182372712560687e-06, "loss": 0.0696, "step": 33840 }, { "epoch": 4.2, "learning_rate": 9.182123739574257e-06, "loss": 0.0562, "step": 33850 }, { "epoch": 4.2, "learning_rate": 9.181874766587826e-06, "loss": 0.0518, "step": 33860 }, { "epoch": 4.21, "learning_rate": 9.181625793601396e-06, "loss": 0.0838, "step": 33870 }, { "epoch": 4.21, "learning_rate": 9.181376820614965e-06, "loss": 0.0397, "step": 33880 }, { "epoch": 4.21, "learning_rate": 9.181127847628533e-06, "loss": 0.0512, "step": 33890 }, { "epoch": 4.21, "learning_rate": 9.180878874642102e-06, "loss": 0.0594, "step": 33900 }, { "epoch": 4.21, "learning_rate": 9.180629901655672e-06, "loss": 0.0436, "step": 33910 }, { "epoch": 4.21, "learning_rate": 9.18038092866924e-06, "loss": 0.0445, "step": 33920 }, { "epoch": 4.21, "learning_rate": 9.180131955682809e-06, "loss": 0.0589, "step": 33930 }, { "epoch": 4.21, "learning_rate": 9.179882982696379e-06, "loss": 0.0778, "step": 33940 }, { "epoch": 4.22, "learning_rate": 9.179634009709946e-06, "loss": 0.0462, "step": 33950 }, { "epoch": 4.22, "learning_rate": 9.179385036723516e-06, "loss": 0.0628, "step": 33960 }, { "epoch": 4.22, "learning_rate": 9.179136063737085e-06, "loss": 0.0763, "step": 33970 }, { "epoch": 4.22, "learning_rate": 9.178887090750655e-06, "loss": 0.0521, "step": 33980 }, { "epoch": 4.22, "learning_rate": 9.178638117764223e-06, "loss": 0.0573, "step": 33990 }, { "epoch": 4.22, "learning_rate": 9.178389144777794e-06, "loss": 0.0581, "step": 34000 }, { "epoch": 4.22, "learning_rate": 9.17814017179136e-06, "loss": 0.0334, "step": 34010 }, { "epoch": 4.22, "learning_rate": 9.17789119880493e-06, "loss": 0.0535, "step": 34020 }, { "epoch": 4.23, "learning_rate": 9.177642225818499e-06, "loss": 0.0603, "step": 34030 }, { "epoch": 4.23, "learning_rate": 9.17739325283207e-06, "loss": 0.0669, "step": 34040 }, { "epoch": 4.23, "learning_rate": 9.177144279845638e-06, "loss": 0.055, "step": 34050 }, { "epoch": 4.23, "learning_rate": 9.176895306859206e-06, "loss": 0.0547, "step": 34060 }, { "epoch": 4.23, "learning_rate": 9.176646333872775e-06, "loss": 0.0543, "step": 34070 }, { "epoch": 4.23, "learning_rate": 9.176397360886345e-06, "loss": 0.0465, "step": 34080 }, { "epoch": 4.23, "learning_rate": 9.176148387899914e-06, "loss": 0.0533, "step": 34090 }, { "epoch": 4.23, "learning_rate": 9.175899414913482e-06, "loss": 0.0534, "step": 34100 }, { "epoch": 4.24, "learning_rate": 9.175650441927052e-06, "loss": 0.0391, "step": 34110 }, { "epoch": 4.24, "learning_rate": 9.175401468940621e-06, "loss": 0.0818, "step": 34120 }, { "epoch": 4.24, "learning_rate": 9.17515249595419e-06, "loss": 0.0572, "step": 34130 }, { "epoch": 4.24, "learning_rate": 9.174903522967758e-06, "loss": 0.06, "step": 34140 }, { "epoch": 4.24, "learning_rate": 9.174654549981328e-06, "loss": 0.0695, "step": 34150 }, { "epoch": 4.24, "learning_rate": 9.174405576994897e-06, "loss": 0.0338, "step": 34160 }, { "epoch": 4.24, "learning_rate": 9.174156604008467e-06, "loss": 0.0721, "step": 34170 }, { "epoch": 4.24, "learning_rate": 9.173907631022035e-06, "loss": 0.0693, "step": 34180 }, { "epoch": 4.25, "learning_rate": 9.173658658035604e-06, "loss": 0.0607, "step": 34190 }, { "epoch": 4.25, "learning_rate": 9.173409685049172e-06, "loss": 0.0701, "step": 34200 }, { "epoch": 4.25, "learning_rate": 9.173160712062743e-06, "loss": 0.0547, "step": 34210 }, { "epoch": 4.25, "learning_rate": 9.172911739076311e-06, "loss": 0.0695, "step": 34220 }, { "epoch": 4.25, "learning_rate": 9.17266276608988e-06, "loss": 0.0769, "step": 34230 }, { "epoch": 4.25, "learning_rate": 9.172413793103448e-06, "loss": 0.0614, "step": 34240 }, { "epoch": 4.25, "learning_rate": 9.172164820117018e-06, "loss": 0.0451, "step": 34250 }, { "epoch": 4.25, "learning_rate": 9.171915847130587e-06, "loss": 0.054, "step": 34260 }, { "epoch": 4.26, "learning_rate": 9.171666874144155e-06, "loss": 0.1098, "step": 34270 }, { "epoch": 4.26, "learning_rate": 9.171417901157726e-06, "loss": 0.0651, "step": 34280 }, { "epoch": 4.26, "learning_rate": 9.171168928171294e-06, "loss": 0.0666, "step": 34290 }, { "epoch": 4.26, "learning_rate": 9.170919955184863e-06, "loss": 0.0547, "step": 34300 }, { "epoch": 4.26, "learning_rate": 9.170670982198431e-06, "loss": 0.0456, "step": 34310 }, { "epoch": 4.26, "learning_rate": 9.170422009212001e-06, "loss": 0.053, "step": 34320 }, { "epoch": 4.26, "learning_rate": 9.17017303622557e-06, "loss": 0.0479, "step": 34330 }, { "epoch": 4.26, "learning_rate": 9.16992406323914e-06, "loss": 0.0378, "step": 34340 }, { "epoch": 4.27, "learning_rate": 9.169675090252709e-06, "loss": 0.0696, "step": 34350 }, { "epoch": 4.27, "learning_rate": 9.169426117266277e-06, "loss": 0.0401, "step": 34360 }, { "epoch": 4.27, "learning_rate": 9.169177144279846e-06, "loss": 0.0693, "step": 34370 }, { "epoch": 4.27, "learning_rate": 9.168928171293416e-06, "loss": 0.0541, "step": 34380 }, { "epoch": 4.27, "learning_rate": 9.168679198306984e-06, "loss": 0.0617, "step": 34390 }, { "epoch": 4.27, "learning_rate": 9.168430225320555e-06, "loss": 0.0346, "step": 34400 }, { "epoch": 4.27, "learning_rate": 9.168181252334123e-06, "loss": 0.0438, "step": 34410 }, { "epoch": 4.27, "learning_rate": 9.167932279347692e-06, "loss": 0.0632, "step": 34420 }, { "epoch": 4.28, "learning_rate": 9.16768330636126e-06, "loss": 0.0641, "step": 34430 }, { "epoch": 4.28, "learning_rate": 9.167434333374829e-06, "loss": 0.0603, "step": 34440 }, { "epoch": 4.28, "learning_rate": 9.167185360388399e-06, "loss": 0.0578, "step": 34450 }, { "epoch": 4.28, "learning_rate": 9.166936387401967e-06, "loss": 0.0383, "step": 34460 }, { "epoch": 4.28, "learning_rate": 9.166687414415538e-06, "loss": 0.0962, "step": 34470 }, { "epoch": 4.28, "learning_rate": 9.166438441429104e-06, "loss": 0.0563, "step": 34480 }, { "epoch": 4.28, "learning_rate": 9.166189468442675e-06, "loss": 0.0524, "step": 34490 }, { "epoch": 4.28, "learning_rate": 9.165940495456243e-06, "loss": 0.0424, "step": 34500 }, { "epoch": 4.29, "learning_rate": 9.165691522469813e-06, "loss": 0.0442, "step": 34510 }, { "epoch": 4.29, "learning_rate": 9.165442549483382e-06, "loss": 0.0785, "step": 34520 }, { "epoch": 4.29, "learning_rate": 9.165193576496952e-06, "loss": 0.059, "step": 34530 }, { "epoch": 4.29, "learning_rate": 9.164944603510519e-06, "loss": 0.0813, "step": 34540 }, { "epoch": 4.29, "learning_rate": 9.164695630524089e-06, "loss": 0.0735, "step": 34550 }, { "epoch": 4.29, "learning_rate": 9.164446657537658e-06, "loss": 0.0648, "step": 34560 }, { "epoch": 4.29, "learning_rate": 9.164197684551228e-06, "loss": 0.0844, "step": 34570 }, { "epoch": 4.29, "learning_rate": 9.163948711564796e-06, "loss": 0.0685, "step": 34580 }, { "epoch": 4.3, "learning_rate": 9.163699738578365e-06, "loss": 0.0869, "step": 34590 }, { "epoch": 4.3, "learning_rate": 9.163450765591933e-06, "loss": 0.0529, "step": 34600 }, { "epoch": 4.3, "learning_rate": 9.163201792605504e-06, "loss": 0.0499, "step": 34610 }, { "epoch": 4.3, "learning_rate": 9.162952819619072e-06, "loss": 0.0654, "step": 34620 }, { "epoch": 4.3, "learning_rate": 9.16270384663264e-06, "loss": 0.064, "step": 34630 }, { "epoch": 4.3, "learning_rate": 9.16245487364621e-06, "loss": 0.0469, "step": 34640 }, { "epoch": 4.3, "learning_rate": 9.16220590065978e-06, "loss": 0.0561, "step": 34650 }, { "epoch": 4.3, "learning_rate": 9.161956927673348e-06, "loss": 0.0444, "step": 34660 }, { "epoch": 4.31, "learning_rate": 9.161707954686916e-06, "loss": 0.0568, "step": 34670 }, { "epoch": 4.31, "learning_rate": 9.161458981700487e-06, "loss": 0.0472, "step": 34680 }, { "epoch": 4.31, "learning_rate": 9.161210008714055e-06, "loss": 0.0554, "step": 34690 }, { "epoch": 4.31, "learning_rate": 9.160961035727625e-06, "loss": 0.0608, "step": 34700 }, { "epoch": 4.31, "learning_rate": 9.160712062741194e-06, "loss": 0.0714, "step": 34710 }, { "epoch": 4.31, "learning_rate": 9.160463089754762e-06, "loss": 0.0633, "step": 34720 }, { "epoch": 4.31, "learning_rate": 9.16021411676833e-06, "loss": 0.0848, "step": 34730 }, { "epoch": 4.31, "learning_rate": 9.159965143781901e-06, "loss": 0.0495, "step": 34740 }, { "epoch": 4.32, "learning_rate": 9.15971617079547e-06, "loss": 0.0696, "step": 34750 }, { "epoch": 4.32, "learning_rate": 9.159467197809038e-06, "loss": 0.0754, "step": 34760 }, { "epoch": 4.32, "learning_rate": 9.159218224822608e-06, "loss": 0.0486, "step": 34770 }, { "epoch": 4.32, "learning_rate": 9.158969251836177e-06, "loss": 0.0606, "step": 34780 }, { "epoch": 4.32, "learning_rate": 9.158720278849745e-06, "loss": 0.056, "step": 34790 }, { "epoch": 4.32, "learning_rate": 9.158471305863314e-06, "loss": 0.0463, "step": 34800 }, { "epoch": 4.32, "learning_rate": 9.158222332876884e-06, "loss": 0.0678, "step": 34810 }, { "epoch": 4.32, "learning_rate": 9.157973359890453e-06, "loss": 0.0444, "step": 34820 }, { "epoch": 4.33, "learning_rate": 9.157724386904023e-06, "loss": 0.0722, "step": 34830 }, { "epoch": 4.33, "learning_rate": 9.15747541391759e-06, "loss": 0.0658, "step": 34840 }, { "epoch": 4.33, "learning_rate": 9.15722644093116e-06, "loss": 0.0531, "step": 34850 }, { "epoch": 4.33, "learning_rate": 9.156977467944728e-06, "loss": 0.0812, "step": 34860 }, { "epoch": 4.33, "learning_rate": 9.156728494958299e-06, "loss": 0.0401, "step": 34870 }, { "epoch": 4.33, "learning_rate": 9.156479521971867e-06, "loss": 0.0671, "step": 34880 }, { "epoch": 4.33, "learning_rate": 9.156230548985436e-06, "loss": 0.0672, "step": 34890 }, { "epoch": 4.33, "learning_rate": 9.155981575999004e-06, "loss": 0.0706, "step": 34900 }, { "epoch": 4.34, "learning_rate": 9.155732603012574e-06, "loss": 0.04, "step": 34910 }, { "epoch": 4.34, "learning_rate": 9.155483630026143e-06, "loss": 0.048, "step": 34920 }, { "epoch": 4.34, "learning_rate": 9.155234657039711e-06, "loss": 0.0757, "step": 34930 }, { "epoch": 4.34, "learning_rate": 9.154985684053282e-06, "loss": 0.0586, "step": 34940 }, { "epoch": 4.34, "learning_rate": 9.15473671106685e-06, "loss": 0.0287, "step": 34950 }, { "epoch": 4.34, "learning_rate": 9.154487738080419e-06, "loss": 0.0597, "step": 34960 }, { "epoch": 4.34, "learning_rate": 9.154238765093987e-06, "loss": 0.0476, "step": 34970 }, { "epoch": 4.34, "learning_rate": 9.153989792107557e-06, "loss": 0.0412, "step": 34980 }, { "epoch": 4.34, "learning_rate": 9.153740819121126e-06, "loss": 0.0786, "step": 34990 }, { "epoch": 4.35, "learning_rate": 9.153491846134696e-06, "loss": 0.0657, "step": 35000 }, { "epoch": 4.35, "eval_bleu": 89.2951, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7638, "eval_has_error_f1": 0.6727, "eval_loss": 0.05327245593070984, "eval_runtime": 1365.2901, "eval_samples_per_second": 2.928, "eval_steps_per_second": 0.732, "step": 35000 }, { "epoch": 4.35, "learning_rate": 9.153242873148263e-06, "loss": 0.0501, "step": 35010 }, { "epoch": 4.35, "learning_rate": 9.152993900161833e-06, "loss": 0.0313, "step": 35020 }, { "epoch": 4.35, "learning_rate": 9.152744927175402e-06, "loss": 0.0757, "step": 35030 }, { "epoch": 4.35, "learning_rate": 9.152495954188972e-06, "loss": 0.0768, "step": 35040 }, { "epoch": 4.35, "learning_rate": 9.15224698120254e-06, "loss": 0.0575, "step": 35050 }, { "epoch": 4.35, "learning_rate": 9.15199800821611e-06, "loss": 0.0477, "step": 35060 }, { "epoch": 4.35, "learning_rate": 9.151749035229677e-06, "loss": 0.0661, "step": 35070 }, { "epoch": 4.36, "learning_rate": 9.151500062243248e-06, "loss": 0.0829, "step": 35080 }, { "epoch": 4.36, "learning_rate": 9.151251089256816e-06, "loss": 0.0557, "step": 35090 }, { "epoch": 4.36, "learning_rate": 9.151002116270386e-06, "loss": 0.0378, "step": 35100 }, { "epoch": 4.36, "learning_rate": 9.150753143283955e-06, "loss": 0.0419, "step": 35110 }, { "epoch": 4.36, "learning_rate": 9.150504170297523e-06, "loss": 0.0871, "step": 35120 }, { "epoch": 4.36, "learning_rate": 9.150255197311092e-06, "loss": 0.0815, "step": 35130 }, { "epoch": 4.36, "learning_rate": 9.150006224324662e-06, "loss": 0.0577, "step": 35140 }, { "epoch": 4.36, "learning_rate": 9.14975725133823e-06, "loss": 0.0762, "step": 35150 }, { "epoch": 4.37, "learning_rate": 9.149508278351799e-06, "loss": 0.036, "step": 35160 }, { "epoch": 4.37, "learning_rate": 9.14925930536537e-06, "loss": 0.0822, "step": 35170 }, { "epoch": 4.37, "learning_rate": 9.149010332378938e-06, "loss": 0.038, "step": 35180 }, { "epoch": 4.37, "learning_rate": 9.148761359392506e-06, "loss": 0.0812, "step": 35190 }, { "epoch": 4.37, "learning_rate": 9.148512386406075e-06, "loss": 0.05, "step": 35200 }, { "epoch": 4.37, "learning_rate": 9.148263413419645e-06, "loss": 0.063, "step": 35210 }, { "epoch": 4.37, "learning_rate": 9.148014440433214e-06, "loss": 0.0642, "step": 35220 }, { "epoch": 4.37, "learning_rate": 9.147765467446784e-06, "loss": 0.0628, "step": 35230 }, { "epoch": 4.38, "learning_rate": 9.147516494460352e-06, "loss": 0.083, "step": 35240 }, { "epoch": 4.38, "learning_rate": 9.14726752147392e-06, "loss": 0.0539, "step": 35250 }, { "epoch": 4.38, "learning_rate": 9.14701854848749e-06, "loss": 0.0485, "step": 35260 }, { "epoch": 4.38, "learning_rate": 9.14676957550106e-06, "loss": 0.0609, "step": 35270 }, { "epoch": 4.38, "learning_rate": 9.146520602514628e-06, "loss": 0.0895, "step": 35280 }, { "epoch": 4.38, "learning_rate": 9.146271629528197e-06, "loss": 0.0457, "step": 35290 }, { "epoch": 4.38, "learning_rate": 9.146022656541767e-06, "loss": 0.0459, "step": 35300 }, { "epoch": 4.38, "learning_rate": 9.145773683555335e-06, "loss": 0.0405, "step": 35310 }, { "epoch": 4.39, "learning_rate": 9.145524710568904e-06, "loss": 0.0813, "step": 35320 }, { "epoch": 4.39, "learning_rate": 9.145275737582472e-06, "loss": 0.053, "step": 35330 }, { "epoch": 4.39, "learning_rate": 9.145026764596042e-06, "loss": 0.0546, "step": 35340 }, { "epoch": 4.39, "learning_rate": 9.144777791609611e-06, "loss": 0.034, "step": 35350 }, { "epoch": 4.39, "learning_rate": 9.144528818623181e-06, "loss": 0.0841, "step": 35360 }, { "epoch": 4.39, "learning_rate": 9.144279845636748e-06, "loss": 0.0372, "step": 35370 }, { "epoch": 4.39, "learning_rate": 9.144030872650318e-06, "loss": 0.069, "step": 35380 }, { "epoch": 4.39, "learning_rate": 9.143781899663887e-06, "loss": 0.0562, "step": 35390 }, { "epoch": 4.4, "learning_rate": 9.143532926677457e-06, "loss": 0.0623, "step": 35400 }, { "epoch": 4.4, "learning_rate": 9.143283953691025e-06, "loss": 0.055, "step": 35410 }, { "epoch": 4.4, "learning_rate": 9.143034980704594e-06, "loss": 0.0583, "step": 35420 }, { "epoch": 4.4, "learning_rate": 9.142786007718163e-06, "loss": 0.0344, "step": 35430 }, { "epoch": 4.4, "learning_rate": 9.142537034731733e-06, "loss": 0.0464, "step": 35440 }, { "epoch": 4.4, "learning_rate": 9.142288061745301e-06, "loss": 0.0452, "step": 35450 }, { "epoch": 4.4, "learning_rate": 9.14203908875887e-06, "loss": 0.0344, "step": 35460 }, { "epoch": 4.4, "learning_rate": 9.14179011577244e-06, "loss": 0.0602, "step": 35470 }, { "epoch": 4.41, "learning_rate": 9.141541142786008e-06, "loss": 0.0627, "step": 35480 }, { "epoch": 4.41, "learning_rate": 9.141292169799577e-06, "loss": 0.0845, "step": 35490 }, { "epoch": 4.41, "learning_rate": 9.141043196813146e-06, "loss": 0.0679, "step": 35500 }, { "epoch": 4.41, "learning_rate": 9.140794223826716e-06, "loss": 0.0632, "step": 35510 }, { "epoch": 4.41, "learning_rate": 9.140545250840284e-06, "loss": 0.0447, "step": 35520 }, { "epoch": 4.41, "learning_rate": 9.140296277853854e-06, "loss": 0.0443, "step": 35530 }, { "epoch": 4.41, "learning_rate": 9.140047304867421e-06, "loss": 0.0697, "step": 35540 }, { "epoch": 4.41, "learning_rate": 9.139798331880991e-06, "loss": 0.0448, "step": 35550 }, { "epoch": 4.42, "learning_rate": 9.13954935889456e-06, "loss": 0.0635, "step": 35560 }, { "epoch": 4.42, "learning_rate": 9.13930038590813e-06, "loss": 0.0441, "step": 35570 }, { "epoch": 4.42, "learning_rate": 9.139051412921699e-06, "loss": 0.0381, "step": 35580 }, { "epoch": 4.42, "learning_rate": 9.138802439935269e-06, "loss": 0.073, "step": 35590 }, { "epoch": 4.42, "learning_rate": 9.138553466948836e-06, "loss": 0.08, "step": 35600 }, { "epoch": 4.42, "learning_rate": 9.138304493962406e-06, "loss": 0.0627, "step": 35610 }, { "epoch": 4.42, "learning_rate": 9.138055520975974e-06, "loss": 0.0753, "step": 35620 }, { "epoch": 4.42, "learning_rate": 9.137806547989545e-06, "loss": 0.047, "step": 35630 }, { "epoch": 4.43, "learning_rate": 9.137557575003113e-06, "loss": 0.0684, "step": 35640 }, { "epoch": 4.43, "learning_rate": 9.137308602016682e-06, "loss": 0.056, "step": 35650 }, { "epoch": 4.43, "learning_rate": 9.13705962903025e-06, "loss": 0.0699, "step": 35660 }, { "epoch": 4.43, "learning_rate": 9.13681065604382e-06, "loss": 0.0616, "step": 35670 }, { "epoch": 4.43, "learning_rate": 9.136561683057389e-06, "loss": 0.0661, "step": 35680 }, { "epoch": 4.43, "learning_rate": 9.136312710070957e-06, "loss": 0.0561, "step": 35690 }, { "epoch": 4.43, "learning_rate": 9.136063737084528e-06, "loss": 0.0526, "step": 35700 }, { "epoch": 4.43, "learning_rate": 9.135814764098096e-06, "loss": 0.0323, "step": 35710 }, { "epoch": 4.44, "learning_rate": 9.135565791111665e-06, "loss": 0.0709, "step": 35720 }, { "epoch": 4.44, "learning_rate": 9.135316818125233e-06, "loss": 0.0708, "step": 35730 }, { "epoch": 4.44, "learning_rate": 9.135067845138803e-06, "loss": 0.0692, "step": 35740 }, { "epoch": 4.44, "learning_rate": 9.134818872152372e-06, "loss": 0.045, "step": 35750 }, { "epoch": 4.44, "learning_rate": 9.134569899165942e-06, "loss": 0.0681, "step": 35760 }, { "epoch": 4.44, "learning_rate": 9.13432092617951e-06, "loss": 0.0789, "step": 35770 }, { "epoch": 4.44, "learning_rate": 9.13407195319308e-06, "loss": 0.0521, "step": 35780 }, { "epoch": 4.44, "learning_rate": 9.133822980206648e-06, "loss": 0.0842, "step": 35790 }, { "epoch": 4.45, "learning_rate": 9.133574007220218e-06, "loss": 0.0602, "step": 35800 }, { "epoch": 4.45, "learning_rate": 9.133325034233786e-06, "loss": 0.0473, "step": 35810 }, { "epoch": 4.45, "learning_rate": 9.133076061247355e-06, "loss": 0.0922, "step": 35820 }, { "epoch": 4.45, "learning_rate": 9.132827088260925e-06, "loss": 0.0914, "step": 35830 }, { "epoch": 4.45, "learning_rate": 9.132578115274494e-06, "loss": 0.0413, "step": 35840 }, { "epoch": 4.45, "learning_rate": 9.132329142288062e-06, "loss": 0.0553, "step": 35850 }, { "epoch": 4.45, "learning_rate": 9.13208016930163e-06, "loss": 0.0597, "step": 35860 }, { "epoch": 4.45, "learning_rate": 9.131831196315201e-06, "loss": 0.0759, "step": 35870 }, { "epoch": 4.46, "learning_rate": 9.13158222332877e-06, "loss": 0.0648, "step": 35880 }, { "epoch": 4.46, "learning_rate": 9.13133325034234e-06, "loss": 0.048, "step": 35890 }, { "epoch": 4.46, "learning_rate": 9.131084277355906e-06, "loss": 0.0516, "step": 35900 }, { "epoch": 4.46, "learning_rate": 9.130835304369477e-06, "loss": 0.0493, "step": 35910 }, { "epoch": 4.46, "learning_rate": 9.130586331383045e-06, "loss": 0.0788, "step": 35920 }, { "epoch": 4.46, "learning_rate": 9.130337358396615e-06, "loss": 0.0512, "step": 35930 }, { "epoch": 4.46, "learning_rate": 9.130088385410184e-06, "loss": 0.0455, "step": 35940 }, { "epoch": 4.46, "learning_rate": 9.129839412423752e-06, "loss": 0.0676, "step": 35950 }, { "epoch": 4.47, "learning_rate": 9.129590439437321e-06, "loss": 0.0568, "step": 35960 }, { "epoch": 4.47, "learning_rate": 9.129341466450891e-06, "loss": 0.0509, "step": 35970 }, { "epoch": 4.47, "learning_rate": 9.12909249346446e-06, "loss": 0.0538, "step": 35980 }, { "epoch": 4.47, "learning_rate": 9.128843520478028e-06, "loss": 0.0768, "step": 35990 }, { "epoch": 4.47, "learning_rate": 9.128594547491598e-06, "loss": 0.0456, "step": 36000 }, { "epoch": 4.47, "learning_rate": 9.128345574505167e-06, "loss": 0.051, "step": 36010 }, { "epoch": 4.47, "learning_rate": 9.128096601518735e-06, "loss": 0.0686, "step": 36020 }, { "epoch": 4.47, "learning_rate": 9.127847628532304e-06, "loss": 0.0664, "step": 36030 }, { "epoch": 4.48, "learning_rate": 9.127598655545874e-06, "loss": 0.0519, "step": 36040 }, { "epoch": 4.48, "learning_rate": 9.127349682559443e-06, "loss": 0.0611, "step": 36050 }, { "epoch": 4.48, "learning_rate": 9.127100709573013e-06, "loss": 0.0364, "step": 36060 }, { "epoch": 4.48, "learning_rate": 9.126851736586581e-06, "loss": 0.0716, "step": 36070 }, { "epoch": 4.48, "learning_rate": 9.12660276360015e-06, "loss": 0.0714, "step": 36080 }, { "epoch": 4.48, "learning_rate": 9.126353790613718e-06, "loss": 0.0677, "step": 36090 }, { "epoch": 4.48, "learning_rate": 9.126104817627289e-06, "loss": 0.0792, "step": 36100 }, { "epoch": 4.48, "learning_rate": 9.125855844640857e-06, "loss": 0.0648, "step": 36110 }, { "epoch": 4.49, "learning_rate": 9.125606871654427e-06, "loss": 0.0715, "step": 36120 }, { "epoch": 4.49, "learning_rate": 9.125357898667996e-06, "loss": 0.0479, "step": 36130 }, { "epoch": 4.49, "learning_rate": 9.125108925681564e-06, "loss": 0.059, "step": 36140 }, { "epoch": 4.49, "learning_rate": 9.124859952695133e-06, "loss": 0.0644, "step": 36150 }, { "epoch": 4.49, "learning_rate": 9.124610979708703e-06, "loss": 0.0832, "step": 36160 }, { "epoch": 4.49, "learning_rate": 9.124362006722272e-06, "loss": 0.0613, "step": 36170 }, { "epoch": 4.49, "learning_rate": 9.12411303373584e-06, "loss": 0.0492, "step": 36180 }, { "epoch": 4.49, "learning_rate": 9.123864060749409e-06, "loss": 0.062, "step": 36190 }, { "epoch": 4.5, "learning_rate": 9.123615087762979e-06, "loss": 0.0623, "step": 36200 }, { "epoch": 4.5, "learning_rate": 9.123366114776547e-06, "loss": 0.044, "step": 36210 }, { "epoch": 4.5, "learning_rate": 9.123117141790116e-06, "loss": 0.0587, "step": 36220 }, { "epoch": 4.5, "learning_rate": 9.122868168803686e-06, "loss": 0.0479, "step": 36230 }, { "epoch": 4.5, "learning_rate": 9.122619195817255e-06, "loss": 0.0664, "step": 36240 }, { "epoch": 4.5, "learning_rate": 9.122370222830823e-06, "loss": 0.0383, "step": 36250 }, { "epoch": 4.5, "learning_rate": 9.122121249844392e-06, "loss": 0.0432, "step": 36260 }, { "epoch": 4.5, "learning_rate": 9.121872276857962e-06, "loss": 0.0403, "step": 36270 }, { "epoch": 4.51, "learning_rate": 9.12162330387153e-06, "loss": 0.0985, "step": 36280 }, { "epoch": 4.51, "learning_rate": 9.1213743308851e-06, "loss": 0.0599, "step": 36290 }, { "epoch": 4.51, "learning_rate": 9.121125357898669e-06, "loss": 0.0614, "step": 36300 }, { "epoch": 4.51, "learning_rate": 9.120876384912238e-06, "loss": 0.0391, "step": 36310 }, { "epoch": 4.51, "learning_rate": 9.120627411925806e-06, "loss": 0.0641, "step": 36320 }, { "epoch": 4.51, "learning_rate": 9.120378438939376e-06, "loss": 0.0765, "step": 36330 }, { "epoch": 4.51, "learning_rate": 9.120129465952945e-06, "loss": 0.0584, "step": 36340 }, { "epoch": 4.51, "learning_rate": 9.119880492966513e-06, "loss": 0.0491, "step": 36350 }, { "epoch": 4.52, "learning_rate": 9.119631519980084e-06, "loss": 0.0674, "step": 36360 }, { "epoch": 4.52, "learning_rate": 9.119382546993652e-06, "loss": 0.0741, "step": 36370 }, { "epoch": 4.52, "learning_rate": 9.11913357400722e-06, "loss": 0.0604, "step": 36380 }, { "epoch": 4.52, "learning_rate": 9.118884601020789e-06, "loss": 0.056, "step": 36390 }, { "epoch": 4.52, "learning_rate": 9.11863562803436e-06, "loss": 0.0414, "step": 36400 }, { "epoch": 4.52, "learning_rate": 9.118386655047928e-06, "loss": 0.0553, "step": 36410 }, { "epoch": 4.52, "learning_rate": 9.118137682061498e-06, "loss": 0.0747, "step": 36420 }, { "epoch": 4.52, "learning_rate": 9.117888709075065e-06, "loss": 0.0626, "step": 36430 }, { "epoch": 4.52, "learning_rate": 9.117639736088635e-06, "loss": 0.0574, "step": 36440 }, { "epoch": 4.53, "learning_rate": 9.117390763102204e-06, "loss": 0.0607, "step": 36450 }, { "epoch": 4.53, "learning_rate": 9.117141790115774e-06, "loss": 0.0624, "step": 36460 }, { "epoch": 4.53, "learning_rate": 9.116892817129342e-06, "loss": 0.0479, "step": 36470 }, { "epoch": 4.53, "learning_rate": 9.116643844142911e-06, "loss": 0.0631, "step": 36480 }, { "epoch": 4.53, "learning_rate": 9.11639487115648e-06, "loss": 0.0545, "step": 36490 }, { "epoch": 4.53, "learning_rate": 9.11614589817005e-06, "loss": 0.0507, "step": 36500 }, { "epoch": 4.53, "learning_rate": 9.115896925183618e-06, "loss": 0.0613, "step": 36510 }, { "epoch": 4.53, "learning_rate": 9.115647952197187e-06, "loss": 0.0564, "step": 36520 }, { "epoch": 4.54, "learning_rate": 9.115398979210757e-06, "loss": 0.044, "step": 36530 }, { "epoch": 4.54, "learning_rate": 9.115150006224325e-06, "loss": 0.0648, "step": 36540 }, { "epoch": 4.54, "learning_rate": 9.114901033237894e-06, "loss": 0.0613, "step": 36550 }, { "epoch": 4.54, "learning_rate": 9.114652060251462e-06, "loss": 0.0712, "step": 36560 }, { "epoch": 4.54, "learning_rate": 9.114403087265033e-06, "loss": 0.061, "step": 36570 }, { "epoch": 4.54, "learning_rate": 9.114154114278601e-06, "loss": 0.0527, "step": 36580 }, { "epoch": 4.54, "learning_rate": 9.113905141292171e-06, "loss": 0.0431, "step": 36590 }, { "epoch": 4.54, "learning_rate": 9.11365616830574e-06, "loss": 0.0398, "step": 36600 }, { "epoch": 4.55, "learning_rate": 9.113407195319308e-06, "loss": 0.0413, "step": 36610 }, { "epoch": 4.55, "learning_rate": 9.113158222332877e-06, "loss": 0.066, "step": 36620 }, { "epoch": 4.55, "learning_rate": 9.112909249346447e-06, "loss": 0.0453, "step": 36630 }, { "epoch": 4.55, "learning_rate": 9.112660276360016e-06, "loss": 0.0498, "step": 36640 }, { "epoch": 4.55, "learning_rate": 9.112411303373586e-06, "loss": 0.0353, "step": 36650 }, { "epoch": 4.55, "learning_rate": 9.112162330387154e-06, "loss": 0.0512, "step": 36660 }, { "epoch": 4.55, "learning_rate": 9.111913357400723e-06, "loss": 0.0725, "step": 36670 }, { "epoch": 4.55, "learning_rate": 9.111664384414291e-06, "loss": 0.061, "step": 36680 }, { "epoch": 4.56, "learning_rate": 9.111415411427862e-06, "loss": 0.0853, "step": 36690 }, { "epoch": 4.56, "learning_rate": 9.11116643844143e-06, "loss": 0.054, "step": 36700 }, { "epoch": 4.56, "learning_rate": 9.110917465454999e-06, "loss": 0.0396, "step": 36710 }, { "epoch": 4.56, "learning_rate": 9.110668492468569e-06, "loss": 0.0852, "step": 36720 }, { "epoch": 4.56, "learning_rate": 9.110419519482137e-06, "loss": 0.0564, "step": 36730 }, { "epoch": 4.56, "learning_rate": 9.110170546495706e-06, "loss": 0.0655, "step": 36740 }, { "epoch": 4.56, "learning_rate": 9.109921573509274e-06, "loss": 0.0622, "step": 36750 }, { "epoch": 4.56, "learning_rate": 9.109672600522845e-06, "loss": 0.0536, "step": 36760 }, { "epoch": 4.57, "learning_rate": 9.109423627536413e-06, "loss": 0.0804, "step": 36770 }, { "epoch": 4.57, "learning_rate": 9.109174654549983e-06, "loss": 0.0531, "step": 36780 }, { "epoch": 4.57, "learning_rate": 9.10892568156355e-06, "loss": 0.0519, "step": 36790 }, { "epoch": 4.57, "learning_rate": 9.10867670857712e-06, "loss": 0.0672, "step": 36800 }, { "epoch": 4.57, "learning_rate": 9.108427735590689e-06, "loss": 0.0472, "step": 36810 }, { "epoch": 4.57, "learning_rate": 9.108178762604259e-06, "loss": 0.0577, "step": 36820 }, { "epoch": 4.57, "learning_rate": 9.107929789617828e-06, "loss": 0.0486, "step": 36830 }, { "epoch": 4.57, "learning_rate": 9.107680816631396e-06, "loss": 0.0576, "step": 36840 }, { "epoch": 4.58, "learning_rate": 9.107431843644965e-06, "loss": 0.0843, "step": 36850 }, { "epoch": 4.58, "learning_rate": 9.107182870658535e-06, "loss": 0.0501, "step": 36860 }, { "epoch": 4.58, "learning_rate": 9.106933897672103e-06, "loss": 0.0559, "step": 36870 }, { "epoch": 4.58, "learning_rate": 9.106684924685672e-06, "loss": 0.0662, "step": 36880 }, { "epoch": 4.58, "learning_rate": 9.106435951699242e-06, "loss": 0.0749, "step": 36890 }, { "epoch": 4.58, "learning_rate": 9.10618697871281e-06, "loss": 0.0636, "step": 36900 }, { "epoch": 4.58, "learning_rate": 9.105938005726379e-06, "loss": 0.0319, "step": 36910 }, { "epoch": 4.58, "learning_rate": 9.105689032739948e-06, "loss": 0.0672, "step": 36920 }, { "epoch": 4.59, "learning_rate": 9.105440059753518e-06, "loss": 0.1066, "step": 36930 }, { "epoch": 4.59, "learning_rate": 9.105191086767086e-06, "loss": 0.0727, "step": 36940 }, { "epoch": 4.59, "learning_rate": 9.104942113780657e-06, "loss": 0.0558, "step": 36950 }, { "epoch": 4.59, "learning_rate": 9.104693140794223e-06, "loss": 0.0597, "step": 36960 }, { "epoch": 4.59, "learning_rate": 9.104444167807794e-06, "loss": 0.0434, "step": 36970 }, { "epoch": 4.59, "learning_rate": 9.104195194821362e-06, "loss": 0.0608, "step": 36980 }, { "epoch": 4.59, "learning_rate": 9.103946221834932e-06, "loss": 0.05, "step": 36990 }, { "epoch": 4.59, "learning_rate": 9.1036972488485e-06, "loss": 0.0499, "step": 37000 }, { "epoch": 4.6, "learning_rate": 9.10344827586207e-06, "loss": 0.0353, "step": 37010 }, { "epoch": 4.6, "learning_rate": 9.103199302875638e-06, "loss": 0.0481, "step": 37020 }, { "epoch": 4.6, "learning_rate": 9.102950329889208e-06, "loss": 0.0692, "step": 37030 }, { "epoch": 4.6, "learning_rate": 9.102701356902777e-06, "loss": 0.0607, "step": 37040 }, { "epoch": 4.6, "learning_rate": 9.102452383916345e-06, "loss": 0.0369, "step": 37050 }, { "epoch": 4.6, "learning_rate": 9.102203410929915e-06, "loss": 0.0481, "step": 37060 }, { "epoch": 4.6, "learning_rate": 9.101954437943484e-06, "loss": 0.0478, "step": 37070 }, { "epoch": 4.6, "learning_rate": 9.101705464957052e-06, "loss": 0.0619, "step": 37080 }, { "epoch": 4.61, "learning_rate": 9.10145649197062e-06, "loss": 0.0572, "step": 37090 }, { "epoch": 4.61, "learning_rate": 9.101207518984191e-06, "loss": 0.0544, "step": 37100 }, { "epoch": 4.61, "learning_rate": 9.10095854599776e-06, "loss": 0.0391, "step": 37110 }, { "epoch": 4.61, "learning_rate": 9.10070957301133e-06, "loss": 0.0629, "step": 37120 }, { "epoch": 4.61, "learning_rate": 9.100460600024898e-06, "loss": 0.0595, "step": 37130 }, { "epoch": 4.61, "learning_rate": 9.100211627038467e-06, "loss": 0.0563, "step": 37140 }, { "epoch": 4.61, "learning_rate": 9.099962654052035e-06, "loss": 0.0481, "step": 37150 }, { "epoch": 4.61, "learning_rate": 9.099713681065606e-06, "loss": 0.0713, "step": 37160 }, { "epoch": 4.62, "learning_rate": 9.099464708079174e-06, "loss": 0.0419, "step": 37170 }, { "epoch": 4.62, "learning_rate": 9.099215735092744e-06, "loss": 0.0773, "step": 37180 }, { "epoch": 4.62, "learning_rate": 9.098966762106313e-06, "loss": 0.0503, "step": 37190 }, { "epoch": 4.62, "learning_rate": 9.098717789119881e-06, "loss": 0.0611, "step": 37200 }, { "epoch": 4.62, "learning_rate": 9.09846881613345e-06, "loss": 0.0492, "step": 37210 }, { "epoch": 4.62, "learning_rate": 9.09821984314702e-06, "loss": 0.0666, "step": 37220 }, { "epoch": 4.62, "learning_rate": 9.097970870160589e-06, "loss": 0.062, "step": 37230 }, { "epoch": 4.62, "learning_rate": 9.097721897174157e-06, "loss": 0.0466, "step": 37240 }, { "epoch": 4.63, "learning_rate": 9.097472924187727e-06, "loss": 0.0423, "step": 37250 }, { "epoch": 4.63, "learning_rate": 9.097223951201296e-06, "loss": 0.0477, "step": 37260 }, { "epoch": 4.63, "learning_rate": 9.096974978214864e-06, "loss": 0.0573, "step": 37270 }, { "epoch": 4.63, "learning_rate": 9.096726005228433e-06, "loss": 0.0581, "step": 37280 }, { "epoch": 4.63, "learning_rate": 9.096477032242003e-06, "loss": 0.0462, "step": 37290 }, { "epoch": 4.63, "learning_rate": 9.096228059255572e-06, "loss": 0.0514, "step": 37300 }, { "epoch": 4.63, "learning_rate": 9.095979086269142e-06, "loss": 0.0425, "step": 37310 }, { "epoch": 4.63, "learning_rate": 9.095730113282709e-06, "loss": 0.0569, "step": 37320 }, { "epoch": 4.64, "learning_rate": 9.095481140296279e-06, "loss": 0.0567, "step": 37330 }, { "epoch": 4.64, "learning_rate": 9.095232167309847e-06, "loss": 0.0546, "step": 37340 }, { "epoch": 4.64, "learning_rate": 9.094983194323417e-06, "loss": 0.0517, "step": 37350 }, { "epoch": 4.64, "learning_rate": 9.094734221336986e-06, "loss": 0.0521, "step": 37360 }, { "epoch": 4.64, "learning_rate": 9.094485248350555e-06, "loss": 0.0727, "step": 37370 }, { "epoch": 4.64, "learning_rate": 9.094236275364123e-06, "loss": 0.053, "step": 37380 }, { "epoch": 4.64, "learning_rate": 9.093987302377693e-06, "loss": 0.0545, "step": 37390 }, { "epoch": 4.64, "learning_rate": 9.093738329391262e-06, "loss": 0.0545, "step": 37400 }, { "epoch": 4.65, "learning_rate": 9.09348935640483e-06, "loss": 0.0421, "step": 37410 }, { "epoch": 4.65, "learning_rate": 9.0932403834184e-06, "loss": 0.0677, "step": 37420 }, { "epoch": 4.65, "learning_rate": 9.092991410431969e-06, "loss": 0.0764, "step": 37430 }, { "epoch": 4.65, "learning_rate": 9.092742437445538e-06, "loss": 0.0986, "step": 37440 }, { "epoch": 4.65, "learning_rate": 9.092493464459106e-06, "loss": 0.0467, "step": 37450 }, { "epoch": 4.65, "learning_rate": 9.092244491472676e-06, "loss": 0.0565, "step": 37460 }, { "epoch": 4.65, "learning_rate": 9.091995518486245e-06, "loss": 0.0755, "step": 37470 }, { "epoch": 4.65, "learning_rate": 9.091746545499815e-06, "loss": 0.0648, "step": 37480 }, { "epoch": 4.66, "learning_rate": 9.091497572513382e-06, "loss": 0.0863, "step": 37490 }, { "epoch": 4.66, "learning_rate": 9.091248599526952e-06, "loss": 0.0446, "step": 37500 }, { "epoch": 4.66, "learning_rate": 9.09099962654052e-06, "loss": 0.0448, "step": 37510 }, { "epoch": 4.66, "learning_rate": 9.09075065355409e-06, "loss": 0.0682, "step": 37520 }, { "epoch": 4.66, "learning_rate": 9.09050168056766e-06, "loss": 0.0776, "step": 37530 }, { "epoch": 4.66, "learning_rate": 9.090252707581228e-06, "loss": 0.0404, "step": 37540 }, { "epoch": 4.66, "learning_rate": 9.090003734594796e-06, "loss": 0.0823, "step": 37550 }, { "epoch": 4.66, "learning_rate": 9.089754761608366e-06, "loss": 0.0333, "step": 37560 }, { "epoch": 4.67, "learning_rate": 9.089505788621935e-06, "loss": 0.0557, "step": 37570 }, { "epoch": 4.67, "learning_rate": 9.089256815635504e-06, "loss": 0.0854, "step": 37580 }, { "epoch": 4.67, "learning_rate": 9.089007842649074e-06, "loss": 0.0591, "step": 37590 }, { "epoch": 4.67, "learning_rate": 9.088758869662642e-06, "loss": 0.0436, "step": 37600 }, { "epoch": 4.67, "learning_rate": 9.08850989667621e-06, "loss": 0.0579, "step": 37610 }, { "epoch": 4.67, "learning_rate": 9.08826092368978e-06, "loss": 0.0782, "step": 37620 }, { "epoch": 4.67, "learning_rate": 9.08801195070335e-06, "loss": 0.065, "step": 37630 }, { "epoch": 4.67, "learning_rate": 9.087762977716918e-06, "loss": 0.0588, "step": 37640 }, { "epoch": 4.68, "learning_rate": 9.087514004730488e-06, "loss": 0.0406, "step": 37650 }, { "epoch": 4.68, "learning_rate": 9.087265031744057e-06, "loss": 0.064, "step": 37660 }, { "epoch": 4.68, "learning_rate": 9.087016058757625e-06, "loss": 0.0662, "step": 37670 }, { "epoch": 4.68, "learning_rate": 9.086767085771194e-06, "loss": 0.0484, "step": 37680 }, { "epoch": 4.68, "learning_rate": 9.086518112784764e-06, "loss": 0.0366, "step": 37690 }, { "epoch": 4.68, "learning_rate": 9.086269139798332e-06, "loss": 0.0645, "step": 37700 }, { "epoch": 4.68, "learning_rate": 9.086020166811903e-06, "loss": 0.0491, "step": 37710 }, { "epoch": 4.68, "learning_rate": 9.085771193825471e-06, "loss": 0.0558, "step": 37720 }, { "epoch": 4.69, "learning_rate": 9.08552222083904e-06, "loss": 0.0586, "step": 37730 }, { "epoch": 4.69, "learning_rate": 9.085273247852608e-06, "loss": 0.0655, "step": 37740 }, { "epoch": 4.69, "learning_rate": 9.085024274866178e-06, "loss": 0.0629, "step": 37750 }, { "epoch": 4.69, "learning_rate": 9.084775301879747e-06, "loss": 0.0539, "step": 37760 }, { "epoch": 4.69, "learning_rate": 9.084526328893315e-06, "loss": 0.0891, "step": 37770 }, { "epoch": 4.69, "learning_rate": 9.084277355906886e-06, "loss": 0.0706, "step": 37780 }, { "epoch": 4.69, "learning_rate": 9.084028382920454e-06, "loss": 0.0612, "step": 37790 }, { "epoch": 4.69, "learning_rate": 9.083779409934023e-06, "loss": 0.0521, "step": 37800 }, { "epoch": 4.7, "learning_rate": 9.083530436947591e-06, "loss": 0.0505, "step": 37810 }, { "epoch": 4.7, "learning_rate": 9.083281463961161e-06, "loss": 0.067, "step": 37820 }, { "epoch": 4.7, "learning_rate": 9.08303249097473e-06, "loss": 0.0629, "step": 37830 }, { "epoch": 4.7, "learning_rate": 9.0827835179883e-06, "loss": 0.0506, "step": 37840 }, { "epoch": 4.7, "learning_rate": 9.082534545001867e-06, "loss": 0.0492, "step": 37850 }, { "epoch": 4.7, "learning_rate": 9.082285572015437e-06, "loss": 0.0685, "step": 37860 }, { "epoch": 4.7, "learning_rate": 9.082036599029006e-06, "loss": 0.0681, "step": 37870 }, { "epoch": 4.7, "learning_rate": 9.081787626042576e-06, "loss": 0.0402, "step": 37880 }, { "epoch": 4.71, "learning_rate": 9.081538653056144e-06, "loss": 0.05, "step": 37890 }, { "epoch": 4.71, "learning_rate": 9.081289680069713e-06, "loss": 0.0859, "step": 37900 }, { "epoch": 4.71, "learning_rate": 9.081040707083281e-06, "loss": 0.0515, "step": 37910 }, { "epoch": 4.71, "learning_rate": 9.080791734096852e-06, "loss": 0.0855, "step": 37920 }, { "epoch": 4.71, "learning_rate": 9.08054276111042e-06, "loss": 0.0561, "step": 37930 }, { "epoch": 4.71, "learning_rate": 9.080293788123989e-06, "loss": 0.0392, "step": 37940 }, { "epoch": 4.71, "learning_rate": 9.080044815137559e-06, "loss": 0.0481, "step": 37950 }, { "epoch": 4.71, "learning_rate": 9.079795842151127e-06, "loss": 0.0344, "step": 37960 }, { "epoch": 4.71, "learning_rate": 9.079546869164696e-06, "loss": 0.0743, "step": 37970 }, { "epoch": 4.72, "learning_rate": 9.079297896178264e-06, "loss": 0.0752, "step": 37980 }, { "epoch": 4.72, "learning_rate": 9.079048923191835e-06, "loss": 0.052, "step": 37990 }, { "epoch": 4.72, "learning_rate": 9.078799950205403e-06, "loss": 0.0746, "step": 38000 }, { "epoch": 4.72, "learning_rate": 9.078550977218973e-06, "loss": 0.0602, "step": 38010 }, { "epoch": 4.72, "learning_rate": 9.078302004232542e-06, "loss": 0.0545, "step": 38020 }, { "epoch": 4.72, "learning_rate": 9.07805303124611e-06, "loss": 0.0468, "step": 38030 }, { "epoch": 4.72, "learning_rate": 9.077804058259679e-06, "loss": 0.094, "step": 38040 }, { "epoch": 4.72, "learning_rate": 9.07755508527325e-06, "loss": 0.04, "step": 38050 }, { "epoch": 4.73, "learning_rate": 9.077306112286818e-06, "loss": 0.0402, "step": 38060 }, { "epoch": 4.73, "learning_rate": 9.077057139300386e-06, "loss": 0.0422, "step": 38070 }, { "epoch": 4.73, "learning_rate": 9.076808166313956e-06, "loss": 0.0606, "step": 38080 }, { "epoch": 4.73, "learning_rate": 9.076559193327525e-06, "loss": 0.0467, "step": 38090 }, { "epoch": 4.73, "learning_rate": 9.076310220341093e-06, "loss": 0.0836, "step": 38100 }, { "epoch": 4.73, "learning_rate": 9.076061247354662e-06, "loss": 0.0448, "step": 38110 }, { "epoch": 4.73, "learning_rate": 9.075812274368232e-06, "loss": 0.0401, "step": 38120 }, { "epoch": 4.73, "learning_rate": 9.0755633013818e-06, "loss": 0.0692, "step": 38130 }, { "epoch": 4.74, "learning_rate": 9.07531432839537e-06, "loss": 0.0732, "step": 38140 }, { "epoch": 4.74, "learning_rate": 9.075065355408938e-06, "loss": 0.0579, "step": 38150 }, { "epoch": 4.74, "learning_rate": 9.074816382422508e-06, "loss": 0.0438, "step": 38160 }, { "epoch": 4.74, "learning_rate": 9.074567409436076e-06, "loss": 0.0976, "step": 38170 }, { "epoch": 4.74, "learning_rate": 9.074318436449647e-06, "loss": 0.0605, "step": 38180 }, { "epoch": 4.74, "learning_rate": 9.074069463463215e-06, "loss": 0.0699, "step": 38190 }, { "epoch": 4.74, "learning_rate": 9.073820490476784e-06, "loss": 0.0639, "step": 38200 }, { "epoch": 4.74, "learning_rate": 9.073571517490352e-06, "loss": 0.053, "step": 38210 }, { "epoch": 4.75, "learning_rate": 9.073322544503922e-06, "loss": 0.0687, "step": 38220 }, { "epoch": 4.75, "learning_rate": 9.073073571517491e-06, "loss": 0.0662, "step": 38230 }, { "epoch": 4.75, "learning_rate": 9.072824598531061e-06, "loss": 0.0302, "step": 38240 }, { "epoch": 4.75, "learning_rate": 9.07257562554463e-06, "loss": 0.0552, "step": 38250 }, { "epoch": 4.75, "learning_rate": 9.072326652558198e-06, "loss": 0.0478, "step": 38260 }, { "epoch": 4.75, "learning_rate": 9.072077679571767e-06, "loss": 0.0875, "step": 38270 }, { "epoch": 4.75, "learning_rate": 9.071828706585337e-06, "loss": 0.0467, "step": 38280 }, { "epoch": 4.75, "learning_rate": 9.071579733598905e-06, "loss": 0.0545, "step": 38290 }, { "epoch": 4.76, "learning_rate": 9.071330760612474e-06, "loss": 0.0664, "step": 38300 }, { "epoch": 4.76, "learning_rate": 9.071081787626044e-06, "loss": 0.0613, "step": 38310 }, { "epoch": 4.76, "learning_rate": 9.070832814639613e-06, "loss": 0.0832, "step": 38320 }, { "epoch": 4.76, "learning_rate": 9.070583841653181e-06, "loss": 0.0519, "step": 38330 }, { "epoch": 4.76, "learning_rate": 9.07033486866675e-06, "loss": 0.0717, "step": 38340 }, { "epoch": 4.76, "learning_rate": 9.07008589568032e-06, "loss": 0.0429, "step": 38350 }, { "epoch": 4.76, "learning_rate": 9.069836922693888e-06, "loss": 0.0268, "step": 38360 }, { "epoch": 4.76, "learning_rate": 9.069587949707459e-06, "loss": 0.0729, "step": 38370 }, { "epoch": 4.77, "learning_rate": 9.069338976721025e-06, "loss": 0.0569, "step": 38380 }, { "epoch": 4.77, "learning_rate": 9.069090003734596e-06, "loss": 0.071, "step": 38390 }, { "epoch": 4.77, "learning_rate": 9.068841030748164e-06, "loss": 0.0469, "step": 38400 }, { "epoch": 4.77, "learning_rate": 9.068592057761734e-06, "loss": 0.061, "step": 38410 }, { "epoch": 4.77, "learning_rate": 9.068343084775303e-06, "loss": 0.0494, "step": 38420 }, { "epoch": 4.77, "learning_rate": 9.068094111788871e-06, "loss": 0.0619, "step": 38430 }, { "epoch": 4.77, "learning_rate": 9.06784513880244e-06, "loss": 0.054, "step": 38440 }, { "epoch": 4.77, "learning_rate": 9.06759616581601e-06, "loss": 0.0605, "step": 38450 }, { "epoch": 4.78, "learning_rate": 9.067347192829579e-06, "loss": 0.035, "step": 38460 }, { "epoch": 4.78, "learning_rate": 9.067098219843147e-06, "loss": 0.0597, "step": 38470 }, { "epoch": 4.78, "learning_rate": 9.066849246856717e-06, "loss": 0.0326, "step": 38480 }, { "epoch": 4.78, "learning_rate": 9.066600273870286e-06, "loss": 0.0615, "step": 38490 }, { "epoch": 4.78, "learning_rate": 9.066351300883854e-06, "loss": 0.0305, "step": 38500 }, { "epoch": 4.78, "learning_rate": 9.066102327897423e-06, "loss": 0.0398, "step": 38510 }, { "epoch": 4.78, "learning_rate": 9.065853354910993e-06, "loss": 0.0773, "step": 38520 }, { "epoch": 4.78, "learning_rate": 9.065604381924562e-06, "loss": 0.0692, "step": 38530 }, { "epoch": 4.79, "learning_rate": 9.065355408938132e-06, "loss": 0.0566, "step": 38540 }, { "epoch": 4.79, "learning_rate": 9.0651064359517e-06, "loss": 0.0596, "step": 38550 }, { "epoch": 4.79, "learning_rate": 9.064857462965269e-06, "loss": 0.0389, "step": 38560 }, { "epoch": 4.79, "learning_rate": 9.064608489978837e-06, "loss": 0.0663, "step": 38570 }, { "epoch": 4.79, "learning_rate": 9.064359516992408e-06, "loss": 0.0668, "step": 38580 }, { "epoch": 4.79, "learning_rate": 9.064110544005976e-06, "loss": 0.0455, "step": 38590 }, { "epoch": 4.79, "learning_rate": 9.063861571019545e-06, "loss": 0.041, "step": 38600 }, { "epoch": 4.79, "learning_rate": 9.063612598033115e-06, "loss": 0.0593, "step": 38610 }, { "epoch": 4.8, "learning_rate": 9.063363625046683e-06, "loss": 0.1014, "step": 38620 }, { "epoch": 4.8, "learning_rate": 9.063114652060252e-06, "loss": 0.0576, "step": 38630 }, { "epoch": 4.8, "learning_rate": 9.06286567907382e-06, "loss": 0.0509, "step": 38640 }, { "epoch": 4.8, "learning_rate": 9.06261670608739e-06, "loss": 0.0546, "step": 38650 }, { "epoch": 4.8, "learning_rate": 9.062367733100959e-06, "loss": 0.0709, "step": 38660 }, { "epoch": 4.8, "learning_rate": 9.06211876011453e-06, "loss": 0.0631, "step": 38670 }, { "epoch": 4.8, "learning_rate": 9.061869787128096e-06, "loss": 0.0719, "step": 38680 }, { "epoch": 4.8, "learning_rate": 9.061620814141666e-06, "loss": 0.042, "step": 38690 }, { "epoch": 4.81, "learning_rate": 9.061371841155235e-06, "loss": 0.0385, "step": 38700 }, { "epoch": 4.81, "learning_rate": 9.061122868168805e-06, "loss": 0.0616, "step": 38710 }, { "epoch": 4.81, "learning_rate": 9.060873895182374e-06, "loss": 0.0496, "step": 38720 }, { "epoch": 4.81, "learning_rate": 9.060624922195944e-06, "loss": 0.0473, "step": 38730 }, { "epoch": 4.81, "learning_rate": 9.06037594920951e-06, "loss": 0.0604, "step": 38740 }, { "epoch": 4.81, "learning_rate": 9.06012697622308e-06, "loss": 0.0535, "step": 38750 }, { "epoch": 4.81, "learning_rate": 9.05987800323665e-06, "loss": 0.0362, "step": 38760 }, { "epoch": 4.81, "learning_rate": 9.05962903025022e-06, "loss": 0.0842, "step": 38770 }, { "epoch": 4.82, "learning_rate": 9.059380057263788e-06, "loss": 0.0571, "step": 38780 }, { "epoch": 4.82, "learning_rate": 9.059131084277357e-06, "loss": 0.0892, "step": 38790 }, { "epoch": 4.82, "learning_rate": 9.058882111290925e-06, "loss": 0.0683, "step": 38800 }, { "epoch": 4.82, "learning_rate": 9.058633138304495e-06, "loss": 0.0396, "step": 38810 }, { "epoch": 4.82, "learning_rate": 9.058384165318064e-06, "loss": 0.0623, "step": 38820 }, { "epoch": 4.82, "learning_rate": 9.058135192331632e-06, "loss": 0.0518, "step": 38830 }, { "epoch": 4.82, "learning_rate": 9.057886219345203e-06, "loss": 0.043, "step": 38840 }, { "epoch": 4.82, "learning_rate": 9.057637246358771e-06, "loss": 0.0577, "step": 38850 }, { "epoch": 4.83, "learning_rate": 9.05738827337234e-06, "loss": 0.0765, "step": 38860 }, { "epoch": 4.83, "learning_rate": 9.057139300385908e-06, "loss": 0.0495, "step": 38870 }, { "epoch": 4.83, "learning_rate": 9.056890327399478e-06, "loss": 0.0398, "step": 38880 }, { "epoch": 4.83, "learning_rate": 9.056641354413047e-06, "loss": 0.0579, "step": 38890 }, { "epoch": 4.83, "learning_rate": 9.056392381426617e-06, "loss": 0.0557, "step": 38900 }, { "epoch": 4.83, "learning_rate": 9.056143408440184e-06, "loss": 0.0391, "step": 38910 }, { "epoch": 4.83, "learning_rate": 9.055894435453754e-06, "loss": 0.0493, "step": 38920 }, { "epoch": 4.83, "learning_rate": 9.055645462467323e-06, "loss": 0.0424, "step": 38930 }, { "epoch": 4.84, "learning_rate": 9.055396489480893e-06, "loss": 0.0509, "step": 38940 }, { "epoch": 4.84, "learning_rate": 9.055147516494461e-06, "loss": 0.0418, "step": 38950 }, { "epoch": 4.84, "learning_rate": 9.05489854350803e-06, "loss": 0.0454, "step": 38960 }, { "epoch": 4.84, "learning_rate": 9.054649570521598e-06, "loss": 0.0695, "step": 38970 }, { "epoch": 4.84, "learning_rate": 9.054400597535169e-06, "loss": 0.0589, "step": 38980 }, { "epoch": 4.84, "learning_rate": 9.054151624548737e-06, "loss": 0.0371, "step": 38990 }, { "epoch": 4.84, "learning_rate": 9.053902651562306e-06, "loss": 0.0501, "step": 39000 }, { "epoch": 4.84, "learning_rate": 9.053653678575876e-06, "loss": 0.0371, "step": 39010 }, { "epoch": 4.85, "learning_rate": 9.053404705589444e-06, "loss": 0.0555, "step": 39020 }, { "epoch": 4.85, "learning_rate": 9.053155732603013e-06, "loss": 0.0788, "step": 39030 }, { "epoch": 4.85, "learning_rate": 9.052906759616581e-06, "loss": 0.0594, "step": 39040 }, { "epoch": 4.85, "learning_rate": 9.052657786630152e-06, "loss": 0.0413, "step": 39050 }, { "epoch": 4.85, "learning_rate": 9.05240881364372e-06, "loss": 0.0304, "step": 39060 }, { "epoch": 4.85, "learning_rate": 9.05215984065729e-06, "loss": 0.0634, "step": 39070 }, { "epoch": 4.85, "learning_rate": 9.051910867670859e-06, "loss": 0.0737, "step": 39080 }, { "epoch": 4.85, "learning_rate": 9.051661894684427e-06, "loss": 0.0577, "step": 39090 }, { "epoch": 4.86, "learning_rate": 9.051412921697996e-06, "loss": 0.0581, "step": 39100 }, { "epoch": 4.86, "learning_rate": 9.051163948711566e-06, "loss": 0.042, "step": 39110 }, { "epoch": 4.86, "learning_rate": 9.050914975725135e-06, "loss": 0.0694, "step": 39120 }, { "epoch": 4.86, "learning_rate": 9.050666002738703e-06, "loss": 0.0341, "step": 39130 }, { "epoch": 4.86, "learning_rate": 9.050417029752273e-06, "loss": 0.0672, "step": 39140 }, { "epoch": 4.86, "learning_rate": 9.050168056765842e-06, "loss": 0.0461, "step": 39150 }, { "epoch": 4.86, "learning_rate": 9.04991908377941e-06, "loss": 0.0492, "step": 39160 }, { "epoch": 4.86, "learning_rate": 9.049670110792979e-06, "loss": 0.073, "step": 39170 }, { "epoch": 4.87, "learning_rate": 9.049421137806549e-06, "loss": 0.0768, "step": 39180 }, { "epoch": 4.87, "learning_rate": 9.049172164820118e-06, "loss": 0.0519, "step": 39190 }, { "epoch": 4.87, "learning_rate": 9.048923191833688e-06, "loss": 0.0468, "step": 39200 }, { "epoch": 4.87, "learning_rate": 9.048674218847255e-06, "loss": 0.0377, "step": 39210 }, { "epoch": 4.87, "learning_rate": 9.048425245860825e-06, "loss": 0.0501, "step": 39220 }, { "epoch": 4.87, "learning_rate": 9.048176272874393e-06, "loss": 0.0801, "step": 39230 }, { "epoch": 4.87, "learning_rate": 9.047927299887964e-06, "loss": 0.049, "step": 39240 }, { "epoch": 4.87, "learning_rate": 9.047678326901532e-06, "loss": 0.0597, "step": 39250 }, { "epoch": 4.88, "learning_rate": 9.047429353915102e-06, "loss": 0.0592, "step": 39260 }, { "epoch": 4.88, "learning_rate": 9.047180380928669e-06, "loss": 0.0518, "step": 39270 }, { "epoch": 4.88, "learning_rate": 9.04693140794224e-06, "loss": 0.0449, "step": 39280 }, { "epoch": 4.88, "learning_rate": 9.046682434955808e-06, "loss": 0.0554, "step": 39290 }, { "epoch": 4.88, "learning_rate": 9.046433461969378e-06, "loss": 0.0624, "step": 39300 }, { "epoch": 4.88, "learning_rate": 9.046184488982947e-06, "loss": 0.0619, "step": 39310 }, { "epoch": 4.88, "learning_rate": 9.045935515996515e-06, "loss": 0.0737, "step": 39320 }, { "epoch": 4.88, "learning_rate": 9.045686543010084e-06, "loss": 0.0588, "step": 39330 }, { "epoch": 4.89, "learning_rate": 9.045437570023654e-06, "loss": 0.0473, "step": 39340 }, { "epoch": 4.89, "learning_rate": 9.045188597037222e-06, "loss": 0.0492, "step": 39350 }, { "epoch": 4.89, "learning_rate": 9.04493962405079e-06, "loss": 0.0632, "step": 39360 }, { "epoch": 4.89, "learning_rate": 9.044690651064361e-06, "loss": 0.0733, "step": 39370 }, { "epoch": 4.89, "learning_rate": 9.04444167807793e-06, "loss": 0.0584, "step": 39380 }, { "epoch": 4.89, "learning_rate": 9.044192705091498e-06, "loss": 0.0454, "step": 39390 }, { "epoch": 4.89, "learning_rate": 9.043943732105067e-06, "loss": 0.0621, "step": 39400 }, { "epoch": 4.89, "learning_rate": 9.043694759118637e-06, "loss": 0.0406, "step": 39410 }, { "epoch": 4.9, "learning_rate": 9.043445786132205e-06, "loss": 0.0781, "step": 39420 }, { "epoch": 4.9, "learning_rate": 9.043196813145775e-06, "loss": 0.0747, "step": 39430 }, { "epoch": 4.9, "learning_rate": 9.042947840159342e-06, "loss": 0.0611, "step": 39440 }, { "epoch": 4.9, "learning_rate": 9.042698867172913e-06, "loss": 0.0654, "step": 39450 }, { "epoch": 4.9, "learning_rate": 9.042449894186481e-06, "loss": 0.0553, "step": 39460 }, { "epoch": 4.9, "learning_rate": 9.042200921200051e-06, "loss": 0.0627, "step": 39470 }, { "epoch": 4.9, "learning_rate": 9.04195194821362e-06, "loss": 0.0606, "step": 39480 }, { "epoch": 4.9, "learning_rate": 9.041702975227188e-06, "loss": 0.0481, "step": 39490 }, { "epoch": 4.9, "learning_rate": 9.041454002240757e-06, "loss": 0.0499, "step": 39500 }, { "epoch": 4.91, "learning_rate": 9.041205029254327e-06, "loss": 0.043, "step": 39510 }, { "epoch": 4.91, "learning_rate": 9.040956056267896e-06, "loss": 0.06, "step": 39520 }, { "epoch": 4.91, "learning_rate": 9.040707083281464e-06, "loss": 0.0589, "step": 39530 }, { "epoch": 4.91, "learning_rate": 9.040458110295034e-06, "loss": 0.0738, "step": 39540 }, { "epoch": 4.91, "learning_rate": 9.040209137308603e-06, "loss": 0.0528, "step": 39550 }, { "epoch": 4.91, "learning_rate": 9.039960164322171e-06, "loss": 0.0402, "step": 39560 }, { "epoch": 4.91, "learning_rate": 9.03971119133574e-06, "loss": 0.0857, "step": 39570 }, { "epoch": 4.91, "learning_rate": 9.03946221834931e-06, "loss": 0.0572, "step": 39580 }, { "epoch": 4.92, "learning_rate": 9.039213245362879e-06, "loss": 0.0689, "step": 39590 }, { "epoch": 4.92, "learning_rate": 9.038964272376449e-06, "loss": 0.0728, "step": 39600 }, { "epoch": 4.92, "learning_rate": 9.038715299390017e-06, "loss": 0.0351, "step": 39610 }, { "epoch": 4.92, "learning_rate": 9.038466326403586e-06, "loss": 0.0611, "step": 39620 }, { "epoch": 4.92, "learning_rate": 9.038217353417154e-06, "loss": 0.0486, "step": 39630 }, { "epoch": 4.92, "learning_rate": 9.037968380430724e-06, "loss": 0.0645, "step": 39640 }, { "epoch": 4.92, "learning_rate": 9.037719407444293e-06, "loss": 0.053, "step": 39650 }, { "epoch": 4.92, "learning_rate": 9.037470434457862e-06, "loss": 0.0984, "step": 39660 }, { "epoch": 4.93, "learning_rate": 9.037221461471432e-06, "loss": 0.1049, "step": 39670 }, { "epoch": 4.93, "learning_rate": 9.036972488485e-06, "loss": 0.0465, "step": 39680 }, { "epoch": 4.93, "learning_rate": 9.036723515498569e-06, "loss": 0.0555, "step": 39690 }, { "epoch": 4.93, "learning_rate": 9.036474542512137e-06, "loss": 0.0432, "step": 39700 }, { "epoch": 4.93, "learning_rate": 9.036225569525707e-06, "loss": 0.0499, "step": 39710 }, { "epoch": 4.93, "learning_rate": 9.035976596539276e-06, "loss": 0.0721, "step": 39720 }, { "epoch": 4.93, "learning_rate": 9.035727623552846e-06, "loss": 0.0397, "step": 39730 }, { "epoch": 4.93, "learning_rate": 9.035478650566413e-06, "loss": 0.1062, "step": 39740 }, { "epoch": 4.94, "learning_rate": 9.035229677579983e-06, "loss": 0.0572, "step": 39750 }, { "epoch": 4.94, "learning_rate": 9.034980704593552e-06, "loss": 0.0633, "step": 39760 }, { "epoch": 4.94, "learning_rate": 9.034731731607122e-06, "loss": 0.0394, "step": 39770 }, { "epoch": 4.94, "learning_rate": 9.03448275862069e-06, "loss": 0.0535, "step": 39780 }, { "epoch": 4.94, "learning_rate": 9.03423378563426e-06, "loss": 0.0653, "step": 39790 }, { "epoch": 4.94, "learning_rate": 9.033984812647828e-06, "loss": 0.056, "step": 39800 }, { "epoch": 4.94, "learning_rate": 9.033735839661398e-06, "loss": 0.04, "step": 39810 }, { "epoch": 4.94, "learning_rate": 9.033486866674966e-06, "loss": 0.0628, "step": 39820 }, { "epoch": 4.95, "learning_rate": 9.033237893688536e-06, "loss": 0.0455, "step": 39830 }, { "epoch": 4.95, "learning_rate": 9.032988920702105e-06, "loss": 0.0778, "step": 39840 }, { "epoch": 4.95, "learning_rate": 9.032739947715673e-06, "loss": 0.0598, "step": 39850 }, { "epoch": 4.95, "learning_rate": 9.032490974729242e-06, "loss": 0.038, "step": 39860 }, { "epoch": 4.95, "learning_rate": 9.032242001742812e-06, "loss": 0.0525, "step": 39870 }, { "epoch": 4.95, "learning_rate": 9.03199302875638e-06, "loss": 0.099, "step": 39880 }, { "epoch": 4.95, "learning_rate": 9.03174405576995e-06, "loss": 0.0464, "step": 39890 }, { "epoch": 4.95, "learning_rate": 9.03149508278352e-06, "loss": 0.0421, "step": 39900 }, { "epoch": 4.96, "learning_rate": 9.031246109797088e-06, "loss": 0.0449, "step": 39910 }, { "epoch": 4.96, "learning_rate": 9.030997136810656e-06, "loss": 0.07, "step": 39920 }, { "epoch": 4.96, "learning_rate": 9.030748163824225e-06, "loss": 0.0522, "step": 39930 }, { "epoch": 4.96, "learning_rate": 9.030499190837795e-06, "loss": 0.0397, "step": 39940 }, { "epoch": 4.96, "learning_rate": 9.030250217851364e-06, "loss": 0.0475, "step": 39950 }, { "epoch": 4.96, "learning_rate": 9.030001244864934e-06, "loss": 0.0284, "step": 39960 }, { "epoch": 4.96, "learning_rate": 9.029752271878502e-06, "loss": 0.0336, "step": 39970 }, { "epoch": 4.96, "learning_rate": 9.029503298892071e-06, "loss": 0.0622, "step": 39980 }, { "epoch": 4.97, "learning_rate": 9.02925432590564e-06, "loss": 0.0325, "step": 39990 }, { "epoch": 4.97, "learning_rate": 9.02900535291921e-06, "loss": 0.0478, "step": 40000 }, { "epoch": 4.97, "eval_bleu": 89.271, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7673, "eval_has_error_f1": 0.6843, "eval_loss": 0.0534321628510952, "eval_runtime": 1371.9861, "eval_samples_per_second": 2.914, "eval_steps_per_second": 0.729, "step": 40000 }, { "epoch": 4.97, "learning_rate": 9.028756379932778e-06, "loss": 0.0413, "step": 40010 }, { "epoch": 4.97, "learning_rate": 9.028507406946347e-06, "loss": 0.0731, "step": 40020 }, { "epoch": 4.97, "learning_rate": 9.028258433959917e-06, "loss": 0.0702, "step": 40030 }, { "epoch": 4.97, "learning_rate": 9.028009460973485e-06, "loss": 0.0489, "step": 40040 }, { "epoch": 4.97, "learning_rate": 9.027760487987054e-06, "loss": 0.0449, "step": 40050 }, { "epoch": 4.97, "learning_rate": 9.027511515000622e-06, "loss": 0.0498, "step": 40060 }, { "epoch": 4.98, "learning_rate": 9.027262542014193e-06, "loss": 0.0736, "step": 40070 }, { "epoch": 4.98, "learning_rate": 9.027013569027761e-06, "loss": 0.0436, "step": 40080 }, { "epoch": 4.98, "learning_rate": 9.02676459604133e-06, "loss": 0.0698, "step": 40090 }, { "epoch": 4.98, "learning_rate": 9.026515623054898e-06, "loss": 0.0493, "step": 40100 }, { "epoch": 4.98, "learning_rate": 9.026266650068468e-06, "loss": 0.0421, "step": 40110 }, { "epoch": 4.98, "learning_rate": 9.026017677082037e-06, "loss": 0.0845, "step": 40120 }, { "epoch": 4.98, "learning_rate": 9.025768704095607e-06, "loss": 0.0761, "step": 40130 }, { "epoch": 4.98, "learning_rate": 9.025519731109176e-06, "loss": 0.0615, "step": 40140 }, { "epoch": 4.99, "learning_rate": 9.025270758122744e-06, "loss": 0.0524, "step": 40150 }, { "epoch": 4.99, "learning_rate": 9.025021785136313e-06, "loss": 0.0445, "step": 40160 }, { "epoch": 4.99, "learning_rate": 9.024772812149883e-06, "loss": 0.0656, "step": 40170 }, { "epoch": 4.99, "learning_rate": 9.024523839163451e-06, "loss": 0.0523, "step": 40180 }, { "epoch": 4.99, "learning_rate": 9.02427486617702e-06, "loss": 0.0725, "step": 40190 }, { "epoch": 4.99, "learning_rate": 9.02402589319059e-06, "loss": 0.0683, "step": 40200 }, { "epoch": 4.99, "learning_rate": 9.023776920204159e-06, "loss": 0.0599, "step": 40210 }, { "epoch": 4.99, "learning_rate": 9.023527947217727e-06, "loss": 0.0506, "step": 40220 }, { "epoch": 5.0, "learning_rate": 9.023278974231296e-06, "loss": 0.0646, "step": 40230 }, { "epoch": 5.0, "learning_rate": 9.023030001244866e-06, "loss": 0.0639, "step": 40240 }, { "epoch": 5.0, "learning_rate": 9.022781028258434e-06, "loss": 0.0519, "step": 40250 }, { "epoch": 5.0, "learning_rate": 9.022532055272005e-06, "loss": 0.0537, "step": 40260 }, { "epoch": 5.0, "learning_rate": 9.022283082285571e-06, "loss": 0.0481, "step": 40270 }, { "epoch": 5.0, "learning_rate": 9.022034109299142e-06, "loss": 0.0688, "step": 40280 }, { "epoch": 5.0, "learning_rate": 9.02178513631271e-06, "loss": 0.0368, "step": 40290 }, { "epoch": 5.0, "learning_rate": 9.02153616332628e-06, "loss": 0.0446, "step": 40300 }, { "epoch": 5.01, "learning_rate": 9.021287190339849e-06, "loss": 0.0313, "step": 40310 }, { "epoch": 5.01, "learning_rate": 9.021038217353419e-06, "loss": 0.0472, "step": 40320 }, { "epoch": 5.01, "learning_rate": 9.020789244366986e-06, "loss": 0.0657, "step": 40330 }, { "epoch": 5.01, "learning_rate": 9.020540271380556e-06, "loss": 0.0271, "step": 40340 }, { "epoch": 5.01, "learning_rate": 9.020291298394125e-06, "loss": 0.0496, "step": 40350 }, { "epoch": 5.01, "learning_rate": 9.020042325407695e-06, "loss": 0.0503, "step": 40360 }, { "epoch": 5.01, "learning_rate": 9.019793352421263e-06, "loss": 0.0589, "step": 40370 }, { "epoch": 5.01, "learning_rate": 9.019544379434832e-06, "loss": 0.0759, "step": 40380 }, { "epoch": 5.02, "learning_rate": 9.0192954064484e-06, "loss": 0.0766, "step": 40390 }, { "epoch": 5.02, "learning_rate": 9.01904643346197e-06, "loss": 0.0496, "step": 40400 }, { "epoch": 5.02, "learning_rate": 9.01879746047554e-06, "loss": 0.0635, "step": 40410 }, { "epoch": 5.02, "learning_rate": 9.018548487489108e-06, "loss": 0.0439, "step": 40420 }, { "epoch": 5.02, "learning_rate": 9.018299514502678e-06, "loss": 0.0698, "step": 40430 }, { "epoch": 5.02, "learning_rate": 9.018050541516246e-06, "loss": 0.0716, "step": 40440 }, { "epoch": 5.02, "learning_rate": 9.017801568529815e-06, "loss": 0.0784, "step": 40450 }, { "epoch": 5.02, "learning_rate": 9.017552595543383e-06, "loss": 0.0268, "step": 40460 }, { "epoch": 5.03, "learning_rate": 9.017303622556954e-06, "loss": 0.0615, "step": 40470 }, { "epoch": 5.03, "learning_rate": 9.017054649570522e-06, "loss": 0.0532, "step": 40480 }, { "epoch": 5.03, "learning_rate": 9.016805676584092e-06, "loss": 0.0574, "step": 40490 }, { "epoch": 5.03, "learning_rate": 9.016556703597661e-06, "loss": 0.0492, "step": 40500 }, { "epoch": 5.03, "learning_rate": 9.01630773061123e-06, "loss": 0.0563, "step": 40510 }, { "epoch": 5.03, "learning_rate": 9.016058757624798e-06, "loss": 0.0486, "step": 40520 }, { "epoch": 5.03, "learning_rate": 9.015809784638368e-06, "loss": 0.0736, "step": 40530 }, { "epoch": 5.03, "learning_rate": 9.015560811651937e-06, "loss": 0.0611, "step": 40540 }, { "epoch": 5.04, "learning_rate": 9.015311838665505e-06, "loss": 0.0697, "step": 40550 }, { "epoch": 5.04, "learning_rate": 9.015062865679075e-06, "loss": 0.0484, "step": 40560 }, { "epoch": 5.04, "learning_rate": 9.014813892692644e-06, "loss": 0.0554, "step": 40570 }, { "epoch": 5.04, "learning_rate": 9.014564919706212e-06, "loss": 0.0528, "step": 40580 }, { "epoch": 5.04, "learning_rate": 9.014315946719781e-06, "loss": 0.0394, "step": 40590 }, { "epoch": 5.04, "learning_rate": 9.014066973733351e-06, "loss": 0.0619, "step": 40600 }, { "epoch": 5.04, "learning_rate": 9.01381800074692e-06, "loss": 0.0401, "step": 40610 }, { "epoch": 5.04, "learning_rate": 9.01356902776049e-06, "loss": 0.0597, "step": 40620 }, { "epoch": 5.05, "learning_rate": 9.013320054774057e-06, "loss": 0.0659, "step": 40630 }, { "epoch": 5.05, "learning_rate": 9.013071081787627e-06, "loss": 0.0407, "step": 40640 }, { "epoch": 5.05, "learning_rate": 9.012822108801195e-06, "loss": 0.0458, "step": 40650 }, { "epoch": 5.05, "learning_rate": 9.012573135814766e-06, "loss": 0.0658, "step": 40660 }, { "epoch": 5.05, "learning_rate": 9.012324162828334e-06, "loss": 0.0414, "step": 40670 }, { "epoch": 5.05, "learning_rate": 9.012075189841903e-06, "loss": 0.0753, "step": 40680 }, { "epoch": 5.05, "learning_rate": 9.011826216855471e-06, "loss": 0.0483, "step": 40690 }, { "epoch": 5.05, "learning_rate": 9.011577243869041e-06, "loss": 0.05, "step": 40700 }, { "epoch": 5.06, "learning_rate": 9.01132827088261e-06, "loss": 0.04, "step": 40710 }, { "epoch": 5.06, "learning_rate": 9.011079297896178e-06, "loss": 0.0592, "step": 40720 }, { "epoch": 5.06, "learning_rate": 9.010830324909749e-06, "loss": 0.0557, "step": 40730 }, { "epoch": 5.06, "learning_rate": 9.010581351923317e-06, "loss": 0.0437, "step": 40740 }, { "epoch": 5.06, "learning_rate": 9.010332378936886e-06, "loss": 0.0476, "step": 40750 }, { "epoch": 5.06, "learning_rate": 9.010083405950454e-06, "loss": 0.0516, "step": 40760 }, { "epoch": 5.06, "learning_rate": 9.009834432964024e-06, "loss": 0.067, "step": 40770 }, { "epoch": 5.06, "learning_rate": 9.009585459977593e-06, "loss": 0.0593, "step": 40780 }, { "epoch": 5.07, "learning_rate": 9.009336486991163e-06, "loss": 0.0763, "step": 40790 }, { "epoch": 5.07, "learning_rate": 9.00908751400473e-06, "loss": 0.076, "step": 40800 }, { "epoch": 5.07, "learning_rate": 9.0088385410183e-06, "loss": 0.0555, "step": 40810 }, { "epoch": 5.07, "learning_rate": 9.008589568031869e-06, "loss": 0.052, "step": 40820 }, { "epoch": 5.07, "learning_rate": 9.008340595045439e-06, "loss": 0.0579, "step": 40830 }, { "epoch": 5.07, "learning_rate": 9.008091622059007e-06, "loss": 0.0511, "step": 40840 }, { "epoch": 5.07, "learning_rate": 9.007842649072578e-06, "loss": 0.0576, "step": 40850 }, { "epoch": 5.07, "learning_rate": 9.007593676086144e-06, "loss": 0.0319, "step": 40860 }, { "epoch": 5.08, "learning_rate": 9.007344703099715e-06, "loss": 0.0597, "step": 40870 }, { "epoch": 5.08, "learning_rate": 9.007095730113283e-06, "loss": 0.0705, "step": 40880 }, { "epoch": 5.08, "learning_rate": 9.006846757126853e-06, "loss": 0.0666, "step": 40890 }, { "epoch": 5.08, "learning_rate": 9.006597784140422e-06, "loss": 0.0536, "step": 40900 }, { "epoch": 5.08, "learning_rate": 9.00634881115399e-06, "loss": 0.054, "step": 40910 }, { "epoch": 5.08, "learning_rate": 9.006099838167559e-06, "loss": 0.068, "step": 40920 }, { "epoch": 5.08, "learning_rate": 9.005850865181129e-06, "loss": 0.0659, "step": 40930 }, { "epoch": 5.08, "learning_rate": 9.005601892194698e-06, "loss": 0.0441, "step": 40940 }, { "epoch": 5.09, "learning_rate": 9.005352919208266e-06, "loss": 0.0703, "step": 40950 }, { "epoch": 5.09, "learning_rate": 9.005103946221836e-06, "loss": 0.0547, "step": 40960 }, { "epoch": 5.09, "learning_rate": 9.004854973235405e-06, "loss": 0.0614, "step": 40970 }, { "epoch": 5.09, "learning_rate": 9.004606000248973e-06, "loss": 0.0647, "step": 40980 }, { "epoch": 5.09, "learning_rate": 9.004357027262542e-06, "loss": 0.0633, "step": 40990 }, { "epoch": 5.09, "learning_rate": 9.004108054276112e-06, "loss": 0.0575, "step": 41000 }, { "epoch": 5.09, "learning_rate": 9.00385908128968e-06, "loss": 0.0575, "step": 41010 }, { "epoch": 5.09, "learning_rate": 9.00361010830325e-06, "loss": 0.0618, "step": 41020 }, { "epoch": 5.09, "learning_rate": 9.00336113531682e-06, "loss": 0.0467, "step": 41030 }, { "epoch": 5.1, "learning_rate": 9.003112162330388e-06, "loss": 0.0473, "step": 41040 }, { "epoch": 5.1, "learning_rate": 9.002863189343956e-06, "loss": 0.0542, "step": 41050 }, { "epoch": 5.1, "learning_rate": 9.002614216357527e-06, "loss": 0.0335, "step": 41060 }, { "epoch": 5.1, "learning_rate": 9.002365243371095e-06, "loss": 0.0759, "step": 41070 }, { "epoch": 5.1, "learning_rate": 9.002116270384664e-06, "loss": 0.0674, "step": 41080 }, { "epoch": 5.1, "learning_rate": 9.001867297398234e-06, "loss": 0.0512, "step": 41090 }, { "epoch": 5.1, "learning_rate": 9.001618324411802e-06, "loss": 0.0437, "step": 41100 }, { "epoch": 5.1, "learning_rate": 9.001369351425371e-06, "loss": 0.0588, "step": 41110 }, { "epoch": 5.11, "learning_rate": 9.00112037843894e-06, "loss": 0.0493, "step": 41120 }, { "epoch": 5.11, "learning_rate": 9.00087140545251e-06, "loss": 0.0559, "step": 41130 }, { "epoch": 5.11, "learning_rate": 9.000622432466078e-06, "loss": 0.0514, "step": 41140 }, { "epoch": 5.11, "learning_rate": 9.000373459479648e-06, "loss": 0.0644, "step": 41150 }, { "epoch": 5.11, "learning_rate": 9.000124486493215e-06, "loss": 0.028, "step": 41160 }, { "epoch": 5.11, "learning_rate": 8.999875513506785e-06, "loss": 0.0561, "step": 41170 }, { "epoch": 5.11, "learning_rate": 8.999626540520354e-06, "loss": 0.0584, "step": 41180 }, { "epoch": 5.11, "learning_rate": 8.999377567533924e-06, "loss": 0.0482, "step": 41190 }, { "epoch": 5.12, "learning_rate": 8.999128594547493e-06, "loss": 0.0466, "step": 41200 }, { "epoch": 5.12, "learning_rate": 8.998879621561061e-06, "loss": 0.0539, "step": 41210 }, { "epoch": 5.12, "learning_rate": 8.99863064857463e-06, "loss": 0.0685, "step": 41220 }, { "epoch": 5.12, "learning_rate": 8.9983816755882e-06, "loss": 0.075, "step": 41230 }, { "epoch": 5.12, "learning_rate": 8.998132702601768e-06, "loss": 0.0493, "step": 41240 }, { "epoch": 5.12, "learning_rate": 8.997883729615337e-06, "loss": 0.0587, "step": 41250 }, { "epoch": 5.12, "learning_rate": 8.997634756628907e-06, "loss": 0.0507, "step": 41260 }, { "epoch": 5.12, "learning_rate": 8.997385783642476e-06, "loss": 0.0555, "step": 41270 }, { "epoch": 5.13, "learning_rate": 8.997136810656044e-06, "loss": 0.0451, "step": 41280 }, { "epoch": 5.13, "learning_rate": 8.996887837669613e-06, "loss": 0.0342, "step": 41290 }, { "epoch": 5.13, "learning_rate": 8.996638864683183e-06, "loss": 0.0546, "step": 41300 }, { "epoch": 5.13, "learning_rate": 8.996389891696751e-06, "loss": 0.0462, "step": 41310 }, { "epoch": 5.13, "learning_rate": 8.996140918710322e-06, "loss": 0.083, "step": 41320 }, { "epoch": 5.13, "learning_rate": 8.99589194572389e-06, "loss": 0.0622, "step": 41330 }, { "epoch": 5.13, "learning_rate": 8.995642972737459e-06, "loss": 0.047, "step": 41340 }, { "epoch": 5.13, "learning_rate": 8.995393999751027e-06, "loss": 0.0526, "step": 41350 }, { "epoch": 5.14, "learning_rate": 8.995145026764597e-06, "loss": 0.0657, "step": 41360 }, { "epoch": 5.14, "learning_rate": 8.994896053778166e-06, "loss": 0.0675, "step": 41370 }, { "epoch": 5.14, "learning_rate": 8.994647080791736e-06, "loss": 0.0544, "step": 41380 }, { "epoch": 5.14, "learning_rate": 8.994398107805303e-06, "loss": 0.0495, "step": 41390 }, { "epoch": 5.14, "learning_rate": 8.994149134818873e-06, "loss": 0.0403, "step": 41400 }, { "epoch": 5.14, "learning_rate": 8.993900161832442e-06, "loss": 0.062, "step": 41410 }, { "epoch": 5.14, "learning_rate": 8.993651188846012e-06, "loss": 0.0539, "step": 41420 }, { "epoch": 5.14, "learning_rate": 8.99340221585958e-06, "loss": 0.0568, "step": 41430 }, { "epoch": 5.15, "learning_rate": 8.993153242873149e-06, "loss": 0.0524, "step": 41440 }, { "epoch": 5.15, "learning_rate": 8.992904269886717e-06, "loss": 0.0768, "step": 41450 }, { "epoch": 5.15, "learning_rate": 8.992655296900288e-06, "loss": 0.055, "step": 41460 }, { "epoch": 5.15, "learning_rate": 8.992406323913856e-06, "loss": 0.0588, "step": 41470 }, { "epoch": 5.15, "learning_rate": 8.992157350927425e-06, "loss": 0.0801, "step": 41480 }, { "epoch": 5.15, "learning_rate": 8.991908377940995e-06, "loss": 0.0534, "step": 41490 }, { "epoch": 5.15, "learning_rate": 8.991659404954563e-06, "loss": 0.0542, "step": 41500 }, { "epoch": 5.15, "learning_rate": 8.991410431968132e-06, "loss": 0.0537, "step": 41510 }, { "epoch": 5.16, "learning_rate": 8.9911614589817e-06, "loss": 0.0528, "step": 41520 }, { "epoch": 5.16, "learning_rate": 8.99091248599527e-06, "loss": 0.0681, "step": 41530 }, { "epoch": 5.16, "learning_rate": 8.990663513008839e-06, "loss": 0.0466, "step": 41540 }, { "epoch": 5.16, "learning_rate": 8.99041454002241e-06, "loss": 0.0527, "step": 41550 }, { "epoch": 5.16, "learning_rate": 8.990165567035978e-06, "loss": 0.0428, "step": 41560 }, { "epoch": 5.16, "learning_rate": 8.989916594049546e-06, "loss": 0.0566, "step": 41570 }, { "epoch": 5.16, "learning_rate": 8.989667621063115e-06, "loss": 0.0508, "step": 41580 }, { "epoch": 5.16, "learning_rate": 8.989418648076685e-06, "loss": 0.0539, "step": 41590 }, { "epoch": 5.17, "learning_rate": 8.989169675090254e-06, "loss": 0.0575, "step": 41600 }, { "epoch": 5.17, "learning_rate": 8.988920702103822e-06, "loss": 0.0376, "step": 41610 }, { "epoch": 5.17, "learning_rate": 8.988671729117392e-06, "loss": 0.0421, "step": 41620 }, { "epoch": 5.17, "learning_rate": 8.98842275613096e-06, "loss": 0.0486, "step": 41630 }, { "epoch": 5.17, "learning_rate": 8.98817378314453e-06, "loss": 0.0506, "step": 41640 }, { "epoch": 5.17, "learning_rate": 8.987924810158098e-06, "loss": 0.055, "step": 41650 }, { "epoch": 5.17, "learning_rate": 8.987675837171668e-06, "loss": 0.0434, "step": 41660 }, { "epoch": 5.17, "learning_rate": 8.987426864185237e-06, "loss": 0.0563, "step": 41670 }, { "epoch": 5.18, "learning_rate": 8.987177891198807e-06, "loss": 0.0557, "step": 41680 }, { "epoch": 5.18, "learning_rate": 8.986928918212374e-06, "loss": 0.0504, "step": 41690 }, { "epoch": 5.18, "learning_rate": 8.986679945225944e-06, "loss": 0.0313, "step": 41700 }, { "epoch": 5.18, "learning_rate": 8.986430972239512e-06, "loss": 0.0591, "step": 41710 }, { "epoch": 5.18, "learning_rate": 8.986181999253083e-06, "loss": 0.0862, "step": 41720 }, { "epoch": 5.18, "learning_rate": 8.985933026266651e-06, "loss": 0.07, "step": 41730 }, { "epoch": 5.18, "learning_rate": 8.98568405328022e-06, "loss": 0.0604, "step": 41740 }, { "epoch": 5.18, "learning_rate": 8.985435080293788e-06, "loss": 0.0719, "step": 41750 }, { "epoch": 5.19, "learning_rate": 8.985186107307358e-06, "loss": 0.036, "step": 41760 }, { "epoch": 5.19, "learning_rate": 8.984937134320927e-06, "loss": 0.0602, "step": 41770 }, { "epoch": 5.19, "learning_rate": 8.984688161334495e-06, "loss": 0.0514, "step": 41780 }, { "epoch": 5.19, "learning_rate": 8.984439188348065e-06, "loss": 0.049, "step": 41790 }, { "epoch": 5.19, "learning_rate": 8.984190215361634e-06, "loss": 0.0448, "step": 41800 }, { "epoch": 5.19, "learning_rate": 8.983941242375203e-06, "loss": 0.063, "step": 41810 }, { "epoch": 5.19, "learning_rate": 8.983692269388771e-06, "loss": 0.0793, "step": 41820 }, { "epoch": 5.19, "learning_rate": 8.983443296402341e-06, "loss": 0.0446, "step": 41830 }, { "epoch": 5.2, "learning_rate": 8.98319432341591e-06, "loss": 0.0486, "step": 41840 }, { "epoch": 5.2, "learning_rate": 8.98294535042948e-06, "loss": 0.0511, "step": 41850 }, { "epoch": 5.2, "learning_rate": 8.982696377443048e-06, "loss": 0.0405, "step": 41860 }, { "epoch": 5.2, "learning_rate": 8.982447404456617e-06, "loss": 0.0556, "step": 41870 }, { "epoch": 5.2, "learning_rate": 8.982198431470186e-06, "loss": 0.0516, "step": 41880 }, { "epoch": 5.2, "learning_rate": 8.981949458483756e-06, "loss": 0.0528, "step": 41890 }, { "epoch": 5.2, "learning_rate": 8.981700485497324e-06, "loss": 0.049, "step": 41900 }, { "epoch": 5.2, "learning_rate": 8.981451512510894e-06, "loss": 0.0492, "step": 41910 }, { "epoch": 5.21, "learning_rate": 8.981202539524463e-06, "loss": 0.0539, "step": 41920 }, { "epoch": 5.21, "learning_rate": 8.980953566538031e-06, "loss": 0.0625, "step": 41930 }, { "epoch": 5.21, "learning_rate": 8.9807045935516e-06, "loss": 0.0754, "step": 41940 }, { "epoch": 5.21, "learning_rate": 8.98045562056517e-06, "loss": 0.0639, "step": 41950 }, { "epoch": 5.21, "learning_rate": 8.980206647578739e-06, "loss": 0.0617, "step": 41960 }, { "epoch": 5.21, "learning_rate": 8.979957674592307e-06, "loss": 0.0445, "step": 41970 }, { "epoch": 5.21, "learning_rate": 8.979708701605877e-06, "loss": 0.0515, "step": 41980 }, { "epoch": 5.21, "learning_rate": 8.979459728619446e-06, "loss": 0.0571, "step": 41990 }, { "epoch": 5.22, "learning_rate": 8.979210755633014e-06, "loss": 0.0384, "step": 42000 }, { "epoch": 5.22, "learning_rate": 8.978961782646583e-06, "loss": 0.0394, "step": 42010 }, { "epoch": 5.22, "learning_rate": 8.978712809660153e-06, "loss": 0.0661, "step": 42020 }, { "epoch": 5.22, "learning_rate": 8.978463836673722e-06, "loss": 0.0763, "step": 42030 }, { "epoch": 5.22, "learning_rate": 8.97821486368729e-06, "loss": 0.0521, "step": 42040 }, { "epoch": 5.22, "learning_rate": 8.977965890700859e-06, "loss": 0.0446, "step": 42050 }, { "epoch": 5.22, "learning_rate": 8.977716917714429e-06, "loss": 0.0582, "step": 42060 }, { "epoch": 5.22, "learning_rate": 8.977467944727997e-06, "loss": 0.0633, "step": 42070 }, { "epoch": 5.23, "learning_rate": 8.977218971741568e-06, "loss": 0.0703, "step": 42080 }, { "epoch": 5.23, "learning_rate": 8.976969998755136e-06, "loss": 0.0388, "step": 42090 }, { "epoch": 5.23, "learning_rate": 8.976721025768705e-06, "loss": 0.0555, "step": 42100 }, { "epoch": 5.23, "learning_rate": 8.976472052782273e-06, "loss": 0.0363, "step": 42110 }, { "epoch": 5.23, "learning_rate": 8.976223079795843e-06, "loss": 0.0699, "step": 42120 }, { "epoch": 5.23, "learning_rate": 8.975974106809412e-06, "loss": 0.0428, "step": 42130 }, { "epoch": 5.23, "learning_rate": 8.97572513382298e-06, "loss": 0.0591, "step": 42140 }, { "epoch": 5.23, "learning_rate": 8.97547616083655e-06, "loss": 0.0492, "step": 42150 }, { "epoch": 5.24, "learning_rate": 8.97522718785012e-06, "loss": 0.0339, "step": 42160 }, { "epoch": 5.24, "learning_rate": 8.974978214863688e-06, "loss": 0.0506, "step": 42170 }, { "epoch": 5.24, "learning_rate": 8.974729241877256e-06, "loss": 0.0674, "step": 42180 }, { "epoch": 5.24, "learning_rate": 8.974480268890826e-06, "loss": 0.0759, "step": 42190 }, { "epoch": 5.24, "learning_rate": 8.974231295904395e-06, "loss": 0.0578, "step": 42200 }, { "epoch": 5.24, "learning_rate": 8.973982322917965e-06, "loss": 0.0403, "step": 42210 }, { "epoch": 5.24, "learning_rate": 8.973733349931532e-06, "loss": 0.0467, "step": 42220 }, { "epoch": 5.24, "learning_rate": 8.973484376945102e-06, "loss": 0.0403, "step": 42230 }, { "epoch": 5.25, "learning_rate": 8.97323540395867e-06, "loss": 0.0519, "step": 42240 }, { "epoch": 5.25, "learning_rate": 8.972986430972241e-06, "loss": 0.0677, "step": 42250 }, { "epoch": 5.25, "learning_rate": 8.97273745798581e-06, "loss": 0.0439, "step": 42260 }, { "epoch": 5.25, "learning_rate": 8.972488484999378e-06, "loss": 0.0478, "step": 42270 }, { "epoch": 5.25, "learning_rate": 8.972239512012946e-06, "loss": 0.039, "step": 42280 }, { "epoch": 5.25, "learning_rate": 8.971990539026517e-06, "loss": 0.0467, "step": 42290 }, { "epoch": 5.25, "learning_rate": 8.971741566040085e-06, "loss": 0.0443, "step": 42300 }, { "epoch": 5.25, "learning_rate": 8.971492593053654e-06, "loss": 0.0602, "step": 42310 }, { "epoch": 5.26, "learning_rate": 8.971243620067224e-06, "loss": 0.0572, "step": 42320 }, { "epoch": 5.26, "learning_rate": 8.970994647080792e-06, "loss": 0.0461, "step": 42330 }, { "epoch": 5.26, "learning_rate": 8.970745674094361e-06, "loss": 0.0781, "step": 42340 }, { "epoch": 5.26, "learning_rate": 8.97049670110793e-06, "loss": 0.0592, "step": 42350 }, { "epoch": 5.26, "learning_rate": 8.9702477281215e-06, "loss": 0.0554, "step": 42360 }, { "epoch": 5.26, "learning_rate": 8.969998755135068e-06, "loss": 0.0493, "step": 42370 }, { "epoch": 5.26, "learning_rate": 8.969749782148638e-06, "loss": 0.0435, "step": 42380 }, { "epoch": 5.26, "learning_rate": 8.969500809162207e-06, "loss": 0.0594, "step": 42390 }, { "epoch": 5.27, "learning_rate": 8.969251836175775e-06, "loss": 0.0422, "step": 42400 }, { "epoch": 5.27, "learning_rate": 8.969002863189344e-06, "loss": 0.0622, "step": 42410 }, { "epoch": 5.27, "learning_rate": 8.968753890202914e-06, "loss": 0.0378, "step": 42420 }, { "epoch": 5.27, "learning_rate": 8.968504917216483e-06, "loss": 0.0643, "step": 42430 }, { "epoch": 5.27, "learning_rate": 8.968255944230053e-06, "loss": 0.0907, "step": 42440 }, { "epoch": 5.27, "learning_rate": 8.968006971243621e-06, "loss": 0.0634, "step": 42450 }, { "epoch": 5.27, "learning_rate": 8.96775799825719e-06, "loss": 0.0573, "step": 42460 }, { "epoch": 5.27, "learning_rate": 8.967509025270758e-06, "loss": 0.0504, "step": 42470 }, { "epoch": 5.28, "learning_rate": 8.967260052284329e-06, "loss": 0.0513, "step": 42480 }, { "epoch": 5.28, "learning_rate": 8.967011079297897e-06, "loss": 0.0438, "step": 42490 }, { "epoch": 5.28, "learning_rate": 8.966762106311466e-06, "loss": 0.0364, "step": 42500 }, { "epoch": 5.28, "learning_rate": 8.966513133325036e-06, "loss": 0.0353, "step": 42510 }, { "epoch": 5.28, "learning_rate": 8.966264160338604e-06, "loss": 0.0751, "step": 42520 }, { "epoch": 5.28, "learning_rate": 8.966015187352173e-06, "loss": 0.0586, "step": 42530 }, { "epoch": 5.28, "learning_rate": 8.965766214365741e-06, "loss": 0.0626, "step": 42540 }, { "epoch": 5.28, "learning_rate": 8.965517241379312e-06, "loss": 0.0598, "step": 42550 }, { "epoch": 5.28, "learning_rate": 8.96526826839288e-06, "loss": 0.0536, "step": 42560 }, { "epoch": 5.29, "learning_rate": 8.96501929540645e-06, "loss": 0.0489, "step": 42570 }, { "epoch": 5.29, "learning_rate": 8.964770322420017e-06, "loss": 0.0455, "step": 42580 }, { "epoch": 5.29, "learning_rate": 8.964521349433587e-06, "loss": 0.0606, "step": 42590 }, { "epoch": 5.29, "learning_rate": 8.964272376447156e-06, "loss": 0.0449, "step": 42600 }, { "epoch": 5.29, "learning_rate": 8.964023403460726e-06, "loss": 0.0508, "step": 42610 }, { "epoch": 5.29, "learning_rate": 8.963774430474295e-06, "loss": 0.0538, "step": 42620 }, { "epoch": 5.29, "learning_rate": 8.963525457487863e-06, "loss": 0.0722, "step": 42630 }, { "epoch": 5.29, "learning_rate": 8.963276484501432e-06, "loss": 0.07, "step": 42640 }, { "epoch": 5.3, "learning_rate": 8.963027511515002e-06, "loss": 0.0474, "step": 42650 }, { "epoch": 5.3, "learning_rate": 8.96277853852857e-06, "loss": 0.0644, "step": 42660 }, { "epoch": 5.3, "learning_rate": 8.962529565542139e-06, "loss": 0.0434, "step": 42670 }, { "epoch": 5.3, "learning_rate": 8.962280592555709e-06, "loss": 0.0373, "step": 42680 }, { "epoch": 5.3, "learning_rate": 8.962031619569278e-06, "loss": 0.0465, "step": 42690 }, { "epoch": 5.3, "learning_rate": 8.961782646582846e-06, "loss": 0.0573, "step": 42700 }, { "epoch": 5.3, "learning_rate": 8.961533673596415e-06, "loss": 0.0539, "step": 42710 }, { "epoch": 5.3, "learning_rate": 8.961284700609985e-06, "loss": 0.0434, "step": 42720 }, { "epoch": 5.31, "learning_rate": 8.961035727623553e-06, "loss": 0.0455, "step": 42730 }, { "epoch": 5.31, "learning_rate": 8.960786754637124e-06, "loss": 0.0663, "step": 42740 }, { "epoch": 5.31, "learning_rate": 8.96053778165069e-06, "loss": 0.0482, "step": 42750 }, { "epoch": 5.31, "learning_rate": 8.96028880866426e-06, "loss": 0.0507, "step": 42760 }, { "epoch": 5.31, "learning_rate": 8.96003983567783e-06, "loss": 0.034, "step": 42770 }, { "epoch": 5.31, "learning_rate": 8.9597908626914e-06, "loss": 0.0439, "step": 42780 }, { "epoch": 5.31, "learning_rate": 8.959541889704968e-06, "loss": 0.0792, "step": 42790 }, { "epoch": 5.31, "learning_rate": 8.959292916718536e-06, "loss": 0.0428, "step": 42800 }, { "epoch": 5.32, "learning_rate": 8.959043943732105e-06, "loss": 0.0543, "step": 42810 }, { "epoch": 5.32, "learning_rate": 8.958794970745675e-06, "loss": 0.0554, "step": 42820 }, { "epoch": 5.32, "learning_rate": 8.958545997759244e-06, "loss": 0.0575, "step": 42830 }, { "epoch": 5.32, "learning_rate": 8.958297024772812e-06, "loss": 0.0455, "step": 42840 }, { "epoch": 5.32, "learning_rate": 8.958048051786382e-06, "loss": 0.0575, "step": 42850 }, { "epoch": 5.32, "learning_rate": 8.957799078799951e-06, "loss": 0.0611, "step": 42860 }, { "epoch": 5.32, "learning_rate": 8.95755010581352e-06, "loss": 0.0595, "step": 42870 }, { "epoch": 5.32, "learning_rate": 8.957301132827088e-06, "loss": 0.0452, "step": 42880 }, { "epoch": 5.33, "learning_rate": 8.957052159840658e-06, "loss": 0.0788, "step": 42890 }, { "epoch": 5.33, "learning_rate": 8.956803186854227e-06, "loss": 0.0407, "step": 42900 }, { "epoch": 5.33, "learning_rate": 8.956554213867797e-06, "loss": 0.0721, "step": 42910 }, { "epoch": 5.33, "learning_rate": 8.956305240881365e-06, "loss": 0.0535, "step": 42920 }, { "epoch": 5.33, "learning_rate": 8.956056267894934e-06, "loss": 0.0638, "step": 42930 }, { "epoch": 5.33, "learning_rate": 8.955807294908502e-06, "loss": 0.0443, "step": 42940 }, { "epoch": 5.33, "learning_rate": 8.955558321922073e-06, "loss": 0.0611, "step": 42950 }, { "epoch": 5.33, "learning_rate": 8.955309348935641e-06, "loss": 0.0585, "step": 42960 }, { "epoch": 5.34, "learning_rate": 8.955060375949211e-06, "loss": 0.0603, "step": 42970 }, { "epoch": 5.34, "learning_rate": 8.95481140296278e-06, "loss": 0.0408, "step": 42980 }, { "epoch": 5.34, "learning_rate": 8.954562429976348e-06, "loss": 0.0375, "step": 42990 }, { "epoch": 5.34, "learning_rate": 8.954313456989917e-06, "loss": 0.0486, "step": 43000 }, { "epoch": 5.34, "learning_rate": 8.954064484003487e-06, "loss": 0.0429, "step": 43010 }, { "epoch": 5.34, "learning_rate": 8.953815511017056e-06, "loss": 0.0667, "step": 43020 }, { "epoch": 5.34, "learning_rate": 8.953566538030624e-06, "loss": 0.0756, "step": 43030 }, { "epoch": 5.34, "learning_rate": 8.953317565044194e-06, "loss": 0.053, "step": 43040 }, { "epoch": 5.35, "learning_rate": 8.953068592057763e-06, "loss": 0.0803, "step": 43050 }, { "epoch": 5.35, "learning_rate": 8.952819619071331e-06, "loss": 0.0688, "step": 43060 }, { "epoch": 5.35, "learning_rate": 8.9525706460849e-06, "loss": 0.0571, "step": 43070 }, { "epoch": 5.35, "learning_rate": 8.95232167309847e-06, "loss": 0.0641, "step": 43080 }, { "epoch": 5.35, "learning_rate": 8.952072700112039e-06, "loss": 0.0561, "step": 43090 }, { "epoch": 5.35, "learning_rate": 8.951823727125609e-06, "loss": 0.0556, "step": 43100 }, { "epoch": 5.35, "learning_rate": 8.951574754139176e-06, "loss": 0.0391, "step": 43110 }, { "epoch": 5.35, "learning_rate": 8.951325781152746e-06, "loss": 0.0314, "step": 43120 }, { "epoch": 5.36, "learning_rate": 8.951076808166314e-06, "loss": 0.0613, "step": 43130 }, { "epoch": 5.36, "learning_rate": 8.950827835179885e-06, "loss": 0.0383, "step": 43140 }, { "epoch": 5.36, "learning_rate": 8.950578862193453e-06, "loss": 0.0573, "step": 43150 }, { "epoch": 5.36, "learning_rate": 8.950329889207022e-06, "loss": 0.0589, "step": 43160 }, { "epoch": 5.36, "learning_rate": 8.95008091622059e-06, "loss": 0.0553, "step": 43170 }, { "epoch": 5.36, "learning_rate": 8.94983194323416e-06, "loss": 0.0754, "step": 43180 }, { "epoch": 5.36, "learning_rate": 8.949582970247729e-06, "loss": 0.0592, "step": 43190 }, { "epoch": 5.36, "learning_rate": 8.949333997261297e-06, "loss": 0.0591, "step": 43200 }, { "epoch": 5.37, "learning_rate": 8.949085024274868e-06, "loss": 0.0538, "step": 43210 }, { "epoch": 5.37, "learning_rate": 8.948836051288436e-06, "loss": 0.0516, "step": 43220 }, { "epoch": 5.37, "learning_rate": 8.948587078302005e-06, "loss": 0.0614, "step": 43230 }, { "epoch": 5.37, "learning_rate": 8.948338105315573e-06, "loss": 0.0404, "step": 43240 }, { "epoch": 5.37, "learning_rate": 8.948089132329143e-06, "loss": 0.0471, "step": 43250 }, { "epoch": 5.37, "learning_rate": 8.947840159342712e-06, "loss": 0.0389, "step": 43260 }, { "epoch": 5.37, "learning_rate": 8.947591186356282e-06, "loss": 0.0623, "step": 43270 }, { "epoch": 5.37, "learning_rate": 8.94734221336985e-06, "loss": 0.0478, "step": 43280 }, { "epoch": 5.38, "learning_rate": 8.947093240383419e-06, "loss": 0.0931, "step": 43290 }, { "epoch": 5.38, "learning_rate": 8.946844267396988e-06, "loss": 0.0622, "step": 43300 }, { "epoch": 5.38, "learning_rate": 8.946595294410558e-06, "loss": 0.0449, "step": 43310 }, { "epoch": 5.38, "learning_rate": 8.946346321424126e-06, "loss": 0.0396, "step": 43320 }, { "epoch": 5.38, "learning_rate": 8.946097348437695e-06, "loss": 0.0531, "step": 43330 }, { "epoch": 5.38, "learning_rate": 8.945848375451263e-06, "loss": 0.0516, "step": 43340 }, { "epoch": 5.38, "learning_rate": 8.945599402464834e-06, "loss": 0.0486, "step": 43350 }, { "epoch": 5.38, "learning_rate": 8.945350429478402e-06, "loss": 0.0555, "step": 43360 }, { "epoch": 5.39, "learning_rate": 8.94510145649197e-06, "loss": 0.053, "step": 43370 }, { "epoch": 5.39, "learning_rate": 8.94485248350554e-06, "loss": 0.0492, "step": 43380 }, { "epoch": 5.39, "learning_rate": 8.94460351051911e-06, "loss": 0.0766, "step": 43390 }, { "epoch": 5.39, "learning_rate": 8.944354537532678e-06, "loss": 0.0389, "step": 43400 }, { "epoch": 5.39, "learning_rate": 8.944105564546246e-06, "loss": 0.0637, "step": 43410 }, { "epoch": 5.39, "learning_rate": 8.943856591559817e-06, "loss": 0.0357, "step": 43420 }, { "epoch": 5.39, "learning_rate": 8.943607618573385e-06, "loss": 0.0538, "step": 43430 }, { "epoch": 5.39, "learning_rate": 8.943358645586955e-06, "loss": 0.036, "step": 43440 }, { "epoch": 5.4, "learning_rate": 8.943109672600524e-06, "loss": 0.0525, "step": 43450 }, { "epoch": 5.4, "learning_rate": 8.942860699614092e-06, "loss": 0.0553, "step": 43460 }, { "epoch": 5.4, "learning_rate": 8.942611726627661e-06, "loss": 0.0385, "step": 43470 }, { "epoch": 5.4, "learning_rate": 8.942362753641231e-06, "loss": 0.0749, "step": 43480 }, { "epoch": 5.4, "learning_rate": 8.9421137806548e-06, "loss": 0.0305, "step": 43490 }, { "epoch": 5.4, "learning_rate": 8.94186480766837e-06, "loss": 0.0576, "step": 43500 }, { "epoch": 5.4, "learning_rate": 8.941615834681938e-06, "loss": 0.0305, "step": 43510 }, { "epoch": 5.4, "learning_rate": 8.941366861695507e-06, "loss": 0.0418, "step": 43520 }, { "epoch": 5.41, "learning_rate": 8.941117888709075e-06, "loss": 0.0612, "step": 43530 }, { "epoch": 5.41, "learning_rate": 8.940868915722646e-06, "loss": 0.0471, "step": 43540 }, { "epoch": 5.41, "learning_rate": 8.940619942736214e-06, "loss": 0.0487, "step": 43550 }, { "epoch": 5.41, "learning_rate": 8.940370969749783e-06, "loss": 0.0411, "step": 43560 }, { "epoch": 5.41, "learning_rate": 8.940121996763353e-06, "loss": 0.0672, "step": 43570 }, { "epoch": 5.41, "learning_rate": 8.93987302377692e-06, "loss": 0.0819, "step": 43580 }, { "epoch": 5.41, "learning_rate": 8.93962405079049e-06, "loss": 0.0477, "step": 43590 }, { "epoch": 5.41, "learning_rate": 8.939375077804058e-06, "loss": 0.0403, "step": 43600 }, { "epoch": 5.42, "learning_rate": 8.939126104817629e-06, "loss": 0.0311, "step": 43610 }, { "epoch": 5.42, "learning_rate": 8.938877131831197e-06, "loss": 0.0652, "step": 43620 }, { "epoch": 5.42, "learning_rate": 8.938628158844767e-06, "loss": 0.0503, "step": 43630 }, { "epoch": 5.42, "learning_rate": 8.938379185858334e-06, "loss": 0.0826, "step": 43640 }, { "epoch": 5.42, "learning_rate": 8.938130212871904e-06, "loss": 0.0666, "step": 43650 }, { "epoch": 5.42, "learning_rate": 8.937881239885473e-06, "loss": 0.0494, "step": 43660 }, { "epoch": 5.42, "learning_rate": 8.937632266899043e-06, "loss": 0.0734, "step": 43670 }, { "epoch": 5.42, "learning_rate": 8.937383293912612e-06, "loss": 0.0826, "step": 43680 }, { "epoch": 5.43, "learning_rate": 8.93713432092618e-06, "loss": 0.0592, "step": 43690 }, { "epoch": 5.43, "learning_rate": 8.936885347939749e-06, "loss": 0.0551, "step": 43700 }, { "epoch": 5.43, "learning_rate": 8.936636374953319e-06, "loss": 0.031, "step": 43710 }, { "epoch": 5.43, "learning_rate": 8.936387401966887e-06, "loss": 0.073, "step": 43720 }, { "epoch": 5.43, "learning_rate": 8.936138428980456e-06, "loss": 0.0619, "step": 43730 }, { "epoch": 5.43, "learning_rate": 8.935889455994026e-06, "loss": 0.0713, "step": 43740 }, { "epoch": 5.43, "learning_rate": 8.935640483007595e-06, "loss": 0.0418, "step": 43750 }, { "epoch": 5.43, "learning_rate": 8.935391510021163e-06, "loss": 0.0394, "step": 43760 }, { "epoch": 5.44, "learning_rate": 8.935142537034732e-06, "loss": 0.0517, "step": 43770 }, { "epoch": 5.44, "learning_rate": 8.934893564048302e-06, "loss": 0.0591, "step": 43780 }, { "epoch": 5.44, "learning_rate": 8.93464459106187e-06, "loss": 0.0718, "step": 43790 }, { "epoch": 5.44, "learning_rate": 8.93439561807544e-06, "loss": 0.0374, "step": 43800 }, { "epoch": 5.44, "learning_rate": 8.934146645089009e-06, "loss": 0.0533, "step": 43810 }, { "epoch": 5.44, "learning_rate": 8.933897672102578e-06, "loss": 0.0524, "step": 43820 }, { "epoch": 5.44, "learning_rate": 8.933648699116146e-06, "loss": 0.0583, "step": 43830 }, { "epoch": 5.44, "learning_rate": 8.933399726129716e-06, "loss": 0.0419, "step": 43840 }, { "epoch": 5.45, "learning_rate": 8.933150753143285e-06, "loss": 0.0426, "step": 43850 }, { "epoch": 5.45, "learning_rate": 8.932901780156853e-06, "loss": 0.0444, "step": 43860 }, { "epoch": 5.45, "learning_rate": 8.932652807170424e-06, "loss": 0.0752, "step": 43870 }, { "epoch": 5.45, "learning_rate": 8.932403834183992e-06, "loss": 0.0711, "step": 43880 }, { "epoch": 5.45, "learning_rate": 8.93215486119756e-06, "loss": 0.0591, "step": 43890 }, { "epoch": 5.45, "learning_rate": 8.931905888211129e-06, "loss": 0.0679, "step": 43900 }, { "epoch": 5.45, "learning_rate": 8.9316569152247e-06, "loss": 0.0574, "step": 43910 }, { "epoch": 5.45, "learning_rate": 8.931407942238268e-06, "loss": 0.0658, "step": 43920 }, { "epoch": 5.46, "learning_rate": 8.931158969251838e-06, "loss": 0.0738, "step": 43930 }, { "epoch": 5.46, "learning_rate": 8.930909996265405e-06, "loss": 0.0799, "step": 43940 }, { "epoch": 5.46, "learning_rate": 8.930661023278975e-06, "loss": 0.0397, "step": 43950 }, { "epoch": 5.46, "learning_rate": 8.930412050292544e-06, "loss": 0.0378, "step": 43960 }, { "epoch": 5.46, "learning_rate": 8.930163077306114e-06, "loss": 0.0504, "step": 43970 }, { "epoch": 5.46, "learning_rate": 8.929914104319682e-06, "loss": 0.0614, "step": 43980 }, { "epoch": 5.46, "learning_rate": 8.92966513133325e-06, "loss": 0.0479, "step": 43990 }, { "epoch": 5.46, "learning_rate": 8.92941615834682e-06, "loss": 0.0718, "step": 44000 }, { "epoch": 5.47, "learning_rate": 8.92916718536039e-06, "loss": 0.0451, "step": 44010 }, { "epoch": 5.47, "learning_rate": 8.928918212373958e-06, "loss": 0.081, "step": 44020 }, { "epoch": 5.47, "learning_rate": 8.928669239387528e-06, "loss": 0.0672, "step": 44030 }, { "epoch": 5.47, "learning_rate": 8.928420266401097e-06, "loss": 0.07, "step": 44040 }, { "epoch": 5.47, "learning_rate": 8.928171293414665e-06, "loss": 0.0473, "step": 44050 }, { "epoch": 5.47, "learning_rate": 8.927922320428234e-06, "loss": 0.0471, "step": 44060 }, { "epoch": 5.47, "learning_rate": 8.927673347441802e-06, "loss": 0.0697, "step": 44070 }, { "epoch": 5.47, "learning_rate": 8.927424374455373e-06, "loss": 0.0446, "step": 44080 }, { "epoch": 5.47, "learning_rate": 8.927175401468941e-06, "loss": 0.0459, "step": 44090 }, { "epoch": 5.48, "learning_rate": 8.926926428482511e-06, "loss": 0.0574, "step": 44100 }, { "epoch": 5.48, "learning_rate": 8.926677455496078e-06, "loss": 0.052, "step": 44110 }, { "epoch": 5.48, "learning_rate": 8.926428482509648e-06, "loss": 0.0737, "step": 44120 }, { "epoch": 5.48, "learning_rate": 8.926179509523217e-06, "loss": 0.0519, "step": 44130 }, { "epoch": 5.48, "learning_rate": 8.925930536536787e-06, "loss": 0.0429, "step": 44140 }, { "epoch": 5.48, "learning_rate": 8.925681563550356e-06, "loss": 0.0508, "step": 44150 }, { "epoch": 5.48, "learning_rate": 8.925432590563926e-06, "loss": 0.0544, "step": 44160 }, { "epoch": 5.48, "learning_rate": 8.925183617577493e-06, "loss": 0.0508, "step": 44170 }, { "epoch": 5.49, "learning_rate": 8.924934644591063e-06, "loss": 0.0681, "step": 44180 }, { "epoch": 5.49, "learning_rate": 8.924685671604631e-06, "loss": 0.0356, "step": 44190 }, { "epoch": 5.49, "learning_rate": 8.924436698618201e-06, "loss": 0.0371, "step": 44200 }, { "epoch": 5.49, "learning_rate": 8.92418772563177e-06, "loss": 0.0565, "step": 44210 }, { "epoch": 5.49, "learning_rate": 8.923938752645339e-06, "loss": 0.0559, "step": 44220 }, { "epoch": 5.49, "learning_rate": 8.923689779658907e-06, "loss": 0.0697, "step": 44230 }, { "epoch": 5.49, "learning_rate": 8.923440806672477e-06, "loss": 0.0432, "step": 44240 }, { "epoch": 5.49, "learning_rate": 8.923191833686046e-06, "loss": 0.0604, "step": 44250 }, { "epoch": 5.5, "learning_rate": 8.922942860699614e-06, "loss": 0.0546, "step": 44260 }, { "epoch": 5.5, "learning_rate": 8.922693887713184e-06, "loss": 0.0705, "step": 44270 }, { "epoch": 5.5, "learning_rate": 8.922444914726753e-06, "loss": 0.0579, "step": 44280 }, { "epoch": 5.5, "learning_rate": 8.922195941740322e-06, "loss": 0.0432, "step": 44290 }, { "epoch": 5.5, "learning_rate": 8.92194696875389e-06, "loss": 0.0451, "step": 44300 }, { "epoch": 5.5, "learning_rate": 8.92169799576746e-06, "loss": 0.0523, "step": 44310 }, { "epoch": 5.5, "learning_rate": 8.921449022781029e-06, "loss": 0.0583, "step": 44320 }, { "epoch": 5.5, "learning_rate": 8.921200049794599e-06, "loss": 0.0627, "step": 44330 }, { "epoch": 5.51, "learning_rate": 8.920951076808167e-06, "loss": 0.0512, "step": 44340 }, { "epoch": 5.51, "learning_rate": 8.920702103821736e-06, "loss": 0.0507, "step": 44350 }, { "epoch": 5.51, "learning_rate": 8.920453130835304e-06, "loss": 0.0565, "step": 44360 }, { "epoch": 5.51, "learning_rate": 8.920204157848875e-06, "loss": 0.0401, "step": 44370 }, { "epoch": 5.51, "learning_rate": 8.919955184862443e-06, "loss": 0.0606, "step": 44380 }, { "epoch": 5.51, "learning_rate": 8.919706211876012e-06, "loss": 0.0428, "step": 44390 }, { "epoch": 5.51, "learning_rate": 8.919457238889582e-06, "loss": 0.0509, "step": 44400 }, { "epoch": 5.51, "learning_rate": 8.91920826590315e-06, "loss": 0.058, "step": 44410 }, { "epoch": 5.52, "learning_rate": 8.918959292916719e-06, "loss": 0.0631, "step": 44420 }, { "epoch": 5.52, "learning_rate": 8.918710319930287e-06, "loss": 0.0719, "step": 44430 }, { "epoch": 5.52, "learning_rate": 8.918461346943858e-06, "loss": 0.045, "step": 44440 }, { "epoch": 5.52, "learning_rate": 8.918212373957426e-06, "loss": 0.052, "step": 44450 }, { "epoch": 5.52, "learning_rate": 8.917963400970996e-06, "loss": 0.0359, "step": 44460 }, { "epoch": 5.52, "learning_rate": 8.917714427984563e-06, "loss": 0.0606, "step": 44470 }, { "epoch": 5.52, "learning_rate": 8.917465454998133e-06, "loss": 0.0561, "step": 44480 }, { "epoch": 5.52, "learning_rate": 8.917216482011702e-06, "loss": 0.064, "step": 44490 }, { "epoch": 5.53, "learning_rate": 8.916967509025272e-06, "loss": 0.0529, "step": 44500 }, { "epoch": 5.53, "learning_rate": 8.91671853603884e-06, "loss": 0.04, "step": 44510 }, { "epoch": 5.53, "learning_rate": 8.916469563052411e-06, "loss": 0.0579, "step": 44520 }, { "epoch": 5.53, "learning_rate": 8.916220590065978e-06, "loss": 0.0777, "step": 44530 }, { "epoch": 5.53, "learning_rate": 8.915971617079548e-06, "loss": 0.0441, "step": 44540 }, { "epoch": 5.53, "learning_rate": 8.915722644093116e-06, "loss": 0.0563, "step": 44550 }, { "epoch": 5.53, "learning_rate": 8.915473671106685e-06, "loss": 0.0614, "step": 44560 }, { "epoch": 5.53, "learning_rate": 8.915224698120255e-06, "loss": 0.0561, "step": 44570 }, { "epoch": 5.54, "learning_rate": 8.914975725133824e-06, "loss": 0.0739, "step": 44580 }, { "epoch": 5.54, "learning_rate": 8.914726752147392e-06, "loss": 0.0644, "step": 44590 }, { "epoch": 5.54, "learning_rate": 8.91447777916096e-06, "loss": 0.0548, "step": 44600 }, { "epoch": 5.54, "learning_rate": 8.914228806174531e-06, "loss": 0.045, "step": 44610 }, { "epoch": 5.54, "learning_rate": 8.9139798331881e-06, "loss": 0.0727, "step": 44620 }, { "epoch": 5.54, "learning_rate": 8.91373086020167e-06, "loss": 0.0631, "step": 44630 }, { "epoch": 5.54, "learning_rate": 8.913481887215236e-06, "loss": 0.0644, "step": 44640 }, { "epoch": 5.54, "learning_rate": 8.913232914228807e-06, "loss": 0.0458, "step": 44650 }, { "epoch": 5.55, "learning_rate": 8.912983941242375e-06, "loss": 0.0629, "step": 44660 }, { "epoch": 5.55, "learning_rate": 8.912734968255945e-06, "loss": 0.0513, "step": 44670 }, { "epoch": 5.55, "learning_rate": 8.912485995269514e-06, "loss": 0.0576, "step": 44680 }, { "epoch": 5.55, "learning_rate": 8.912237022283084e-06, "loss": 0.0554, "step": 44690 }, { "epoch": 5.55, "learning_rate": 8.911988049296651e-06, "loss": 0.0705, "step": 44700 }, { "epoch": 5.55, "learning_rate": 8.911739076310221e-06, "loss": 0.031, "step": 44710 }, { "epoch": 5.55, "learning_rate": 8.91149010332379e-06, "loss": 0.0642, "step": 44720 }, { "epoch": 5.55, "learning_rate": 8.91124113033736e-06, "loss": 0.0695, "step": 44730 }, { "epoch": 5.56, "learning_rate": 8.910992157350928e-06, "loss": 0.056, "step": 44740 }, { "epoch": 5.56, "learning_rate": 8.910743184364497e-06, "loss": 0.0623, "step": 44750 }, { "epoch": 5.56, "learning_rate": 8.910494211378065e-06, "loss": 0.0382, "step": 44760 }, { "epoch": 5.56, "learning_rate": 8.910245238391636e-06, "loss": 0.053, "step": 44770 }, { "epoch": 5.56, "learning_rate": 8.909996265405204e-06, "loss": 0.069, "step": 44780 }, { "epoch": 5.56, "learning_rate": 8.909747292418773e-06, "loss": 0.0572, "step": 44790 }, { "epoch": 5.56, "learning_rate": 8.909498319432343e-06, "loss": 0.048, "step": 44800 }, { "epoch": 5.56, "learning_rate": 8.909249346445911e-06, "loss": 0.0666, "step": 44810 }, { "epoch": 5.57, "learning_rate": 8.90900037345948e-06, "loss": 0.0384, "step": 44820 }, { "epoch": 5.57, "learning_rate": 8.908751400473048e-06, "loss": 0.0648, "step": 44830 }, { "epoch": 5.57, "learning_rate": 8.908502427486619e-06, "loss": 0.053, "step": 44840 }, { "epoch": 5.57, "learning_rate": 8.908253454500187e-06, "loss": 0.0518, "step": 44850 }, { "epoch": 5.57, "learning_rate": 8.908004481513757e-06, "loss": 0.0326, "step": 44860 }, { "epoch": 5.57, "learning_rate": 8.907755508527326e-06, "loss": 0.0334, "step": 44870 }, { "epoch": 5.57, "learning_rate": 8.907506535540894e-06, "loss": 0.0362, "step": 44880 }, { "epoch": 5.57, "learning_rate": 8.907257562554463e-06, "loss": 0.0778, "step": 44890 }, { "epoch": 5.58, "learning_rate": 8.907008589568033e-06, "loss": 0.0401, "step": 44900 }, { "epoch": 5.58, "learning_rate": 8.906759616581602e-06, "loss": 0.0495, "step": 44910 }, { "epoch": 5.58, "learning_rate": 8.90651064359517e-06, "loss": 0.0578, "step": 44920 }, { "epoch": 5.58, "learning_rate": 8.90626167060874e-06, "loss": 0.0663, "step": 44930 }, { "epoch": 5.58, "learning_rate": 8.906012697622309e-06, "loss": 0.0568, "step": 44940 }, { "epoch": 5.58, "learning_rate": 8.905763724635877e-06, "loss": 0.0254, "step": 44950 }, { "epoch": 5.58, "learning_rate": 8.905514751649446e-06, "loss": 0.0419, "step": 44960 }, { "epoch": 5.58, "learning_rate": 8.905265778663016e-06, "loss": 0.0784, "step": 44970 }, { "epoch": 5.59, "learning_rate": 8.905016805676585e-06, "loss": 0.0693, "step": 44980 }, { "epoch": 5.59, "learning_rate": 8.904767832690155e-06, "loss": 0.0232, "step": 44990 }, { "epoch": 5.59, "learning_rate": 8.904518859703722e-06, "loss": 0.0379, "step": 45000 }, { "epoch": 5.59, "eval_bleu": 89.3398, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7603, "eval_has_error_f1": 0.6634, "eval_loss": 0.05368762090802193, "eval_runtime": 1359.4735, "eval_samples_per_second": 2.941, "eval_steps_per_second": 0.736, "step": 45000 }, { "epoch": 5.59, "learning_rate": 8.904269886717292e-06, "loss": 0.0525, "step": 45010 }, { "epoch": 5.59, "learning_rate": 8.90402091373086e-06, "loss": 0.0497, "step": 45020 }, { "epoch": 5.59, "learning_rate": 8.90377194074443e-06, "loss": 0.034, "step": 45030 }, { "epoch": 5.59, "learning_rate": 8.903522967757999e-06, "loss": 0.0423, "step": 45040 }, { "epoch": 5.59, "learning_rate": 8.903273994771568e-06, "loss": 0.0425, "step": 45050 }, { "epoch": 5.6, "learning_rate": 8.903025021785136e-06, "loss": 0.0855, "step": 45060 }, { "epoch": 5.6, "learning_rate": 8.902776048798706e-06, "loss": 0.0756, "step": 45070 }, { "epoch": 5.6, "learning_rate": 8.902527075812275e-06, "loss": 0.0349, "step": 45080 }, { "epoch": 5.6, "learning_rate": 8.902278102825843e-06, "loss": 0.0513, "step": 45090 }, { "epoch": 5.6, "learning_rate": 8.902029129839414e-06, "loss": 0.032, "step": 45100 }, { "epoch": 5.6, "learning_rate": 8.901780156852982e-06, "loss": 0.0594, "step": 45110 }, { "epoch": 5.6, "learning_rate": 8.90153118386655e-06, "loss": 0.0525, "step": 45120 }, { "epoch": 5.6, "learning_rate": 8.90128221088012e-06, "loss": 0.0778, "step": 45130 }, { "epoch": 5.61, "learning_rate": 8.90103323789369e-06, "loss": 0.0493, "step": 45140 }, { "epoch": 5.61, "learning_rate": 8.900784264907258e-06, "loss": 0.0529, "step": 45150 }, { "epoch": 5.61, "learning_rate": 8.900535291920828e-06, "loss": 0.034, "step": 45160 }, { "epoch": 5.61, "learning_rate": 8.900286318934397e-06, "loss": 0.0628, "step": 45170 }, { "epoch": 5.61, "learning_rate": 8.900037345947965e-06, "loss": 0.0451, "step": 45180 }, { "epoch": 5.61, "learning_rate": 8.899788372961534e-06, "loss": 0.0802, "step": 45190 }, { "epoch": 5.61, "learning_rate": 8.899539399975104e-06, "loss": 0.0547, "step": 45200 }, { "epoch": 5.61, "learning_rate": 8.899290426988672e-06, "loss": 0.0331, "step": 45210 }, { "epoch": 5.62, "learning_rate": 8.899041454002243e-06, "loss": 0.0739, "step": 45220 }, { "epoch": 5.62, "learning_rate": 8.898792481015811e-06, "loss": 0.0605, "step": 45230 }, { "epoch": 5.62, "learning_rate": 8.89854350802938e-06, "loss": 0.0489, "step": 45240 }, { "epoch": 5.62, "learning_rate": 8.898294535042948e-06, "loss": 0.0402, "step": 45250 }, { "epoch": 5.62, "learning_rate": 8.898045562056518e-06, "loss": 0.041, "step": 45260 }, { "epoch": 5.62, "learning_rate": 8.897796589070087e-06, "loss": 0.045, "step": 45270 }, { "epoch": 5.62, "learning_rate": 8.897547616083655e-06, "loss": 0.065, "step": 45280 }, { "epoch": 5.62, "learning_rate": 8.897298643097224e-06, "loss": 0.0752, "step": 45290 }, { "epoch": 5.63, "learning_rate": 8.897049670110794e-06, "loss": 0.0519, "step": 45300 }, { "epoch": 5.63, "learning_rate": 8.896800697124363e-06, "loss": 0.0322, "step": 45310 }, { "epoch": 5.63, "learning_rate": 8.896551724137931e-06, "loss": 0.0504, "step": 45320 }, { "epoch": 5.63, "learning_rate": 8.896302751151501e-06, "loss": 0.0455, "step": 45330 }, { "epoch": 5.63, "learning_rate": 8.89605377816507e-06, "loss": 0.0414, "step": 45340 }, { "epoch": 5.63, "learning_rate": 8.895804805178638e-06, "loss": 0.0754, "step": 45350 }, { "epoch": 5.63, "learning_rate": 8.895555832192207e-06, "loss": 0.0534, "step": 45360 }, { "epoch": 5.63, "learning_rate": 8.895306859205777e-06, "loss": 0.0513, "step": 45370 }, { "epoch": 5.64, "learning_rate": 8.895057886219346e-06, "loss": 0.042, "step": 45380 }, { "epoch": 5.64, "learning_rate": 8.894808913232916e-06, "loss": 0.0353, "step": 45390 }, { "epoch": 5.64, "learning_rate": 8.894559940246484e-06, "loss": 0.0527, "step": 45400 }, { "epoch": 5.64, "learning_rate": 8.894310967260053e-06, "loss": 0.0693, "step": 45410 }, { "epoch": 5.64, "learning_rate": 8.894061994273621e-06, "loss": 0.0558, "step": 45420 }, { "epoch": 5.64, "learning_rate": 8.893813021287192e-06, "loss": 0.0726, "step": 45430 }, { "epoch": 5.64, "learning_rate": 8.89356404830076e-06, "loss": 0.0464, "step": 45440 }, { "epoch": 5.64, "learning_rate": 8.893315075314329e-06, "loss": 0.0682, "step": 45450 }, { "epoch": 5.65, "learning_rate": 8.893066102327899e-06, "loss": 0.052, "step": 45460 }, { "epoch": 5.65, "learning_rate": 8.892817129341467e-06, "loss": 0.0573, "step": 45470 }, { "epoch": 5.65, "learning_rate": 8.892568156355036e-06, "loss": 0.0619, "step": 45480 }, { "epoch": 5.65, "learning_rate": 8.892319183368604e-06, "loss": 0.0564, "step": 45490 }, { "epoch": 5.65, "learning_rate": 8.892070210382175e-06, "loss": 0.0476, "step": 45500 }, { "epoch": 5.65, "learning_rate": 8.891821237395743e-06, "loss": 0.0607, "step": 45510 }, { "epoch": 5.65, "learning_rate": 8.891572264409313e-06, "loss": 0.0663, "step": 45520 }, { "epoch": 5.65, "learning_rate": 8.89132329142288e-06, "loss": 0.0486, "step": 45530 }, { "epoch": 5.65, "learning_rate": 8.89107431843645e-06, "loss": 0.0384, "step": 45540 }, { "epoch": 5.66, "learning_rate": 8.890825345450019e-06, "loss": 0.0554, "step": 45550 }, { "epoch": 5.66, "learning_rate": 8.890576372463589e-06, "loss": 0.0468, "step": 45560 }, { "epoch": 5.66, "learning_rate": 8.890327399477158e-06, "loss": 0.0569, "step": 45570 }, { "epoch": 5.66, "learning_rate": 8.890078426490726e-06, "loss": 0.0605, "step": 45580 }, { "epoch": 5.66, "learning_rate": 8.889829453504295e-06, "loss": 0.0437, "step": 45590 }, { "epoch": 5.66, "learning_rate": 8.889580480517865e-06, "loss": 0.0677, "step": 45600 }, { "epoch": 5.66, "learning_rate": 8.889331507531433e-06, "loss": 0.0398, "step": 45610 }, { "epoch": 5.66, "learning_rate": 8.889082534545002e-06, "loss": 0.0721, "step": 45620 }, { "epoch": 5.67, "learning_rate": 8.888833561558572e-06, "loss": 0.0713, "step": 45630 }, { "epoch": 5.67, "learning_rate": 8.88858458857214e-06, "loss": 0.0674, "step": 45640 }, { "epoch": 5.67, "learning_rate": 8.888335615585709e-06, "loss": 0.0672, "step": 45650 }, { "epoch": 5.67, "learning_rate": 8.888086642599278e-06, "loss": 0.0692, "step": 45660 }, { "epoch": 5.67, "learning_rate": 8.887837669612848e-06, "loss": 0.037, "step": 45670 }, { "epoch": 5.67, "learning_rate": 8.887588696626416e-06, "loss": 0.0625, "step": 45680 }, { "epoch": 5.67, "learning_rate": 8.887339723639987e-06, "loss": 0.0319, "step": 45690 }, { "epoch": 5.67, "learning_rate": 8.887090750653555e-06, "loss": 0.043, "step": 45700 }, { "epoch": 5.68, "learning_rate": 8.886841777667124e-06, "loss": 0.041, "step": 45710 }, { "epoch": 5.68, "learning_rate": 8.886592804680692e-06, "loss": 0.0675, "step": 45720 }, { "epoch": 5.68, "learning_rate": 8.886343831694262e-06, "loss": 0.0691, "step": 45730 }, { "epoch": 5.68, "learning_rate": 8.88609485870783e-06, "loss": 0.0531, "step": 45740 }, { "epoch": 5.68, "learning_rate": 8.885845885721401e-06, "loss": 0.0551, "step": 45750 }, { "epoch": 5.68, "learning_rate": 8.88559691273497e-06, "loss": 0.0716, "step": 45760 }, { "epoch": 5.68, "learning_rate": 8.885347939748538e-06, "loss": 0.0512, "step": 45770 }, { "epoch": 5.68, "learning_rate": 8.885098966762107e-06, "loss": 0.0649, "step": 45780 }, { "epoch": 5.69, "learning_rate": 8.884849993775677e-06, "loss": 0.059, "step": 45790 }, { "epoch": 5.69, "learning_rate": 8.884601020789245e-06, "loss": 0.0847, "step": 45800 }, { "epoch": 5.69, "learning_rate": 8.884352047802814e-06, "loss": 0.0386, "step": 45810 }, { "epoch": 5.69, "learning_rate": 8.884103074816384e-06, "loss": 0.0593, "step": 45820 }, { "epoch": 5.69, "learning_rate": 8.883854101829953e-06, "loss": 0.0466, "step": 45830 }, { "epoch": 5.69, "learning_rate": 8.883605128843521e-06, "loss": 0.1093, "step": 45840 }, { "epoch": 5.69, "learning_rate": 8.88335615585709e-06, "loss": 0.0586, "step": 45850 }, { "epoch": 5.69, "learning_rate": 8.88310718287066e-06, "loss": 0.044, "step": 45860 }, { "epoch": 5.7, "learning_rate": 8.882858209884228e-06, "loss": 0.0727, "step": 45870 }, { "epoch": 5.7, "learning_rate": 8.882609236897799e-06, "loss": 0.0527, "step": 45880 }, { "epoch": 5.7, "learning_rate": 8.882360263911365e-06, "loss": 0.0903, "step": 45890 }, { "epoch": 5.7, "learning_rate": 8.882111290924936e-06, "loss": 0.065, "step": 45900 }, { "epoch": 5.7, "learning_rate": 8.881862317938504e-06, "loss": 0.0353, "step": 45910 }, { "epoch": 5.7, "learning_rate": 8.881613344952074e-06, "loss": 0.0679, "step": 45920 }, { "epoch": 5.7, "learning_rate": 8.881364371965643e-06, "loss": 0.0534, "step": 45930 }, { "epoch": 5.7, "learning_rate": 8.881115398979211e-06, "loss": 0.0576, "step": 45940 }, { "epoch": 5.71, "learning_rate": 8.88086642599278e-06, "loss": 0.0447, "step": 45950 }, { "epoch": 5.71, "learning_rate": 8.88061745300635e-06, "loss": 0.0569, "step": 45960 }, { "epoch": 5.71, "learning_rate": 8.880368480019919e-06, "loss": 0.079, "step": 45970 }, { "epoch": 5.71, "learning_rate": 8.880119507033487e-06, "loss": 0.0633, "step": 45980 }, { "epoch": 5.71, "learning_rate": 8.879870534047057e-06, "loss": 0.0446, "step": 45990 }, { "epoch": 5.71, "learning_rate": 8.879621561060626e-06, "loss": 0.0479, "step": 46000 }, { "epoch": 5.71, "learning_rate": 8.879372588074194e-06, "loss": 0.048, "step": 46010 }, { "epoch": 5.71, "learning_rate": 8.879123615087763e-06, "loss": 0.0555, "step": 46020 }, { "epoch": 5.72, "learning_rate": 8.878874642101333e-06, "loss": 0.0606, "step": 46030 }, { "epoch": 5.72, "learning_rate": 8.878625669114902e-06, "loss": 0.0495, "step": 46040 }, { "epoch": 5.72, "learning_rate": 8.878376696128472e-06, "loss": 0.1122, "step": 46050 }, { "epoch": 5.72, "learning_rate": 8.878127723142039e-06, "loss": 0.0359, "step": 46060 }, { "epoch": 5.72, "learning_rate": 8.877878750155609e-06, "loss": 0.0424, "step": 46070 }, { "epoch": 5.72, "learning_rate": 8.877629777169177e-06, "loss": 0.0442, "step": 46080 }, { "epoch": 5.72, "learning_rate": 8.877380804182748e-06, "loss": 0.0556, "step": 46090 }, { "epoch": 5.72, "learning_rate": 8.877131831196316e-06, "loss": 0.0706, "step": 46100 }, { "epoch": 5.73, "learning_rate": 8.876882858209885e-06, "loss": 0.0649, "step": 46110 }, { "epoch": 5.73, "learning_rate": 8.876633885223453e-06, "loss": 0.0682, "step": 46120 }, { "epoch": 5.73, "learning_rate": 8.876384912237023e-06, "loss": 0.0363, "step": 46130 }, { "epoch": 5.73, "learning_rate": 8.876135939250592e-06, "loss": 0.0535, "step": 46140 }, { "epoch": 5.73, "learning_rate": 8.87588696626416e-06, "loss": 0.0524, "step": 46150 }, { "epoch": 5.73, "learning_rate": 8.87563799327773e-06, "loss": 0.0633, "step": 46160 }, { "epoch": 5.73, "learning_rate": 8.875389020291299e-06, "loss": 0.0691, "step": 46170 }, { "epoch": 5.73, "learning_rate": 8.875140047304868e-06, "loss": 0.0838, "step": 46180 }, { "epoch": 5.74, "learning_rate": 8.874891074318436e-06, "loss": 0.0587, "step": 46190 }, { "epoch": 5.74, "learning_rate": 8.874642101332006e-06, "loss": 0.0272, "step": 46200 }, { "epoch": 5.74, "learning_rate": 8.874393128345575e-06, "loss": 0.0601, "step": 46210 }, { "epoch": 5.74, "learning_rate": 8.874144155359145e-06, "loss": 0.0672, "step": 46220 }, { "epoch": 5.74, "learning_rate": 8.873895182372714e-06, "loss": 0.0717, "step": 46230 }, { "epoch": 5.74, "learning_rate": 8.873646209386282e-06, "loss": 0.0557, "step": 46240 }, { "epoch": 5.74, "learning_rate": 8.87339723639985e-06, "loss": 0.0658, "step": 46250 }, { "epoch": 5.74, "learning_rate": 8.87314826341342e-06, "loss": 0.0293, "step": 46260 }, { "epoch": 5.75, "learning_rate": 8.87289929042699e-06, "loss": 0.0785, "step": 46270 }, { "epoch": 5.75, "learning_rate": 8.87265031744056e-06, "loss": 0.0426, "step": 46280 }, { "epoch": 5.75, "learning_rate": 8.872401344454128e-06, "loss": 0.0574, "step": 46290 }, { "epoch": 5.75, "learning_rate": 8.872152371467697e-06, "loss": 0.0697, "step": 46300 }, { "epoch": 5.75, "learning_rate": 8.871903398481265e-06, "loss": 0.0363, "step": 46310 }, { "epoch": 5.75, "learning_rate": 8.871654425494835e-06, "loss": 0.08, "step": 46320 }, { "epoch": 5.75, "learning_rate": 8.871405452508404e-06, "loss": 0.0564, "step": 46330 }, { "epoch": 5.75, "learning_rate": 8.871156479521972e-06, "loss": 0.0495, "step": 46340 }, { "epoch": 5.76, "learning_rate": 8.870907506535542e-06, "loss": 0.0494, "step": 46350 }, { "epoch": 5.76, "learning_rate": 8.870658533549111e-06, "loss": 0.0487, "step": 46360 }, { "epoch": 5.76, "learning_rate": 8.87040956056268e-06, "loss": 0.0512, "step": 46370 }, { "epoch": 5.76, "learning_rate": 8.870160587576248e-06, "loss": 0.0715, "step": 46380 }, { "epoch": 5.76, "learning_rate": 8.869911614589818e-06, "loss": 0.0668, "step": 46390 }, { "epoch": 5.76, "learning_rate": 8.869662641603387e-06, "loss": 0.0713, "step": 46400 }, { "epoch": 5.76, "learning_rate": 8.869413668616957e-06, "loss": 0.0523, "step": 46410 }, { "epoch": 5.76, "learning_rate": 8.869164695630524e-06, "loss": 0.0493, "step": 46420 }, { "epoch": 5.77, "learning_rate": 8.868915722644094e-06, "loss": 0.051, "step": 46430 }, { "epoch": 5.77, "learning_rate": 8.868666749657663e-06, "loss": 0.0545, "step": 46440 }, { "epoch": 5.77, "learning_rate": 8.868417776671233e-06, "loss": 0.0434, "step": 46450 }, { "epoch": 5.77, "learning_rate": 8.868168803684801e-06, "loss": 0.08, "step": 46460 }, { "epoch": 5.77, "learning_rate": 8.86791983069837e-06, "loss": 0.0633, "step": 46470 }, { "epoch": 5.77, "learning_rate": 8.867670857711938e-06, "loss": 0.0489, "step": 46480 }, { "epoch": 5.77, "learning_rate": 8.867421884725508e-06, "loss": 0.0783, "step": 46490 }, { "epoch": 5.77, "learning_rate": 8.867172911739077e-06, "loss": 0.0568, "step": 46500 }, { "epoch": 5.78, "learning_rate": 8.866923938752646e-06, "loss": 0.0342, "step": 46510 }, { "epoch": 5.78, "learning_rate": 8.866674965766216e-06, "loss": 0.046, "step": 46520 }, { "epoch": 5.78, "learning_rate": 8.866425992779784e-06, "loss": 0.0498, "step": 46530 }, { "epoch": 5.78, "learning_rate": 8.866177019793353e-06, "loss": 0.0795, "step": 46540 }, { "epoch": 5.78, "learning_rate": 8.865928046806921e-06, "loss": 0.0491, "step": 46550 }, { "epoch": 5.78, "learning_rate": 8.865679073820491e-06, "loss": 0.0581, "step": 46560 }, { "epoch": 5.78, "learning_rate": 8.86543010083406e-06, "loss": 0.0516, "step": 46570 }, { "epoch": 5.78, "learning_rate": 8.86518112784763e-06, "loss": 0.0599, "step": 46580 }, { "epoch": 5.79, "learning_rate": 8.864932154861197e-06, "loss": 0.063, "step": 46590 }, { "epoch": 5.79, "learning_rate": 8.864683181874767e-06, "loss": 0.0448, "step": 46600 }, { "epoch": 5.79, "learning_rate": 8.864434208888336e-06, "loss": 0.0443, "step": 46610 }, { "epoch": 5.79, "learning_rate": 8.864185235901906e-06, "loss": 0.0733, "step": 46620 }, { "epoch": 5.79, "learning_rate": 8.863936262915474e-06, "loss": 0.0599, "step": 46630 }, { "epoch": 5.79, "learning_rate": 8.863687289929043e-06, "loss": 0.0517, "step": 46640 }, { "epoch": 5.79, "learning_rate": 8.863438316942612e-06, "loss": 0.0558, "step": 46650 }, { "epoch": 5.79, "learning_rate": 8.863189343956182e-06, "loss": 0.0406, "step": 46660 }, { "epoch": 5.8, "learning_rate": 8.86294037096975e-06, "loss": 0.0545, "step": 46670 }, { "epoch": 5.8, "learning_rate": 8.862691397983319e-06, "loss": 0.0611, "step": 46680 }, { "epoch": 5.8, "learning_rate": 8.862442424996889e-06, "loss": 0.0811, "step": 46690 }, { "epoch": 5.8, "learning_rate": 8.862193452010457e-06, "loss": 0.0454, "step": 46700 }, { "epoch": 5.8, "learning_rate": 8.861944479024026e-06, "loss": 0.0368, "step": 46710 }, { "epoch": 5.8, "learning_rate": 8.861695506037595e-06, "loss": 0.0474, "step": 46720 }, { "epoch": 5.8, "learning_rate": 8.861446533051165e-06, "loss": 0.0422, "step": 46730 }, { "epoch": 5.8, "learning_rate": 8.861197560064733e-06, "loss": 0.0704, "step": 46740 }, { "epoch": 5.81, "learning_rate": 8.860948587078303e-06, "loss": 0.0404, "step": 46750 }, { "epoch": 5.81, "learning_rate": 8.860699614091872e-06, "loss": 0.0465, "step": 46760 }, { "epoch": 5.81, "learning_rate": 8.86045064110544e-06, "loss": 0.0873, "step": 46770 }, { "epoch": 5.81, "learning_rate": 8.860201668119009e-06, "loss": 0.0673, "step": 46780 }, { "epoch": 5.81, "learning_rate": 8.85995269513258e-06, "loss": 0.0679, "step": 46790 }, { "epoch": 5.81, "learning_rate": 8.859703722146148e-06, "loss": 0.0606, "step": 46800 }, { "epoch": 5.81, "learning_rate": 8.859454749159718e-06, "loss": 0.0374, "step": 46810 }, { "epoch": 5.81, "learning_rate": 8.859205776173286e-06, "loss": 0.0453, "step": 46820 }, { "epoch": 5.82, "learning_rate": 8.858956803186855e-06, "loss": 0.0661, "step": 46830 }, { "epoch": 5.82, "learning_rate": 8.858707830200423e-06, "loss": 0.0517, "step": 46840 }, { "epoch": 5.82, "learning_rate": 8.858458857213994e-06, "loss": 0.0466, "step": 46850 }, { "epoch": 5.82, "learning_rate": 8.858209884227562e-06, "loss": 0.072, "step": 46860 }, { "epoch": 5.82, "learning_rate": 8.85796091124113e-06, "loss": 0.0596, "step": 46870 }, { "epoch": 5.82, "learning_rate": 8.857711938254701e-06, "loss": 0.0859, "step": 46880 }, { "epoch": 5.82, "learning_rate": 8.85746296526827e-06, "loss": 0.0396, "step": 46890 }, { "epoch": 5.82, "learning_rate": 8.857213992281838e-06, "loss": 0.0596, "step": 46900 }, { "epoch": 5.83, "learning_rate": 8.856965019295406e-06, "loss": 0.0594, "step": 46910 }, { "epoch": 5.83, "learning_rate": 8.856716046308977e-06, "loss": 0.0517, "step": 46920 }, { "epoch": 5.83, "learning_rate": 8.856467073322545e-06, "loss": 0.0608, "step": 46930 }, { "epoch": 5.83, "learning_rate": 8.856218100336115e-06, "loss": 0.0404, "step": 46940 }, { "epoch": 5.83, "learning_rate": 8.855969127349682e-06, "loss": 0.0442, "step": 46950 }, { "epoch": 5.83, "learning_rate": 8.855720154363252e-06, "loss": 0.042, "step": 46960 }, { "epoch": 5.83, "learning_rate": 8.855471181376821e-06, "loss": 0.0889, "step": 46970 }, { "epoch": 5.83, "learning_rate": 8.855222208390391e-06, "loss": 0.0786, "step": 46980 }, { "epoch": 5.84, "learning_rate": 8.85497323540396e-06, "loss": 0.0866, "step": 46990 }, { "epoch": 5.84, "learning_rate": 8.854724262417528e-06, "loss": 0.0504, "step": 47000 }, { "epoch": 5.84, "learning_rate": 8.854475289431097e-06, "loss": 0.0445, "step": 47010 }, { "epoch": 5.84, "learning_rate": 8.854226316444667e-06, "loss": 0.0539, "step": 47020 }, { "epoch": 5.84, "learning_rate": 8.853977343458235e-06, "loss": 0.0563, "step": 47030 }, { "epoch": 5.84, "learning_rate": 8.853728370471804e-06, "loss": 0.0573, "step": 47040 }, { "epoch": 5.84, "learning_rate": 8.853479397485374e-06, "loss": 0.0711, "step": 47050 }, { "epoch": 5.84, "learning_rate": 8.853230424498943e-06, "loss": 0.0481, "step": 47060 }, { "epoch": 5.84, "learning_rate": 8.852981451512511e-06, "loss": 0.0454, "step": 47070 }, { "epoch": 5.85, "learning_rate": 8.85273247852608e-06, "loss": 0.0392, "step": 47080 }, { "epoch": 5.85, "learning_rate": 8.85248350553965e-06, "loss": 0.0466, "step": 47090 }, { "epoch": 5.85, "learning_rate": 8.852234532553218e-06, "loss": 0.098, "step": 47100 }, { "epoch": 5.85, "learning_rate": 8.851985559566789e-06, "loss": 0.0521, "step": 47110 }, { "epoch": 5.85, "learning_rate": 8.851736586580357e-06, "loss": 0.073, "step": 47120 }, { "epoch": 5.85, "learning_rate": 8.851487613593926e-06, "loss": 0.0605, "step": 47130 }, { "epoch": 5.85, "learning_rate": 8.851238640607494e-06, "loss": 0.0548, "step": 47140 }, { "epoch": 5.85, "learning_rate": 8.850989667621064e-06, "loss": 0.0609, "step": 47150 }, { "epoch": 5.86, "learning_rate": 8.850740694634633e-06, "loss": 0.0453, "step": 47160 }, { "epoch": 5.86, "learning_rate": 8.850491721648201e-06, "loss": 0.0529, "step": 47170 }, { "epoch": 5.86, "learning_rate": 8.850242748661772e-06, "loss": 0.0407, "step": 47180 }, { "epoch": 5.86, "learning_rate": 8.84999377567534e-06, "loss": 0.0821, "step": 47190 }, { "epoch": 5.86, "learning_rate": 8.849744802688909e-06, "loss": 0.0521, "step": 47200 }, { "epoch": 5.86, "learning_rate": 8.849495829702477e-06, "loss": 0.0576, "step": 47210 }, { "epoch": 5.86, "learning_rate": 8.849246856716047e-06, "loss": 0.0311, "step": 47220 }, { "epoch": 5.86, "learning_rate": 8.848997883729616e-06, "loss": 0.0655, "step": 47230 }, { "epoch": 5.87, "learning_rate": 8.848748910743184e-06, "loss": 0.0461, "step": 47240 }, { "epoch": 5.87, "learning_rate": 8.848499937756753e-06, "loss": 0.0544, "step": 47250 }, { "epoch": 5.87, "learning_rate": 8.848250964770323e-06, "loss": 0.0362, "step": 47260 }, { "epoch": 5.87, "learning_rate": 8.848001991783892e-06, "loss": 0.0722, "step": 47270 }, { "epoch": 5.87, "learning_rate": 8.847753018797462e-06, "loss": 0.0542, "step": 47280 }, { "epoch": 5.87, "learning_rate": 8.84750404581103e-06, "loss": 0.0598, "step": 47290 }, { "epoch": 5.87, "learning_rate": 8.847255072824599e-06, "loss": 0.0433, "step": 47300 }, { "epoch": 5.87, "learning_rate": 8.847006099838167e-06, "loss": 0.0537, "step": 47310 }, { "epoch": 5.88, "learning_rate": 8.846757126851738e-06, "loss": 0.0583, "step": 47320 }, { "epoch": 5.88, "learning_rate": 8.846508153865306e-06, "loss": 0.0675, "step": 47330 }, { "epoch": 5.88, "learning_rate": 8.846259180878876e-06, "loss": 0.0581, "step": 47340 }, { "epoch": 5.88, "learning_rate": 8.846010207892445e-06, "loss": 0.0467, "step": 47350 }, { "epoch": 5.88, "learning_rate": 8.845761234906013e-06, "loss": 0.0314, "step": 47360 }, { "epoch": 5.88, "learning_rate": 8.845512261919582e-06, "loss": 0.0595, "step": 47370 }, { "epoch": 5.88, "learning_rate": 8.845263288933152e-06, "loss": 0.0638, "step": 47380 }, { "epoch": 5.88, "learning_rate": 8.84501431594672e-06, "loss": 0.0593, "step": 47390 }, { "epoch": 5.89, "learning_rate": 8.84476534296029e-06, "loss": 0.042, "step": 47400 }, { "epoch": 5.89, "learning_rate": 8.84451636997386e-06, "loss": 0.0554, "step": 47410 }, { "epoch": 5.89, "learning_rate": 8.844267396987428e-06, "loss": 0.0617, "step": 47420 }, { "epoch": 5.89, "learning_rate": 8.844018424000996e-06, "loss": 0.0601, "step": 47430 }, { "epoch": 5.89, "learning_rate": 8.843769451014565e-06, "loss": 0.0545, "step": 47440 }, { "epoch": 5.89, "learning_rate": 8.843520478028135e-06, "loss": 0.0309, "step": 47450 }, { "epoch": 5.89, "learning_rate": 8.843271505041704e-06, "loss": 0.0418, "step": 47460 }, { "epoch": 5.89, "learning_rate": 8.843022532055274e-06, "loss": 0.0661, "step": 47470 }, { "epoch": 5.9, "learning_rate": 8.84277355906884e-06, "loss": 0.0579, "step": 47480 }, { "epoch": 5.9, "learning_rate": 8.842524586082411e-06, "loss": 0.0739, "step": 47490 }, { "epoch": 5.9, "learning_rate": 8.84227561309598e-06, "loss": 0.0462, "step": 47500 }, { "epoch": 5.9, "learning_rate": 8.84202664010955e-06, "loss": 0.0325, "step": 47510 }, { "epoch": 5.9, "learning_rate": 8.841777667123118e-06, "loss": 0.0632, "step": 47520 }, { "epoch": 5.9, "learning_rate": 8.841528694136687e-06, "loss": 0.0445, "step": 47530 }, { "epoch": 5.9, "learning_rate": 8.841279721150255e-06, "loss": 0.0663, "step": 47540 }, { "epoch": 5.9, "learning_rate": 8.841030748163825e-06, "loss": 0.0529, "step": 47550 }, { "epoch": 5.91, "learning_rate": 8.840781775177394e-06, "loss": 0.0335, "step": 47560 }, { "epoch": 5.91, "learning_rate": 8.840532802190962e-06, "loss": 0.069, "step": 47570 }, { "epoch": 5.91, "learning_rate": 8.840283829204533e-06, "loss": 0.0697, "step": 47580 }, { "epoch": 5.91, "learning_rate": 8.840034856218101e-06, "loss": 0.0436, "step": 47590 }, { "epoch": 5.91, "learning_rate": 8.83978588323167e-06, "loss": 0.0617, "step": 47600 }, { "epoch": 5.91, "learning_rate": 8.839536910245238e-06, "loss": 0.0611, "step": 47610 }, { "epoch": 5.91, "learning_rate": 8.839287937258808e-06, "loss": 0.0728, "step": 47620 }, { "epoch": 5.91, "learning_rate": 8.839038964272377e-06, "loss": 0.061, "step": 47630 }, { "epoch": 5.92, "learning_rate": 8.838789991285947e-06, "loss": 0.0733, "step": 47640 }, { "epoch": 5.92, "learning_rate": 8.838541018299516e-06, "loss": 0.0546, "step": 47650 }, { "epoch": 5.92, "learning_rate": 8.838292045313084e-06, "loss": 0.0691, "step": 47660 }, { "epoch": 5.92, "learning_rate": 8.838043072326653e-06, "loss": 0.0891, "step": 47670 }, { "epoch": 5.92, "learning_rate": 8.837794099340223e-06, "loss": 0.0556, "step": 47680 }, { "epoch": 5.92, "learning_rate": 8.837545126353791e-06, "loss": 0.0537, "step": 47690 }, { "epoch": 5.92, "learning_rate": 8.83729615336736e-06, "loss": 0.0649, "step": 47700 }, { "epoch": 5.92, "learning_rate": 8.83704718038093e-06, "loss": 0.0686, "step": 47710 }, { "epoch": 5.93, "learning_rate": 8.836798207394499e-06, "loss": 0.0529, "step": 47720 }, { "epoch": 5.93, "learning_rate": 8.836549234408067e-06, "loss": 0.0652, "step": 47730 }, { "epoch": 5.93, "learning_rate": 8.836300261421636e-06, "loss": 0.0482, "step": 47740 }, { "epoch": 5.93, "learning_rate": 8.836051288435206e-06, "loss": 0.0466, "step": 47750 }, { "epoch": 5.93, "learning_rate": 8.835802315448774e-06, "loss": 0.0669, "step": 47760 }, { "epoch": 5.93, "learning_rate": 8.835553342462345e-06, "loss": 0.0766, "step": 47770 }, { "epoch": 5.93, "learning_rate": 8.835304369475911e-06, "loss": 0.055, "step": 47780 }, { "epoch": 5.93, "learning_rate": 8.835055396489482e-06, "loss": 0.0502, "step": 47790 }, { "epoch": 5.94, "learning_rate": 8.83480642350305e-06, "loss": 0.0605, "step": 47800 }, { "epoch": 5.94, "learning_rate": 8.83455745051662e-06, "loss": 0.0487, "step": 47810 }, { "epoch": 5.94, "learning_rate": 8.834308477530189e-06, "loss": 0.0744, "step": 47820 }, { "epoch": 5.94, "learning_rate": 8.834059504543759e-06, "loss": 0.058, "step": 47830 }, { "epoch": 5.94, "learning_rate": 8.833810531557326e-06, "loss": 0.0629, "step": 47840 }, { "epoch": 5.94, "learning_rate": 8.833561558570896e-06, "loss": 0.0453, "step": 47850 }, { "epoch": 5.94, "learning_rate": 8.833312585584465e-06, "loss": 0.0383, "step": 47860 }, { "epoch": 5.94, "learning_rate": 8.833063612598035e-06, "loss": 0.048, "step": 47870 }, { "epoch": 5.95, "learning_rate": 8.832814639611603e-06, "loss": 0.0432, "step": 47880 }, { "epoch": 5.95, "learning_rate": 8.832565666625172e-06, "loss": 0.0451, "step": 47890 }, { "epoch": 5.95, "learning_rate": 8.83231669363874e-06, "loss": 0.0508, "step": 47900 }, { "epoch": 5.95, "learning_rate": 8.83206772065231e-06, "loss": 0.0578, "step": 47910 }, { "epoch": 5.95, "learning_rate": 8.831818747665879e-06, "loss": 0.0438, "step": 47920 }, { "epoch": 5.95, "learning_rate": 8.831569774679448e-06, "loss": 0.0557, "step": 47930 }, { "epoch": 5.95, "learning_rate": 8.831320801693018e-06, "loss": 0.0426, "step": 47940 }, { "epoch": 5.95, "learning_rate": 8.831071828706586e-06, "loss": 0.0486, "step": 47950 }, { "epoch": 5.96, "learning_rate": 8.830822855720155e-06, "loss": 0.0455, "step": 47960 }, { "epoch": 5.96, "learning_rate": 8.830573882733723e-06, "loss": 0.0506, "step": 47970 }, { "epoch": 5.96, "learning_rate": 8.830324909747294e-06, "loss": 0.0641, "step": 47980 }, { "epoch": 5.96, "learning_rate": 8.830075936760862e-06, "loss": 0.0644, "step": 47990 }, { "epoch": 5.96, "learning_rate": 8.829826963774432e-06, "loss": 0.0421, "step": 48000 }, { "epoch": 5.96, "learning_rate": 8.829577990787999e-06, "loss": 0.0533, "step": 48010 }, { "epoch": 5.96, "learning_rate": 8.82932901780157e-06, "loss": 0.0419, "step": 48020 }, { "epoch": 5.96, "learning_rate": 8.829080044815138e-06, "loss": 0.0671, "step": 48030 }, { "epoch": 5.97, "learning_rate": 8.828831071828708e-06, "loss": 0.0518, "step": 48040 }, { "epoch": 5.97, "learning_rate": 8.828582098842277e-06, "loss": 0.0556, "step": 48050 }, { "epoch": 5.97, "learning_rate": 8.828333125855845e-06, "loss": 0.0447, "step": 48060 }, { "epoch": 5.97, "learning_rate": 8.828084152869414e-06, "loss": 0.047, "step": 48070 }, { "epoch": 5.97, "learning_rate": 8.827835179882984e-06, "loss": 0.0448, "step": 48080 }, { "epoch": 5.97, "learning_rate": 8.827586206896552e-06, "loss": 0.0391, "step": 48090 }, { "epoch": 5.97, "learning_rate": 8.82733723391012e-06, "loss": 0.057, "step": 48100 }, { "epoch": 5.97, "learning_rate": 8.827088260923691e-06, "loss": 0.0508, "step": 48110 }, { "epoch": 5.98, "learning_rate": 8.82683928793726e-06, "loss": 0.078, "step": 48120 }, { "epoch": 5.98, "learning_rate": 8.826590314950828e-06, "loss": 0.0622, "step": 48130 }, { "epoch": 5.98, "learning_rate": 8.826341341964397e-06, "loss": 0.0375, "step": 48140 }, { "epoch": 5.98, "learning_rate": 8.826092368977967e-06, "loss": 0.0464, "step": 48150 }, { "epoch": 5.98, "learning_rate": 8.825843395991535e-06, "loss": 0.0526, "step": 48160 }, { "epoch": 5.98, "learning_rate": 8.825594423005106e-06, "loss": 0.0374, "step": 48170 }, { "epoch": 5.98, "learning_rate": 8.825345450018674e-06, "loss": 0.049, "step": 48180 }, { "epoch": 5.98, "learning_rate": 8.825096477032243e-06, "loss": 0.0659, "step": 48190 }, { "epoch": 5.99, "learning_rate": 8.824847504045811e-06, "loss": 0.0523, "step": 48200 }, { "epoch": 5.99, "learning_rate": 8.824598531059381e-06, "loss": 0.0607, "step": 48210 }, { "epoch": 5.99, "learning_rate": 8.82434955807295e-06, "loss": 0.042, "step": 48220 }, { "epoch": 5.99, "learning_rate": 8.824100585086518e-06, "loss": 0.0514, "step": 48230 }, { "epoch": 5.99, "learning_rate": 8.823851612100089e-06, "loss": 0.0468, "step": 48240 }, { "epoch": 5.99, "learning_rate": 8.823602639113657e-06, "loss": 0.0632, "step": 48250 }, { "epoch": 5.99, "learning_rate": 8.823353666127226e-06, "loss": 0.0657, "step": 48260 }, { "epoch": 5.99, "learning_rate": 8.823104693140794e-06, "loss": 0.0667, "step": 48270 }, { "epoch": 6.0, "learning_rate": 8.822855720154364e-06, "loss": 0.0745, "step": 48280 }, { "epoch": 6.0, "learning_rate": 8.822606747167933e-06, "loss": 0.0531, "step": 48290 }, { "epoch": 6.0, "learning_rate": 8.822357774181503e-06, "loss": 0.0491, "step": 48300 }, { "epoch": 6.0, "learning_rate": 8.82210880119507e-06, "loss": 0.0445, "step": 48310 }, { "epoch": 6.0, "learning_rate": 8.82185982820864e-06, "loss": 0.0891, "step": 48320 }, { "epoch": 6.0, "learning_rate": 8.821610855222209e-06, "loss": 0.0687, "step": 48330 }, { "epoch": 6.0, "learning_rate": 8.821361882235779e-06, "loss": 0.0573, "step": 48340 }, { "epoch": 6.0, "learning_rate": 8.821112909249347e-06, "loss": 0.0465, "step": 48350 }, { "epoch": 6.01, "learning_rate": 8.820863936262917e-06, "loss": 0.044, "step": 48360 }, { "epoch": 6.01, "learning_rate": 8.820614963276484e-06, "loss": 0.0395, "step": 48370 }, { "epoch": 6.01, "learning_rate": 8.820365990290055e-06, "loss": 0.086, "step": 48380 }, { "epoch": 6.01, "learning_rate": 8.820117017303623e-06, "loss": 0.0326, "step": 48390 }, { "epoch": 6.01, "learning_rate": 8.819868044317193e-06, "loss": 0.0643, "step": 48400 }, { "epoch": 6.01, "learning_rate": 8.819619071330762e-06, "loss": 0.0246, "step": 48410 }, { "epoch": 6.01, "learning_rate": 8.81937009834433e-06, "loss": 0.056, "step": 48420 }, { "epoch": 6.01, "learning_rate": 8.819121125357899e-06, "loss": 0.0529, "step": 48430 }, { "epoch": 6.02, "learning_rate": 8.818872152371469e-06, "loss": 0.0741, "step": 48440 }, { "epoch": 6.02, "learning_rate": 8.818623179385038e-06, "loss": 0.0444, "step": 48450 }, { "epoch": 6.02, "learning_rate": 8.818374206398606e-06, "loss": 0.0584, "step": 48460 }, { "epoch": 6.02, "learning_rate": 8.818125233412176e-06, "loss": 0.0465, "step": 48470 }, { "epoch": 6.02, "learning_rate": 8.817876260425745e-06, "loss": 0.0602, "step": 48480 }, { "epoch": 6.02, "learning_rate": 8.817627287439313e-06, "loss": 0.0492, "step": 48490 }, { "epoch": 6.02, "learning_rate": 8.817378314452882e-06, "loss": 0.0381, "step": 48500 }, { "epoch": 6.02, "learning_rate": 8.817129341466452e-06, "loss": 0.037, "step": 48510 }, { "epoch": 6.03, "learning_rate": 8.81688036848002e-06, "loss": 0.0375, "step": 48520 }, { "epoch": 6.03, "learning_rate": 8.81663139549359e-06, "loss": 0.0642, "step": 48530 }, { "epoch": 6.03, "learning_rate": 8.816382422507158e-06, "loss": 0.0732, "step": 48540 }, { "epoch": 6.03, "learning_rate": 8.816133449520728e-06, "loss": 0.0753, "step": 48550 }, { "epoch": 6.03, "learning_rate": 8.815884476534296e-06, "loss": 0.06, "step": 48560 }, { "epoch": 6.03, "learning_rate": 8.815635503547866e-06, "loss": 0.0643, "step": 48570 }, { "epoch": 6.03, "learning_rate": 8.815386530561435e-06, "loss": 0.0517, "step": 48580 }, { "epoch": 6.03, "learning_rate": 8.815137557575004e-06, "loss": 0.0438, "step": 48590 }, { "epoch": 6.04, "learning_rate": 8.814888584588572e-06, "loss": 0.0725, "step": 48600 }, { "epoch": 6.04, "learning_rate": 8.814639611602142e-06, "loss": 0.0517, "step": 48610 }, { "epoch": 6.04, "learning_rate": 8.81439063861571e-06, "loss": 0.0293, "step": 48620 }, { "epoch": 6.04, "learning_rate": 8.81414166562928e-06, "loss": 0.0686, "step": 48630 }, { "epoch": 6.04, "learning_rate": 8.81389269264285e-06, "loss": 0.0502, "step": 48640 }, { "epoch": 6.04, "learning_rate": 8.813643719656418e-06, "loss": 0.0561, "step": 48650 }, { "epoch": 6.04, "learning_rate": 8.813394746669987e-06, "loss": 0.0457, "step": 48660 }, { "epoch": 6.04, "learning_rate": 8.813145773683555e-06, "loss": 0.0328, "step": 48670 }, { "epoch": 6.04, "learning_rate": 8.812896800697125e-06, "loss": 0.0396, "step": 48680 }, { "epoch": 6.05, "learning_rate": 8.812647827710694e-06, "loss": 0.0682, "step": 48690 }, { "epoch": 6.05, "learning_rate": 8.812398854724264e-06, "loss": 0.0627, "step": 48700 }, { "epoch": 6.05, "learning_rate": 8.812149881737832e-06, "loss": 0.0628, "step": 48710 }, { "epoch": 6.05, "learning_rate": 8.811900908751401e-06, "loss": 0.0317, "step": 48720 }, { "epoch": 6.05, "learning_rate": 8.81165193576497e-06, "loss": 0.0625, "step": 48730 }, { "epoch": 6.05, "learning_rate": 8.81140296277854e-06, "loss": 0.0631, "step": 48740 }, { "epoch": 6.05, "learning_rate": 8.811153989792108e-06, "loss": 0.054, "step": 48750 }, { "epoch": 6.05, "learning_rate": 8.810905016805677e-06, "loss": 0.0659, "step": 48760 }, { "epoch": 6.06, "learning_rate": 8.810656043819247e-06, "loss": 0.0462, "step": 48770 }, { "epoch": 6.06, "learning_rate": 8.810407070832815e-06, "loss": 0.0386, "step": 48780 }, { "epoch": 6.06, "learning_rate": 8.810158097846384e-06, "loss": 0.0486, "step": 48790 }, { "epoch": 6.06, "learning_rate": 8.809909124859953e-06, "loss": 0.0354, "step": 48800 }, { "epoch": 6.06, "learning_rate": 8.809660151873523e-06, "loss": 0.0391, "step": 48810 }, { "epoch": 6.06, "learning_rate": 8.809411178887091e-06, "loss": 0.0438, "step": 48820 }, { "epoch": 6.06, "learning_rate": 8.809162205900661e-06, "loss": 0.0629, "step": 48830 }, { "epoch": 6.06, "learning_rate": 8.808913232914228e-06, "loss": 0.0646, "step": 48840 }, { "epoch": 6.07, "learning_rate": 8.808664259927798e-06, "loss": 0.0574, "step": 48850 }, { "epoch": 6.07, "learning_rate": 8.808415286941367e-06, "loss": 0.0459, "step": 48860 }, { "epoch": 6.07, "learning_rate": 8.808166313954937e-06, "loss": 0.0445, "step": 48870 }, { "epoch": 6.07, "learning_rate": 8.807917340968506e-06, "loss": 0.0414, "step": 48880 }, { "epoch": 6.07, "learning_rate": 8.807668367982076e-06, "loss": 0.0666, "step": 48890 }, { "epoch": 6.07, "learning_rate": 8.807419394995643e-06, "loss": 0.0569, "step": 48900 }, { "epoch": 6.07, "learning_rate": 8.807170422009213e-06, "loss": 0.0793, "step": 48910 }, { "epoch": 6.07, "learning_rate": 8.806921449022781e-06, "loss": 0.045, "step": 48920 }, { "epoch": 6.08, "learning_rate": 8.806672476036352e-06, "loss": 0.0965, "step": 48930 }, { "epoch": 6.08, "learning_rate": 8.80642350304992e-06, "loss": 0.0425, "step": 48940 }, { "epoch": 6.08, "learning_rate": 8.806174530063489e-06, "loss": 0.0384, "step": 48950 }, { "epoch": 6.08, "learning_rate": 8.805925557077057e-06, "loss": 0.0441, "step": 48960 }, { "epoch": 6.08, "learning_rate": 8.805676584090627e-06, "loss": 0.0498, "step": 48970 }, { "epoch": 6.08, "learning_rate": 8.805427611104196e-06, "loss": 0.0848, "step": 48980 }, { "epoch": 6.08, "learning_rate": 8.805178638117764e-06, "loss": 0.0616, "step": 48990 }, { "epoch": 6.08, "learning_rate": 8.804929665131335e-06, "loss": 0.0338, "step": 49000 }, { "epoch": 6.09, "learning_rate": 8.804680692144903e-06, "loss": 0.0537, "step": 49010 }, { "epoch": 6.09, "learning_rate": 8.804431719158472e-06, "loss": 0.0357, "step": 49020 }, { "epoch": 6.09, "learning_rate": 8.80418274617204e-06, "loss": 0.0581, "step": 49030 }, { "epoch": 6.09, "learning_rate": 8.80393377318561e-06, "loss": 0.0437, "step": 49040 }, { "epoch": 6.09, "learning_rate": 8.803684800199179e-06, "loss": 0.0359, "step": 49050 }, { "epoch": 6.09, "learning_rate": 8.80343582721275e-06, "loss": 0.075, "step": 49060 }, { "epoch": 6.09, "learning_rate": 8.803186854226318e-06, "loss": 0.0439, "step": 49070 }, { "epoch": 6.09, "learning_rate": 8.802937881239886e-06, "loss": 0.0746, "step": 49080 }, { "epoch": 6.1, "learning_rate": 8.802688908253455e-06, "loss": 0.0683, "step": 49090 }, { "epoch": 6.1, "learning_rate": 8.802439935267025e-06, "loss": 0.0553, "step": 49100 }, { "epoch": 6.1, "learning_rate": 8.802190962280593e-06, "loss": 0.0588, "step": 49110 }, { "epoch": 6.1, "learning_rate": 8.801941989294162e-06, "loss": 0.07, "step": 49120 }, { "epoch": 6.1, "learning_rate": 8.801693016307732e-06, "loss": 0.0413, "step": 49130 }, { "epoch": 6.1, "learning_rate": 8.8014440433213e-06, "loss": 0.0635, "step": 49140 }, { "epoch": 6.1, "learning_rate": 8.80119507033487e-06, "loss": 0.039, "step": 49150 }, { "epoch": 6.1, "learning_rate": 8.800946097348438e-06, "loss": 0.0574, "step": 49160 }, { "epoch": 6.11, "learning_rate": 8.800697124362008e-06, "loss": 0.0463, "step": 49170 }, { "epoch": 6.11, "learning_rate": 8.800448151375576e-06, "loss": 0.0571, "step": 49180 }, { "epoch": 6.11, "learning_rate": 8.800199178389145e-06, "loss": 0.0371, "step": 49190 }, { "epoch": 6.11, "learning_rate": 8.799950205402713e-06, "loss": 0.0536, "step": 49200 }, { "epoch": 6.11, "learning_rate": 8.799701232416284e-06, "loss": 0.0374, "step": 49210 }, { "epoch": 6.11, "learning_rate": 8.799452259429852e-06, "loss": 0.043, "step": 49220 }, { "epoch": 6.11, "learning_rate": 8.799203286443422e-06, "loss": 0.0613, "step": 49230 }, { "epoch": 6.11, "learning_rate": 8.798954313456991e-06, "loss": 0.0367, "step": 49240 }, { "epoch": 6.12, "learning_rate": 8.79870534047056e-06, "loss": 0.071, "step": 49250 }, { "epoch": 6.12, "learning_rate": 8.798456367484128e-06, "loss": 0.0383, "step": 49260 }, { "epoch": 6.12, "learning_rate": 8.798207394497698e-06, "loss": 0.0573, "step": 49270 }, { "epoch": 6.12, "learning_rate": 8.797958421511267e-06, "loss": 0.0575, "step": 49280 }, { "epoch": 6.12, "learning_rate": 8.797709448524835e-06, "loss": 0.0355, "step": 49290 }, { "epoch": 6.12, "learning_rate": 8.797460475538405e-06, "loss": 0.0556, "step": 49300 }, { "epoch": 6.12, "learning_rate": 8.797211502551974e-06, "loss": 0.0523, "step": 49310 }, { "epoch": 6.12, "learning_rate": 8.796962529565542e-06, "loss": 0.0408, "step": 49320 }, { "epoch": 6.13, "learning_rate": 8.796713556579111e-06, "loss": 0.0667, "step": 49330 }, { "epoch": 6.13, "learning_rate": 8.796464583592681e-06, "loss": 0.066, "step": 49340 }, { "epoch": 6.13, "learning_rate": 8.79621561060625e-06, "loss": 0.0631, "step": 49350 }, { "epoch": 6.13, "learning_rate": 8.79596663761982e-06, "loss": 0.0319, "step": 49360 }, { "epoch": 6.13, "learning_rate": 8.795717664633387e-06, "loss": 0.0546, "step": 49370 }, { "epoch": 6.13, "learning_rate": 8.795468691646957e-06, "loss": 0.0612, "step": 49380 }, { "epoch": 6.13, "learning_rate": 8.795219718660525e-06, "loss": 0.084, "step": 49390 }, { "epoch": 6.13, "learning_rate": 8.794970745674096e-06, "loss": 0.0558, "step": 49400 }, { "epoch": 6.14, "learning_rate": 8.794721772687664e-06, "loss": 0.0394, "step": 49410 }, { "epoch": 6.14, "learning_rate": 8.794472799701234e-06, "loss": 0.0675, "step": 49420 }, { "epoch": 6.14, "learning_rate": 8.794223826714801e-06, "loss": 0.085, "step": 49430 }, { "epoch": 6.14, "learning_rate": 8.793974853728371e-06, "loss": 0.0325, "step": 49440 }, { "epoch": 6.14, "learning_rate": 8.79372588074194e-06, "loss": 0.0645, "step": 49450 }, { "epoch": 6.14, "learning_rate": 8.79347690775551e-06, "loss": 0.0498, "step": 49460 }, { "epoch": 6.14, "learning_rate": 8.793227934769079e-06, "loss": 0.0666, "step": 49470 }, { "epoch": 6.14, "learning_rate": 8.792978961782647e-06, "loss": 0.0732, "step": 49480 }, { "epoch": 6.15, "learning_rate": 8.792729988796216e-06, "loss": 0.0398, "step": 49490 }, { "epoch": 6.15, "learning_rate": 8.792481015809786e-06, "loss": 0.0589, "step": 49500 }, { "epoch": 6.15, "learning_rate": 8.792232042823354e-06, "loss": 0.0597, "step": 49510 }, { "epoch": 6.15, "learning_rate": 8.791983069836923e-06, "loss": 0.0452, "step": 49520 }, { "epoch": 6.15, "learning_rate": 8.791734096850493e-06, "loss": 0.0507, "step": 49530 }, { "epoch": 6.15, "learning_rate": 8.791485123864062e-06, "loss": 0.065, "step": 49540 }, { "epoch": 6.15, "learning_rate": 8.79123615087763e-06, "loss": 0.05, "step": 49550 }, { "epoch": 6.15, "learning_rate": 8.790987177891199e-06, "loss": 0.0498, "step": 49560 }, { "epoch": 6.16, "learning_rate": 8.790738204904769e-06, "loss": 0.058, "step": 49570 }, { "epoch": 6.16, "learning_rate": 8.790489231918337e-06, "loss": 0.0596, "step": 49580 }, { "epoch": 6.16, "learning_rate": 8.790240258931908e-06, "loss": 0.0664, "step": 49590 }, { "epoch": 6.16, "learning_rate": 8.789991285945476e-06, "loss": 0.0563, "step": 49600 }, { "epoch": 6.16, "learning_rate": 8.789742312959045e-06, "loss": 0.0471, "step": 49610 }, { "epoch": 6.16, "learning_rate": 8.789493339972613e-06, "loss": 0.0636, "step": 49620 }, { "epoch": 6.16, "learning_rate": 8.789244366986183e-06, "loss": 0.0644, "step": 49630 }, { "epoch": 6.16, "learning_rate": 8.788995393999752e-06, "loss": 0.0404, "step": 49640 }, { "epoch": 6.17, "learning_rate": 8.78874642101332e-06, "loss": 0.0491, "step": 49650 }, { "epoch": 6.17, "learning_rate": 8.78849744802689e-06, "loss": 0.0489, "step": 49660 }, { "epoch": 6.17, "learning_rate": 8.788248475040459e-06, "loss": 0.0434, "step": 49670 }, { "epoch": 6.17, "learning_rate": 8.787999502054028e-06, "loss": 0.0507, "step": 49680 }, { "epoch": 6.17, "learning_rate": 8.787750529067596e-06, "loss": 0.0414, "step": 49690 }, { "epoch": 6.17, "learning_rate": 8.787501556081166e-06, "loss": 0.0592, "step": 49700 }, { "epoch": 6.17, "learning_rate": 8.787252583094735e-06, "loss": 0.065, "step": 49710 }, { "epoch": 6.17, "learning_rate": 8.787003610108305e-06, "loss": 0.046, "step": 49720 }, { "epoch": 6.18, "learning_rate": 8.786754637121872e-06, "loss": 0.0628, "step": 49730 }, { "epoch": 6.18, "learning_rate": 8.786505664135442e-06, "loss": 0.0395, "step": 49740 }, { "epoch": 6.18, "learning_rate": 8.78625669114901e-06, "loss": 0.0772, "step": 49750 }, { "epoch": 6.18, "learning_rate": 8.786007718162581e-06, "loss": 0.0324, "step": 49760 }, { "epoch": 6.18, "learning_rate": 8.78575874517615e-06, "loss": 0.0709, "step": 49770 }, { "epoch": 6.18, "learning_rate": 8.785509772189718e-06, "loss": 0.0754, "step": 49780 }, { "epoch": 6.18, "learning_rate": 8.785260799203286e-06, "loss": 0.051, "step": 49790 }, { "epoch": 6.18, "learning_rate": 8.785011826216857e-06, "loss": 0.08, "step": 49800 }, { "epoch": 6.19, "learning_rate": 8.784762853230425e-06, "loss": 0.0517, "step": 49810 }, { "epoch": 6.19, "learning_rate": 8.784513880243994e-06, "loss": 0.0256, "step": 49820 }, { "epoch": 6.19, "learning_rate": 8.784264907257564e-06, "loss": 0.0438, "step": 49830 }, { "epoch": 6.19, "learning_rate": 8.784015934271132e-06, "loss": 0.0601, "step": 49840 }, { "epoch": 6.19, "learning_rate": 8.783766961284701e-06, "loss": 0.0662, "step": 49850 }, { "epoch": 6.19, "learning_rate": 8.78351798829827e-06, "loss": 0.0302, "step": 49860 }, { "epoch": 6.19, "learning_rate": 8.78326901531184e-06, "loss": 0.0394, "step": 49870 }, { "epoch": 6.19, "learning_rate": 8.783020042325408e-06, "loss": 0.047, "step": 49880 }, { "epoch": 6.2, "learning_rate": 8.782771069338978e-06, "loss": 0.0444, "step": 49890 }, { "epoch": 6.2, "learning_rate": 8.782522096352545e-06, "loss": 0.0438, "step": 49900 }, { "epoch": 6.2, "learning_rate": 8.782273123366115e-06, "loss": 0.0674, "step": 49910 }, { "epoch": 6.2, "learning_rate": 8.782024150379684e-06, "loss": 0.0404, "step": 49920 }, { "epoch": 6.2, "learning_rate": 8.781775177393254e-06, "loss": 0.0633, "step": 49930 }, { "epoch": 6.2, "learning_rate": 8.781526204406823e-06, "loss": 0.0727, "step": 49940 }, { "epoch": 6.2, "learning_rate": 8.781277231420393e-06, "loss": 0.0544, "step": 49950 }, { "epoch": 6.2, "learning_rate": 8.78102825843396e-06, "loss": 0.043, "step": 49960 }, { "epoch": 6.21, "learning_rate": 8.78077928544753e-06, "loss": 0.0449, "step": 49970 }, { "epoch": 6.21, "learning_rate": 8.780530312461098e-06, "loss": 0.0673, "step": 49980 }, { "epoch": 6.21, "learning_rate": 8.780281339474669e-06, "loss": 0.0553, "step": 49990 }, { "epoch": 6.21, "learning_rate": 8.780032366488237e-06, "loss": 0.0701, "step": 50000 }, { "epoch": 6.21, "eval_bleu": 89.3937, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7668, "eval_has_error_f1": 0.6813, "eval_loss": 0.05286862701177597, "eval_runtime": 1351.1128, "eval_samples_per_second": 2.959, "eval_steps_per_second": 0.74, "step": 50000 }, { "epoch": 6.21, "learning_rate": 8.779783393501806e-06, "loss": 0.0584, "step": 50010 }, { "epoch": 6.21, "learning_rate": 8.779534420515374e-06, "loss": 0.0691, "step": 50020 }, { "epoch": 6.21, "learning_rate": 8.779285447528944e-06, "loss": 0.0734, "step": 50030 }, { "epoch": 6.21, "learning_rate": 8.779036474542513e-06, "loss": 0.0597, "step": 50040 }, { "epoch": 6.22, "learning_rate": 8.778787501556081e-06, "loss": 0.0898, "step": 50050 }, { "epoch": 6.22, "learning_rate": 8.778538528569652e-06, "loss": 0.0541, "step": 50060 }, { "epoch": 6.22, "learning_rate": 8.77828955558322e-06, "loss": 0.0787, "step": 50070 }, { "epoch": 6.22, "learning_rate": 8.778040582596789e-06, "loss": 0.0525, "step": 50080 }, { "epoch": 6.22, "learning_rate": 8.777791609610357e-06, "loss": 0.0592, "step": 50090 }, { "epoch": 6.22, "learning_rate": 8.777542636623927e-06, "loss": 0.0494, "step": 50100 }, { "epoch": 6.22, "learning_rate": 8.777293663637496e-06, "loss": 0.0578, "step": 50110 }, { "epoch": 6.22, "learning_rate": 8.777044690651066e-06, "loss": 0.0938, "step": 50120 }, { "epoch": 6.22, "learning_rate": 8.776795717664635e-06, "loss": 0.0526, "step": 50130 }, { "epoch": 6.23, "learning_rate": 8.776546744678203e-06, "loss": 0.0595, "step": 50140 }, { "epoch": 6.23, "learning_rate": 8.776297771691772e-06, "loss": 0.0632, "step": 50150 }, { "epoch": 6.23, "learning_rate": 8.776048798705342e-06, "loss": 0.0335, "step": 50160 }, { "epoch": 6.23, "learning_rate": 8.77579982571891e-06, "loss": 0.0378, "step": 50170 }, { "epoch": 6.23, "learning_rate": 8.775550852732479e-06, "loss": 0.06, "step": 50180 }, { "epoch": 6.23, "learning_rate": 8.775301879746049e-06, "loss": 0.051, "step": 50190 }, { "epoch": 6.23, "learning_rate": 8.775052906759618e-06, "loss": 0.0664, "step": 50200 }, { "epoch": 6.23, "learning_rate": 8.774803933773186e-06, "loss": 0.0457, "step": 50210 }, { "epoch": 6.24, "learning_rate": 8.774554960786755e-06, "loss": 0.0452, "step": 50220 }, { "epoch": 6.24, "learning_rate": 8.774305987800325e-06, "loss": 0.0733, "step": 50230 }, { "epoch": 6.24, "learning_rate": 8.774057014813893e-06, "loss": 0.0536, "step": 50240 }, { "epoch": 6.24, "learning_rate": 8.773808041827464e-06, "loss": 0.0371, "step": 50250 }, { "epoch": 6.24, "learning_rate": 8.77355906884103e-06, "loss": 0.0352, "step": 50260 }, { "epoch": 6.24, "learning_rate": 8.7733100958546e-06, "loss": 0.0398, "step": 50270 }, { "epoch": 6.24, "learning_rate": 8.773061122868169e-06, "loss": 0.0487, "step": 50280 }, { "epoch": 6.24, "learning_rate": 8.77281214988174e-06, "loss": 0.0488, "step": 50290 }, { "epoch": 6.25, "learning_rate": 8.772563176895308e-06, "loss": 0.0541, "step": 50300 }, { "epoch": 6.25, "learning_rate": 8.772314203908876e-06, "loss": 0.068, "step": 50310 }, { "epoch": 6.25, "learning_rate": 8.772065230922445e-06, "loss": 0.0467, "step": 50320 }, { "epoch": 6.25, "learning_rate": 8.771816257936015e-06, "loss": 0.1059, "step": 50330 }, { "epoch": 6.25, "learning_rate": 8.771567284949584e-06, "loss": 0.053, "step": 50340 }, { "epoch": 6.25, "learning_rate": 8.771318311963152e-06, "loss": 0.0477, "step": 50350 }, { "epoch": 6.25, "learning_rate": 8.771069338976722e-06, "loss": 0.0517, "step": 50360 }, { "epoch": 6.25, "learning_rate": 8.77082036599029e-06, "loss": 0.04, "step": 50370 }, { "epoch": 6.26, "learning_rate": 8.77057139300386e-06, "loss": 0.0459, "step": 50380 }, { "epoch": 6.26, "learning_rate": 8.770322420017428e-06, "loss": 0.0476, "step": 50390 }, { "epoch": 6.26, "learning_rate": 8.770073447030998e-06, "loss": 0.0336, "step": 50400 }, { "epoch": 6.26, "learning_rate": 8.769824474044567e-06, "loss": 0.0334, "step": 50410 }, { "epoch": 6.26, "learning_rate": 8.769575501058137e-06, "loss": 0.0518, "step": 50420 }, { "epoch": 6.26, "learning_rate": 8.769326528071705e-06, "loss": 0.0364, "step": 50430 }, { "epoch": 6.26, "learning_rate": 8.769077555085274e-06, "loss": 0.0574, "step": 50440 }, { "epoch": 6.26, "learning_rate": 8.768828582098842e-06, "loss": 0.0501, "step": 50450 }, { "epoch": 6.27, "learning_rate": 8.768579609112413e-06, "loss": 0.0566, "step": 50460 }, { "epoch": 6.27, "learning_rate": 8.768330636125981e-06, "loss": 0.0529, "step": 50470 }, { "epoch": 6.27, "learning_rate": 8.768081663139551e-06, "loss": 0.0452, "step": 50480 }, { "epoch": 6.27, "learning_rate": 8.767832690153118e-06, "loss": 0.0365, "step": 50490 }, { "epoch": 6.27, "learning_rate": 8.767583717166688e-06, "loss": 0.0457, "step": 50500 }, { "epoch": 6.27, "learning_rate": 8.767334744180257e-06, "loss": 0.027, "step": 50510 }, { "epoch": 6.27, "learning_rate": 8.767085771193827e-06, "loss": 0.0398, "step": 50520 }, { "epoch": 6.27, "learning_rate": 8.766836798207396e-06, "loss": 0.0338, "step": 50530 }, { "epoch": 6.28, "learning_rate": 8.766587825220964e-06, "loss": 0.0346, "step": 50540 }, { "epoch": 6.28, "learning_rate": 8.766338852234533e-06, "loss": 0.0253, "step": 50550 }, { "epoch": 6.28, "learning_rate": 8.766089879248103e-06, "loss": 0.0415, "step": 50560 }, { "epoch": 6.28, "learning_rate": 8.765840906261671e-06, "loss": 0.0514, "step": 50570 }, { "epoch": 6.28, "learning_rate": 8.76559193327524e-06, "loss": 0.0799, "step": 50580 }, { "epoch": 6.28, "learning_rate": 8.76534296028881e-06, "loss": 0.0489, "step": 50590 }, { "epoch": 6.28, "learning_rate": 8.765093987302379e-06, "loss": 0.0475, "step": 50600 }, { "epoch": 6.28, "learning_rate": 8.764845014315947e-06, "loss": 0.0471, "step": 50610 }, { "epoch": 6.29, "learning_rate": 8.764596041329516e-06, "loss": 0.0548, "step": 50620 }, { "epoch": 6.29, "learning_rate": 8.764347068343086e-06, "loss": 0.0482, "step": 50630 }, { "epoch": 6.29, "learning_rate": 8.764098095356654e-06, "loss": 0.059, "step": 50640 }, { "epoch": 6.29, "learning_rate": 8.763849122370224e-06, "loss": 0.0284, "step": 50650 }, { "epoch": 6.29, "learning_rate": 8.763600149383793e-06, "loss": 0.043, "step": 50660 }, { "epoch": 6.29, "learning_rate": 8.763351176397362e-06, "loss": 0.0324, "step": 50670 }, { "epoch": 6.29, "learning_rate": 8.76310220341093e-06, "loss": 0.0747, "step": 50680 }, { "epoch": 6.29, "learning_rate": 8.7628532304245e-06, "loss": 0.0451, "step": 50690 }, { "epoch": 6.3, "learning_rate": 8.762604257438069e-06, "loss": 0.0324, "step": 50700 }, { "epoch": 6.3, "learning_rate": 8.762355284451637e-06, "loss": 0.0441, "step": 50710 }, { "epoch": 6.3, "learning_rate": 8.762106311465207e-06, "loss": 0.0472, "step": 50720 }, { "epoch": 6.3, "learning_rate": 8.761857338478776e-06, "loss": 0.043, "step": 50730 }, { "epoch": 6.3, "learning_rate": 8.761608365492345e-06, "loss": 0.064, "step": 50740 }, { "epoch": 6.3, "learning_rate": 8.761359392505913e-06, "loss": 0.0619, "step": 50750 }, { "epoch": 6.3, "learning_rate": 8.761110419519483e-06, "loss": 0.053, "step": 50760 }, { "epoch": 6.3, "learning_rate": 8.760861446533052e-06, "loss": 0.0414, "step": 50770 }, { "epoch": 6.31, "learning_rate": 8.760612473546622e-06, "loss": 0.0602, "step": 50780 }, { "epoch": 6.31, "learning_rate": 8.760363500560189e-06, "loss": 0.049, "step": 50790 }, { "epoch": 6.31, "learning_rate": 8.760114527573759e-06, "loss": 0.067, "step": 50800 }, { "epoch": 6.31, "learning_rate": 8.759865554587328e-06, "loss": 0.0393, "step": 50810 }, { "epoch": 6.31, "learning_rate": 8.759616581600898e-06, "loss": 0.0503, "step": 50820 }, { "epoch": 6.31, "learning_rate": 8.759367608614466e-06, "loss": 0.0744, "step": 50830 }, { "epoch": 6.31, "learning_rate": 8.759118635628035e-06, "loss": 0.0622, "step": 50840 }, { "epoch": 6.31, "learning_rate": 8.758869662641603e-06, "loss": 0.0392, "step": 50850 }, { "epoch": 6.32, "learning_rate": 8.758620689655173e-06, "loss": 0.0464, "step": 50860 }, { "epoch": 6.32, "learning_rate": 8.758371716668742e-06, "loss": 0.0724, "step": 50870 }, { "epoch": 6.32, "learning_rate": 8.75812274368231e-06, "loss": 0.06, "step": 50880 }, { "epoch": 6.32, "learning_rate": 8.75787377069588e-06, "loss": 0.0397, "step": 50890 }, { "epoch": 6.32, "learning_rate": 8.75762479770945e-06, "loss": 0.0376, "step": 50900 }, { "epoch": 6.32, "learning_rate": 8.757375824723018e-06, "loss": 0.0559, "step": 50910 }, { "epoch": 6.32, "learning_rate": 8.757126851736586e-06, "loss": 0.046, "step": 50920 }, { "epoch": 6.32, "learning_rate": 8.756877878750156e-06, "loss": 0.0631, "step": 50930 }, { "epoch": 6.33, "learning_rate": 8.756628905763725e-06, "loss": 0.0458, "step": 50940 }, { "epoch": 6.33, "learning_rate": 8.756379932777295e-06, "loss": 0.0509, "step": 50950 }, { "epoch": 6.33, "learning_rate": 8.756130959790864e-06, "loss": 0.0479, "step": 50960 }, { "epoch": 6.33, "learning_rate": 8.755881986804432e-06, "loss": 0.0572, "step": 50970 }, { "epoch": 6.33, "learning_rate": 8.755633013818e-06, "loss": 0.0574, "step": 50980 }, { "epoch": 6.33, "learning_rate": 8.755384040831571e-06, "loss": 0.0784, "step": 50990 }, { "epoch": 6.33, "learning_rate": 8.75513506784514e-06, "loss": 0.0361, "step": 51000 }, { "epoch": 6.33, "learning_rate": 8.75488609485871e-06, "loss": 0.0454, "step": 51010 }, { "epoch": 6.34, "learning_rate": 8.754637121872278e-06, "loss": 0.0689, "step": 51020 }, { "epoch": 6.34, "learning_rate": 8.754388148885847e-06, "loss": 0.0452, "step": 51030 }, { "epoch": 6.34, "learning_rate": 8.754139175899415e-06, "loss": 0.0582, "step": 51040 }, { "epoch": 6.34, "learning_rate": 8.753890202912985e-06, "loss": 0.0487, "step": 51050 }, { "epoch": 6.34, "learning_rate": 8.753641229926554e-06, "loss": 0.0399, "step": 51060 }, { "epoch": 6.34, "learning_rate": 8.753392256940122e-06, "loss": 0.0387, "step": 51070 }, { "epoch": 6.34, "learning_rate": 8.753143283953693e-06, "loss": 0.0654, "step": 51080 }, { "epoch": 6.34, "learning_rate": 8.752894310967261e-06, "loss": 0.0601, "step": 51090 }, { "epoch": 6.35, "learning_rate": 8.75264533798083e-06, "loss": 0.0666, "step": 51100 }, { "epoch": 6.35, "learning_rate": 8.752396364994398e-06, "loss": 0.0487, "step": 51110 }, { "epoch": 6.35, "learning_rate": 8.752147392007968e-06, "loss": 0.0389, "step": 51120 }, { "epoch": 6.35, "learning_rate": 8.751898419021537e-06, "loss": 0.0683, "step": 51130 }, { "epoch": 6.35, "learning_rate": 8.751649446035105e-06, "loss": 0.0324, "step": 51140 }, { "epoch": 6.35, "learning_rate": 8.751400473048674e-06, "loss": 0.06, "step": 51150 }, { "epoch": 6.35, "learning_rate": 8.751151500062244e-06, "loss": 0.0388, "step": 51160 }, { "epoch": 6.35, "learning_rate": 8.750902527075813e-06, "loss": 0.0491, "step": 51170 }, { "epoch": 6.36, "learning_rate": 8.750653554089383e-06, "loss": 0.0533, "step": 51180 }, { "epoch": 6.36, "learning_rate": 8.750404581102951e-06, "loss": 0.0542, "step": 51190 }, { "epoch": 6.36, "learning_rate": 8.75015560811652e-06, "loss": 0.0562, "step": 51200 }, { "epoch": 6.36, "learning_rate": 8.749906635130088e-06, "loss": 0.0673, "step": 51210 }, { "epoch": 6.36, "learning_rate": 8.749657662143659e-06, "loss": 0.0427, "step": 51220 }, { "epoch": 6.36, "learning_rate": 8.749408689157227e-06, "loss": 0.0327, "step": 51230 }, { "epoch": 6.36, "learning_rate": 8.749159716170796e-06, "loss": 0.0493, "step": 51240 }, { "epoch": 6.36, "learning_rate": 8.748910743184366e-06, "loss": 0.0511, "step": 51250 }, { "epoch": 6.37, "learning_rate": 8.748661770197934e-06, "loss": 0.0507, "step": 51260 }, { "epoch": 6.37, "learning_rate": 8.748412797211503e-06, "loss": 0.0778, "step": 51270 }, { "epoch": 6.37, "learning_rate": 8.748163824225071e-06, "loss": 0.0684, "step": 51280 }, { "epoch": 6.37, "learning_rate": 8.747914851238642e-06, "loss": 0.0306, "step": 51290 }, { "epoch": 6.37, "learning_rate": 8.74766587825221e-06, "loss": 0.0448, "step": 51300 }, { "epoch": 6.37, "learning_rate": 8.74741690526578e-06, "loss": 0.0362, "step": 51310 }, { "epoch": 6.37, "learning_rate": 8.747167932279347e-06, "loss": 0.0567, "step": 51320 }, { "epoch": 6.37, "learning_rate": 8.746918959292917e-06, "loss": 0.0735, "step": 51330 }, { "epoch": 6.38, "learning_rate": 8.746669986306486e-06, "loss": 0.0404, "step": 51340 }, { "epoch": 6.38, "learning_rate": 8.746421013320056e-06, "loss": 0.0612, "step": 51350 }, { "epoch": 6.38, "learning_rate": 8.746172040333625e-06, "loss": 0.0429, "step": 51360 }, { "epoch": 6.38, "learning_rate": 8.745923067347193e-06, "loss": 0.0529, "step": 51370 }, { "epoch": 6.38, "learning_rate": 8.745674094360762e-06, "loss": 0.0847, "step": 51380 }, { "epoch": 6.38, "learning_rate": 8.745425121374332e-06, "loss": 0.0556, "step": 51390 }, { "epoch": 6.38, "learning_rate": 8.7451761483879e-06, "loss": 0.0442, "step": 51400 }, { "epoch": 6.38, "learning_rate": 8.744927175401469e-06, "loss": 0.0445, "step": 51410 }, { "epoch": 6.39, "learning_rate": 8.74467820241504e-06, "loss": 0.0416, "step": 51420 }, { "epoch": 6.39, "learning_rate": 8.744429229428608e-06, "loss": 0.0342, "step": 51430 }, { "epoch": 6.39, "learning_rate": 8.744180256442176e-06, "loss": 0.0447, "step": 51440 }, { "epoch": 6.39, "learning_rate": 8.743931283455745e-06, "loss": 0.0539, "step": 51450 }, { "epoch": 6.39, "learning_rate": 8.743682310469315e-06, "loss": 0.0311, "step": 51460 }, { "epoch": 6.39, "learning_rate": 8.743433337482883e-06, "loss": 0.0664, "step": 51470 }, { "epoch": 6.39, "learning_rate": 8.743184364496454e-06, "loss": 0.0674, "step": 51480 }, { "epoch": 6.39, "learning_rate": 8.742935391510022e-06, "loss": 0.0773, "step": 51490 }, { "epoch": 6.4, "learning_rate": 8.74268641852359e-06, "loss": 0.0594, "step": 51500 }, { "epoch": 6.4, "learning_rate": 8.74243744553716e-06, "loss": 0.0567, "step": 51510 }, { "epoch": 6.4, "learning_rate": 8.74218847255073e-06, "loss": 0.0514, "step": 51520 }, { "epoch": 6.4, "learning_rate": 8.741939499564298e-06, "loss": 0.0408, "step": 51530 }, { "epoch": 6.4, "learning_rate": 8.741690526577868e-06, "loss": 0.0623, "step": 51540 }, { "epoch": 6.4, "learning_rate": 8.741441553591437e-06, "loss": 0.0423, "step": 51550 }, { "epoch": 6.4, "learning_rate": 8.741192580605005e-06, "loss": 0.0383, "step": 51560 }, { "epoch": 6.4, "learning_rate": 8.740943607618574e-06, "loss": 0.0495, "step": 51570 }, { "epoch": 6.41, "learning_rate": 8.740694634632144e-06, "loss": 0.084, "step": 51580 }, { "epoch": 6.41, "learning_rate": 8.740445661645712e-06, "loss": 0.0428, "step": 51590 }, { "epoch": 6.41, "learning_rate": 8.740196688659281e-06, "loss": 0.074, "step": 51600 }, { "epoch": 6.41, "learning_rate": 8.739947715672851e-06, "loss": 0.0628, "step": 51610 }, { "epoch": 6.41, "learning_rate": 8.73969874268642e-06, "loss": 0.0365, "step": 51620 }, { "epoch": 6.41, "learning_rate": 8.739449769699988e-06, "loss": 0.0584, "step": 51630 }, { "epoch": 6.41, "learning_rate": 8.739200796713557e-06, "loss": 0.0445, "step": 51640 }, { "epoch": 6.41, "learning_rate": 8.738951823727127e-06, "loss": 0.0408, "step": 51650 }, { "epoch": 6.41, "learning_rate": 8.738702850740695e-06, "loss": 0.0422, "step": 51660 }, { "epoch": 6.42, "learning_rate": 8.738453877754266e-06, "loss": 0.0313, "step": 51670 }, { "epoch": 6.42, "learning_rate": 8.738204904767832e-06, "loss": 0.0592, "step": 51680 }, { "epoch": 6.42, "learning_rate": 8.737955931781403e-06, "loss": 0.0621, "step": 51690 }, { "epoch": 6.42, "learning_rate": 8.737706958794971e-06, "loss": 0.0381, "step": 51700 }, { "epoch": 6.42, "learning_rate": 8.737457985808541e-06, "loss": 0.0346, "step": 51710 }, { "epoch": 6.42, "learning_rate": 8.73720901282211e-06, "loss": 0.0352, "step": 51720 }, { "epoch": 6.42, "learning_rate": 8.736960039835678e-06, "loss": 0.039, "step": 51730 }, { "epoch": 6.42, "learning_rate": 8.736711066849247e-06, "loss": 0.0335, "step": 51740 }, { "epoch": 6.43, "learning_rate": 8.736462093862817e-06, "loss": 0.0442, "step": 51750 }, { "epoch": 6.43, "learning_rate": 8.736213120876386e-06, "loss": 0.0443, "step": 51760 }, { "epoch": 6.43, "learning_rate": 8.735964147889954e-06, "loss": 0.0447, "step": 51770 }, { "epoch": 6.43, "learning_rate": 8.735715174903524e-06, "loss": 0.0458, "step": 51780 }, { "epoch": 6.43, "learning_rate": 8.735466201917093e-06, "loss": 0.0631, "step": 51790 }, { "epoch": 6.43, "learning_rate": 8.735217228930661e-06, "loss": 0.0621, "step": 51800 }, { "epoch": 6.43, "learning_rate": 8.73496825594423e-06, "loss": 0.0725, "step": 51810 }, { "epoch": 6.43, "learning_rate": 8.7347192829578e-06, "loss": 0.0376, "step": 51820 }, { "epoch": 6.44, "learning_rate": 8.734470309971369e-06, "loss": 0.0515, "step": 51830 }, { "epoch": 6.44, "learning_rate": 8.734221336984939e-06, "loss": 0.0425, "step": 51840 }, { "epoch": 6.44, "learning_rate": 8.733972363998506e-06, "loss": 0.0458, "step": 51850 }, { "epoch": 6.44, "learning_rate": 8.733723391012076e-06, "loss": 0.0493, "step": 51860 }, { "epoch": 6.44, "learning_rate": 8.733474418025644e-06, "loss": 0.0553, "step": 51870 }, { "epoch": 6.44, "learning_rate": 8.733225445039215e-06, "loss": 0.0534, "step": 51880 }, { "epoch": 6.44, "learning_rate": 8.732976472052783e-06, "loss": 0.0681, "step": 51890 }, { "epoch": 6.44, "learning_rate": 8.732727499066352e-06, "loss": 0.059, "step": 51900 }, { "epoch": 6.45, "learning_rate": 8.73247852607992e-06, "loss": 0.0389, "step": 51910 }, { "epoch": 6.45, "learning_rate": 8.73222955309349e-06, "loss": 0.0589, "step": 51920 }, { "epoch": 6.45, "learning_rate": 8.731980580107059e-06, "loss": 0.0442, "step": 51930 }, { "epoch": 6.45, "learning_rate": 8.731731607120627e-06, "loss": 0.0613, "step": 51940 }, { "epoch": 6.45, "learning_rate": 8.731482634134198e-06, "loss": 0.0452, "step": 51950 }, { "epoch": 6.45, "learning_rate": 8.731233661147766e-06, "loss": 0.0337, "step": 51960 }, { "epoch": 6.45, "learning_rate": 8.730984688161335e-06, "loss": 0.0368, "step": 51970 }, { "epoch": 6.45, "learning_rate": 8.730735715174903e-06, "loss": 0.0552, "step": 51980 }, { "epoch": 6.46, "learning_rate": 8.730486742188473e-06, "loss": 0.0657, "step": 51990 }, { "epoch": 6.46, "learning_rate": 8.730237769202042e-06, "loss": 0.049, "step": 52000 }, { "epoch": 6.46, "learning_rate": 8.729988796215612e-06, "loss": 0.0461, "step": 52010 }, { "epoch": 6.46, "learning_rate": 8.72973982322918e-06, "loss": 0.0494, "step": 52020 }, { "epoch": 6.46, "learning_rate": 8.729490850242749e-06, "loss": 0.0801, "step": 52030 }, { "epoch": 6.46, "learning_rate": 8.729241877256318e-06, "loss": 0.0871, "step": 52040 }, { "epoch": 6.46, "learning_rate": 8.728992904269888e-06, "loss": 0.06, "step": 52050 }, { "epoch": 6.46, "learning_rate": 8.728743931283456e-06, "loss": 0.043, "step": 52060 }, { "epoch": 6.47, "learning_rate": 8.728494958297027e-06, "loss": 0.0423, "step": 52070 }, { "epoch": 6.47, "learning_rate": 8.728245985310595e-06, "loss": 0.0901, "step": 52080 }, { "epoch": 6.47, "learning_rate": 8.727997012324164e-06, "loss": 0.028, "step": 52090 }, { "epoch": 6.47, "learning_rate": 8.727748039337732e-06, "loss": 0.072, "step": 52100 }, { "epoch": 6.47, "learning_rate": 8.727499066351302e-06, "loss": 0.0424, "step": 52110 }, { "epoch": 6.47, "learning_rate": 8.727250093364871e-06, "loss": 0.0308, "step": 52120 }, { "epoch": 6.47, "learning_rate": 8.72700112037844e-06, "loss": 0.0834, "step": 52130 }, { "epoch": 6.47, "learning_rate": 8.72675214739201e-06, "loss": 0.0589, "step": 52140 }, { "epoch": 6.48, "learning_rate": 8.726503174405578e-06, "loss": 0.0633, "step": 52150 }, { "epoch": 6.48, "learning_rate": 8.726254201419147e-06, "loss": 0.0432, "step": 52160 }, { "epoch": 6.48, "learning_rate": 8.726005228432715e-06, "loss": 0.0304, "step": 52170 }, { "epoch": 6.48, "learning_rate": 8.725756255446285e-06, "loss": 0.0621, "step": 52180 }, { "epoch": 6.48, "learning_rate": 8.725507282459854e-06, "loss": 0.0617, "step": 52190 }, { "epoch": 6.48, "learning_rate": 8.725258309473424e-06, "loss": 0.079, "step": 52200 }, { "epoch": 6.48, "learning_rate": 8.725009336486991e-06, "loss": 0.0309, "step": 52210 }, { "epoch": 6.48, "learning_rate": 8.724760363500561e-06, "loss": 0.0735, "step": 52220 }, { "epoch": 6.49, "learning_rate": 8.72451139051413e-06, "loss": 0.0623, "step": 52230 }, { "epoch": 6.49, "learning_rate": 8.7242624175277e-06, "loss": 0.0558, "step": 52240 }, { "epoch": 6.49, "learning_rate": 8.724013444541268e-06, "loss": 0.0364, "step": 52250 }, { "epoch": 6.49, "learning_rate": 8.723764471554837e-06, "loss": 0.0615, "step": 52260 }, { "epoch": 6.49, "learning_rate": 8.723515498568405e-06, "loss": 0.0339, "step": 52270 }, { "epoch": 6.49, "learning_rate": 8.723266525581976e-06, "loss": 0.0486, "step": 52280 }, { "epoch": 6.49, "learning_rate": 8.723017552595544e-06, "loss": 0.0618, "step": 52290 }, { "epoch": 6.49, "learning_rate": 8.722768579609113e-06, "loss": 0.0363, "step": 52300 }, { "epoch": 6.5, "learning_rate": 8.722519606622683e-06, "loss": 0.0455, "step": 52310 }, { "epoch": 6.5, "learning_rate": 8.722270633636251e-06, "loss": 0.0415, "step": 52320 }, { "epoch": 6.5, "learning_rate": 8.72202166064982e-06, "loss": 0.0496, "step": 52330 }, { "epoch": 6.5, "learning_rate": 8.721772687663388e-06, "loss": 0.0511, "step": 52340 }, { "epoch": 6.5, "learning_rate": 8.721523714676959e-06, "loss": 0.0517, "step": 52350 }, { "epoch": 6.5, "learning_rate": 8.721274741690527e-06, "loss": 0.0341, "step": 52360 }, { "epoch": 6.5, "learning_rate": 8.721025768704097e-06, "loss": 0.0492, "step": 52370 }, { "epoch": 6.5, "learning_rate": 8.720776795717666e-06, "loss": 0.0619, "step": 52380 }, { "epoch": 6.51, "learning_rate": 8.720527822731234e-06, "loss": 0.0571, "step": 52390 }, { "epoch": 6.51, "learning_rate": 8.720278849744803e-06, "loss": 0.034, "step": 52400 }, { "epoch": 6.51, "learning_rate": 8.720029876758373e-06, "loss": 0.0591, "step": 52410 }, { "epoch": 6.51, "learning_rate": 8.719780903771942e-06, "loss": 0.0383, "step": 52420 }, { "epoch": 6.51, "learning_rate": 8.71953193078551e-06, "loss": 0.0475, "step": 52430 }, { "epoch": 6.51, "learning_rate": 8.719282957799079e-06, "loss": 0.0521, "step": 52440 }, { "epoch": 6.51, "learning_rate": 8.719033984812649e-06, "loss": 0.0315, "step": 52450 }, { "epoch": 6.51, "learning_rate": 8.718785011826217e-06, "loss": 0.045, "step": 52460 }, { "epoch": 6.52, "learning_rate": 8.718536038839786e-06, "loss": 0.0655, "step": 52470 }, { "epoch": 6.52, "learning_rate": 8.718287065853356e-06, "loss": 0.0583, "step": 52480 }, { "epoch": 6.52, "learning_rate": 8.718038092866925e-06, "loss": 0.0656, "step": 52490 }, { "epoch": 6.52, "learning_rate": 8.717789119880493e-06, "loss": 0.0454, "step": 52500 }, { "epoch": 6.52, "learning_rate": 8.717540146894062e-06, "loss": 0.0286, "step": 52510 }, { "epoch": 6.52, "learning_rate": 8.717291173907632e-06, "loss": 0.0775, "step": 52520 }, { "epoch": 6.52, "learning_rate": 8.7170422009212e-06, "loss": 0.0484, "step": 52530 }, { "epoch": 6.52, "learning_rate": 8.71679322793477e-06, "loss": 0.0489, "step": 52540 }, { "epoch": 6.53, "learning_rate": 8.716544254948339e-06, "loss": 0.0703, "step": 52550 }, { "epoch": 6.53, "learning_rate": 8.716295281961908e-06, "loss": 0.0405, "step": 52560 }, { "epoch": 6.53, "learning_rate": 8.716046308975476e-06, "loss": 0.0463, "step": 52570 }, { "epoch": 6.53, "learning_rate": 8.715797335989046e-06, "loss": 0.0462, "step": 52580 }, { "epoch": 6.53, "learning_rate": 8.715548363002615e-06, "loss": 0.0505, "step": 52590 }, { "epoch": 6.53, "learning_rate": 8.715299390016185e-06, "loss": 0.0598, "step": 52600 }, { "epoch": 6.53, "learning_rate": 8.715050417029754e-06, "loss": 0.0343, "step": 52610 }, { "epoch": 6.53, "learning_rate": 8.714801444043322e-06, "loss": 0.0541, "step": 52620 }, { "epoch": 6.54, "learning_rate": 8.71455247105689e-06, "loss": 0.0574, "step": 52630 }, { "epoch": 6.54, "learning_rate": 8.71430349807046e-06, "loss": 0.0698, "step": 52640 }, { "epoch": 6.54, "learning_rate": 8.71405452508403e-06, "loss": 0.0422, "step": 52650 }, { "epoch": 6.54, "learning_rate": 8.713805552097598e-06, "loss": 0.0734, "step": 52660 }, { "epoch": 6.54, "learning_rate": 8.713556579111168e-06, "loss": 0.0367, "step": 52670 }, { "epoch": 6.54, "learning_rate": 8.713307606124737e-06, "loss": 0.0714, "step": 52680 }, { "epoch": 6.54, "learning_rate": 8.713058633138305e-06, "loss": 0.0705, "step": 52690 }, { "epoch": 6.54, "learning_rate": 8.712809660151874e-06, "loss": 0.0481, "step": 52700 }, { "epoch": 6.55, "learning_rate": 8.712560687165444e-06, "loss": 0.0412, "step": 52710 }, { "epoch": 6.55, "learning_rate": 8.712311714179012e-06, "loss": 0.0631, "step": 52720 }, { "epoch": 6.55, "learning_rate": 8.712062741192583e-06, "loss": 0.0394, "step": 52730 }, { "epoch": 6.55, "learning_rate": 8.71181376820615e-06, "loss": 0.0689, "step": 52740 }, { "epoch": 6.55, "learning_rate": 8.71156479521972e-06, "loss": 0.0551, "step": 52750 }, { "epoch": 6.55, "learning_rate": 8.711315822233288e-06, "loss": 0.0408, "step": 52760 }, { "epoch": 6.55, "learning_rate": 8.711066849246858e-06, "loss": 0.038, "step": 52770 }, { "epoch": 6.55, "learning_rate": 8.710817876260427e-06, "loss": 0.0517, "step": 52780 }, { "epoch": 6.56, "learning_rate": 8.710568903273995e-06, "loss": 0.053, "step": 52790 }, { "epoch": 6.56, "learning_rate": 8.710319930287564e-06, "loss": 0.0408, "step": 52800 }, { "epoch": 6.56, "learning_rate": 8.710070957301134e-06, "loss": 0.0392, "step": 52810 }, { "epoch": 6.56, "learning_rate": 8.709821984314703e-06, "loss": 0.0493, "step": 52820 }, { "epoch": 6.56, "learning_rate": 8.709573011328271e-06, "loss": 0.0593, "step": 52830 }, { "epoch": 6.56, "learning_rate": 8.709324038341841e-06, "loss": 0.088, "step": 52840 }, { "epoch": 6.56, "learning_rate": 8.70907506535541e-06, "loss": 0.0333, "step": 52850 }, { "epoch": 6.56, "learning_rate": 8.708826092368978e-06, "loss": 0.0367, "step": 52860 }, { "epoch": 6.57, "learning_rate": 8.708577119382547e-06, "loss": 0.0525, "step": 52870 }, { "epoch": 6.57, "learning_rate": 8.708328146396117e-06, "loss": 0.0444, "step": 52880 }, { "epoch": 6.57, "learning_rate": 8.708079173409686e-06, "loss": 0.0597, "step": 52890 }, { "epoch": 6.57, "learning_rate": 8.707830200423256e-06, "loss": 0.0449, "step": 52900 }, { "epoch": 6.57, "learning_rate": 8.707581227436824e-06, "loss": 0.0354, "step": 52910 }, { "epoch": 6.57, "learning_rate": 8.707332254450393e-06, "loss": 0.0472, "step": 52920 }, { "epoch": 6.57, "learning_rate": 8.707083281463961e-06, "loss": 0.0524, "step": 52930 }, { "epoch": 6.57, "learning_rate": 8.706834308477532e-06, "loss": 0.0665, "step": 52940 }, { "epoch": 6.58, "learning_rate": 8.7065853354911e-06, "loss": 0.0533, "step": 52950 }, { "epoch": 6.58, "learning_rate": 8.706336362504669e-06, "loss": 0.0326, "step": 52960 }, { "epoch": 6.58, "learning_rate": 8.706087389518239e-06, "loss": 0.0469, "step": 52970 }, { "epoch": 6.58, "learning_rate": 8.705838416531807e-06, "loss": 0.0463, "step": 52980 }, { "epoch": 6.58, "learning_rate": 8.705589443545376e-06, "loss": 0.0569, "step": 52990 }, { "epoch": 6.58, "learning_rate": 8.705340470558944e-06, "loss": 0.0432, "step": 53000 }, { "epoch": 6.58, "learning_rate": 8.705091497572515e-06, "loss": 0.0554, "step": 53010 }, { "epoch": 6.58, "learning_rate": 8.704842524586083e-06, "loss": 0.051, "step": 53020 }, { "epoch": 6.59, "learning_rate": 8.704593551599653e-06, "loss": 0.0427, "step": 53030 }, { "epoch": 6.59, "learning_rate": 8.70434457861322e-06, "loss": 0.046, "step": 53040 }, { "epoch": 6.59, "learning_rate": 8.70409560562679e-06, "loss": 0.0553, "step": 53050 }, { "epoch": 6.59, "learning_rate": 8.703846632640359e-06, "loss": 0.0608, "step": 53060 }, { "epoch": 6.59, "learning_rate": 8.703597659653929e-06, "loss": 0.0482, "step": 53070 }, { "epoch": 6.59, "learning_rate": 8.703348686667497e-06, "loss": 0.0753, "step": 53080 }, { "epoch": 6.59, "learning_rate": 8.703099713681066e-06, "loss": 0.0615, "step": 53090 }, { "epoch": 6.59, "learning_rate": 8.702850740694635e-06, "loss": 0.0473, "step": 53100 }, { "epoch": 6.6, "learning_rate": 8.702601767708205e-06, "loss": 0.0599, "step": 53110 }, { "epoch": 6.6, "learning_rate": 8.702352794721773e-06, "loss": 0.04, "step": 53120 }, { "epoch": 6.6, "learning_rate": 8.702103821735343e-06, "loss": 0.0688, "step": 53130 }, { "epoch": 6.6, "learning_rate": 8.701854848748912e-06, "loss": 0.0673, "step": 53140 }, { "epoch": 6.6, "learning_rate": 8.70160587576248e-06, "loss": 0.062, "step": 53150 }, { "epoch": 6.6, "learning_rate": 8.701356902776049e-06, "loss": 0.08, "step": 53160 }, { "epoch": 6.6, "learning_rate": 8.70110792978962e-06, "loss": 0.0493, "step": 53170 }, { "epoch": 6.6, "learning_rate": 8.700858956803188e-06, "loss": 0.0924, "step": 53180 }, { "epoch": 6.6, "learning_rate": 8.700609983816756e-06, "loss": 0.087, "step": 53190 }, { "epoch": 6.61, "learning_rate": 8.700361010830326e-06, "loss": 0.0442, "step": 53200 }, { "epoch": 6.61, "learning_rate": 8.700112037843893e-06, "loss": 0.0448, "step": 53210 }, { "epoch": 6.61, "learning_rate": 8.699863064857463e-06, "loss": 0.0916, "step": 53220 }, { "epoch": 6.61, "learning_rate": 8.699614091871032e-06, "loss": 0.0488, "step": 53230 }, { "epoch": 6.61, "learning_rate": 8.699365118884602e-06, "loss": 0.0591, "step": 53240 }, { "epoch": 6.61, "learning_rate": 8.69911614589817e-06, "loss": 0.0419, "step": 53250 }, { "epoch": 6.61, "learning_rate": 8.698867172911741e-06, "loss": 0.0492, "step": 53260 }, { "epoch": 6.61, "learning_rate": 8.698618199925308e-06, "loss": 0.0506, "step": 53270 }, { "epoch": 6.62, "learning_rate": 8.698369226938878e-06, "loss": 0.0673, "step": 53280 }, { "epoch": 6.62, "learning_rate": 8.698120253952446e-06, "loss": 0.0776, "step": 53290 }, { "epoch": 6.62, "learning_rate": 8.697871280966017e-06, "loss": 0.0911, "step": 53300 }, { "epoch": 6.62, "learning_rate": 8.697622307979585e-06, "loss": 0.0601, "step": 53310 }, { "epoch": 6.62, "learning_rate": 8.697373334993154e-06, "loss": 0.0536, "step": 53320 }, { "epoch": 6.62, "learning_rate": 8.697124362006722e-06, "loss": 0.0511, "step": 53330 }, { "epoch": 6.62, "learning_rate": 8.696875389020292e-06, "loss": 0.0612, "step": 53340 }, { "epoch": 6.62, "learning_rate": 8.696626416033861e-06, "loss": 0.0647, "step": 53350 }, { "epoch": 6.63, "learning_rate": 8.69637744304743e-06, "loss": 0.0624, "step": 53360 }, { "epoch": 6.63, "learning_rate": 8.696128470061e-06, "loss": 0.0318, "step": 53370 }, { "epoch": 6.63, "learning_rate": 8.695879497074568e-06, "loss": 0.0742, "step": 53380 }, { "epoch": 6.63, "learning_rate": 8.695630524088137e-06, "loss": 0.0405, "step": 53390 }, { "epoch": 6.63, "learning_rate": 8.695381551101705e-06, "loss": 0.051, "step": 53400 }, { "epoch": 6.63, "learning_rate": 8.695132578115275e-06, "loss": 0.0546, "step": 53410 }, { "epoch": 6.63, "learning_rate": 8.694883605128844e-06, "loss": 0.0682, "step": 53420 }, { "epoch": 6.63, "learning_rate": 8.694634632142414e-06, "loss": 0.0446, "step": 53430 }, { "epoch": 6.64, "learning_rate": 8.694385659155983e-06, "loss": 0.0692, "step": 53440 }, { "epoch": 6.64, "learning_rate": 8.694136686169551e-06, "loss": 0.0525, "step": 53450 }, { "epoch": 6.64, "learning_rate": 8.69388771318312e-06, "loss": 0.0383, "step": 53460 }, { "epoch": 6.64, "learning_rate": 8.69363874019669e-06, "loss": 0.0412, "step": 53470 }, { "epoch": 6.64, "learning_rate": 8.693389767210258e-06, "loss": 0.0592, "step": 53480 }, { "epoch": 6.64, "learning_rate": 8.693140794223827e-06, "loss": 0.0467, "step": 53490 }, { "epoch": 6.64, "learning_rate": 8.692891821237397e-06, "loss": 0.0504, "step": 53500 }, { "epoch": 6.64, "learning_rate": 8.692642848250966e-06, "loss": 0.0411, "step": 53510 }, { "epoch": 6.65, "learning_rate": 8.692393875264534e-06, "loss": 0.0572, "step": 53520 }, { "epoch": 6.65, "learning_rate": 8.692144902278103e-06, "loss": 0.0602, "step": 53530 }, { "epoch": 6.65, "learning_rate": 8.691895929291673e-06, "loss": 0.0653, "step": 53540 }, { "epoch": 6.65, "learning_rate": 8.691646956305241e-06, "loss": 0.0374, "step": 53550 }, { "epoch": 6.65, "learning_rate": 8.691397983318812e-06, "loss": 0.0748, "step": 53560 }, { "epoch": 6.65, "learning_rate": 8.691149010332378e-06, "loss": 0.0804, "step": 53570 }, { "epoch": 6.65, "learning_rate": 8.690900037345949e-06, "loss": 0.0871, "step": 53580 }, { "epoch": 6.65, "learning_rate": 8.690651064359517e-06, "loss": 0.0777, "step": 53590 }, { "epoch": 6.66, "learning_rate": 8.690402091373087e-06, "loss": 0.0655, "step": 53600 }, { "epoch": 6.66, "learning_rate": 8.690153118386656e-06, "loss": 0.0486, "step": 53610 }, { "epoch": 6.66, "learning_rate": 8.689904145400226e-06, "loss": 0.0831, "step": 53620 }, { "epoch": 6.66, "learning_rate": 8.689655172413793e-06, "loss": 0.0742, "step": 53630 }, { "epoch": 6.66, "learning_rate": 8.689406199427363e-06, "loss": 0.0662, "step": 53640 }, { "epoch": 6.66, "learning_rate": 8.689157226440932e-06, "loss": 0.0669, "step": 53650 }, { "epoch": 6.66, "learning_rate": 8.688908253454502e-06, "loss": 0.0251, "step": 53660 }, { "epoch": 6.66, "learning_rate": 8.68865928046807e-06, "loss": 0.0433, "step": 53670 }, { "epoch": 6.67, "learning_rate": 8.688410307481639e-06, "loss": 0.0703, "step": 53680 }, { "epoch": 6.67, "learning_rate": 8.688161334495207e-06, "loss": 0.0522, "step": 53690 }, { "epoch": 6.67, "learning_rate": 8.687912361508776e-06, "loss": 0.0448, "step": 53700 }, { "epoch": 6.67, "learning_rate": 8.687663388522346e-06, "loss": 0.0511, "step": 53710 }, { "epoch": 6.67, "learning_rate": 8.687414415535915e-06, "loss": 0.043, "step": 53720 }, { "epoch": 6.67, "learning_rate": 8.687165442549485e-06, "loss": 0.0438, "step": 53730 }, { "epoch": 6.67, "learning_rate": 8.686916469563052e-06, "loss": 0.0514, "step": 53740 }, { "epoch": 6.67, "learning_rate": 8.686667496576622e-06, "loss": 0.0457, "step": 53750 }, { "epoch": 6.68, "learning_rate": 8.68641852359019e-06, "loss": 0.0444, "step": 53760 }, { "epoch": 6.68, "learning_rate": 8.68616955060376e-06, "loss": 0.049, "step": 53770 }, { "epoch": 6.68, "learning_rate": 8.68592057761733e-06, "loss": 0.0355, "step": 53780 }, { "epoch": 6.68, "learning_rate": 8.6856716046309e-06, "loss": 0.04, "step": 53790 }, { "epoch": 6.68, "learning_rate": 8.685422631644466e-06, "loss": 0.0713, "step": 53800 }, { "epoch": 6.68, "learning_rate": 8.685173658658036e-06, "loss": 0.0744, "step": 53810 }, { "epoch": 6.68, "learning_rate": 8.684924685671605e-06, "loss": 0.0489, "step": 53820 }, { "epoch": 6.68, "learning_rate": 8.684675712685175e-06, "loss": 0.0514, "step": 53830 }, { "epoch": 6.69, "learning_rate": 8.684426739698744e-06, "loss": 0.0455, "step": 53840 }, { "epoch": 6.69, "learning_rate": 8.684177766712312e-06, "loss": 0.0746, "step": 53850 }, { "epoch": 6.69, "learning_rate": 8.68392879372588e-06, "loss": 0.0379, "step": 53860 }, { "epoch": 6.69, "learning_rate": 8.683679820739451e-06, "loss": 0.0407, "step": 53870 }, { "epoch": 6.69, "learning_rate": 8.68343084775302e-06, "loss": 0.046, "step": 53880 }, { "epoch": 6.69, "learning_rate": 8.683181874766588e-06, "loss": 0.0719, "step": 53890 }, { "epoch": 6.69, "learning_rate": 8.682932901780158e-06, "loss": 0.0562, "step": 53900 }, { "epoch": 6.69, "learning_rate": 8.682683928793727e-06, "loss": 0.0421, "step": 53910 }, { "epoch": 6.7, "learning_rate": 8.682434955807295e-06, "loss": 0.0355, "step": 53920 }, { "epoch": 6.7, "learning_rate": 8.682185982820864e-06, "loss": 0.0488, "step": 53930 }, { "epoch": 6.7, "learning_rate": 8.681937009834434e-06, "loss": 0.0611, "step": 53940 }, { "epoch": 6.7, "learning_rate": 8.681688036848002e-06, "loss": 0.0388, "step": 53950 }, { "epoch": 6.7, "learning_rate": 8.681439063861573e-06, "loss": 0.0312, "step": 53960 }, { "epoch": 6.7, "learning_rate": 8.681190090875141e-06, "loss": 0.0459, "step": 53970 }, { "epoch": 6.7, "learning_rate": 8.68094111788871e-06, "loss": 0.0666, "step": 53980 }, { "epoch": 6.7, "learning_rate": 8.680692144902278e-06, "loss": 0.0807, "step": 53990 }, { "epoch": 6.71, "learning_rate": 8.680443171915848e-06, "loss": 0.0453, "step": 54000 }, { "epoch": 6.71, "learning_rate": 8.680194198929417e-06, "loss": 0.0534, "step": 54010 }, { "epoch": 6.71, "learning_rate": 8.679945225942985e-06, "loss": 0.0653, "step": 54020 }, { "epoch": 6.71, "learning_rate": 8.679696252956556e-06, "loss": 0.0665, "step": 54030 }, { "epoch": 6.71, "learning_rate": 8.679447279970124e-06, "loss": 0.084, "step": 54040 }, { "epoch": 6.71, "learning_rate": 8.679198306983693e-06, "loss": 0.0609, "step": 54050 }, { "epoch": 6.71, "learning_rate": 8.678949333997261e-06, "loss": 0.0508, "step": 54060 }, { "epoch": 6.71, "learning_rate": 8.678700361010831e-06, "loss": 0.0513, "step": 54070 }, { "epoch": 6.72, "learning_rate": 8.6784513880244e-06, "loss": 0.0729, "step": 54080 }, { "epoch": 6.72, "learning_rate": 8.67820241503797e-06, "loss": 0.0435, "step": 54090 }, { "epoch": 6.72, "learning_rate": 8.677953442051537e-06, "loss": 0.0591, "step": 54100 }, { "epoch": 6.72, "learning_rate": 8.677704469065107e-06, "loss": 0.0427, "step": 54110 }, { "epoch": 6.72, "learning_rate": 8.677455496078676e-06, "loss": 0.0748, "step": 54120 }, { "epoch": 6.72, "learning_rate": 8.677206523092246e-06, "loss": 0.0568, "step": 54130 }, { "epoch": 6.72, "learning_rate": 8.676957550105814e-06, "loss": 0.0486, "step": 54140 }, { "epoch": 6.72, "learning_rate": 8.676708577119385e-06, "loss": 0.0524, "step": 54150 }, { "epoch": 6.73, "learning_rate": 8.676459604132951e-06, "loss": 0.0495, "step": 54160 }, { "epoch": 6.73, "learning_rate": 8.676210631146522e-06, "loss": 0.036, "step": 54170 }, { "epoch": 6.73, "learning_rate": 8.67596165816009e-06, "loss": 0.0697, "step": 54180 }, { "epoch": 6.73, "learning_rate": 8.675712685173659e-06, "loss": 0.0654, "step": 54190 }, { "epoch": 6.73, "learning_rate": 8.675463712187229e-06, "loss": 0.0495, "step": 54200 }, { "epoch": 6.73, "learning_rate": 8.675214739200797e-06, "loss": 0.0708, "step": 54210 }, { "epoch": 6.73, "learning_rate": 8.674965766214366e-06, "loss": 0.0436, "step": 54220 }, { "epoch": 6.73, "learning_rate": 8.674716793227934e-06, "loss": 0.0908, "step": 54230 }, { "epoch": 6.74, "learning_rate": 8.674467820241505e-06, "loss": 0.0945, "step": 54240 }, { "epoch": 6.74, "learning_rate": 8.674218847255073e-06, "loss": 0.0571, "step": 54250 }, { "epoch": 6.74, "learning_rate": 8.673969874268643e-06, "loss": 0.0458, "step": 54260 }, { "epoch": 6.74, "learning_rate": 8.673720901282212e-06, "loss": 0.0392, "step": 54270 }, { "epoch": 6.74, "learning_rate": 8.67347192829578e-06, "loss": 0.0602, "step": 54280 }, { "epoch": 6.74, "learning_rate": 8.673222955309349e-06, "loss": 0.0517, "step": 54290 }, { "epoch": 6.74, "learning_rate": 8.672973982322919e-06, "loss": 0.0451, "step": 54300 }, { "epoch": 6.74, "learning_rate": 8.672725009336488e-06, "loss": 0.0498, "step": 54310 }, { "epoch": 6.75, "learning_rate": 8.672476036350058e-06, "loss": 0.0495, "step": 54320 }, { "epoch": 6.75, "learning_rate": 8.672227063363626e-06, "loss": 0.0914, "step": 54330 }, { "epoch": 6.75, "learning_rate": 8.671978090377195e-06, "loss": 0.0379, "step": 54340 }, { "epoch": 6.75, "learning_rate": 8.671729117390763e-06, "loss": 0.0665, "step": 54350 }, { "epoch": 6.75, "learning_rate": 8.671480144404334e-06, "loss": 0.0644, "step": 54360 }, { "epoch": 6.75, "learning_rate": 8.671231171417902e-06, "loss": 0.0467, "step": 54370 }, { "epoch": 6.75, "learning_rate": 8.67098219843147e-06, "loss": 0.0662, "step": 54380 }, { "epoch": 6.75, "learning_rate": 8.670733225445039e-06, "loss": 0.054, "step": 54390 }, { "epoch": 6.76, "learning_rate": 8.67048425245861e-06, "loss": 0.0476, "step": 54400 }, { "epoch": 6.76, "learning_rate": 8.670235279472178e-06, "loss": 0.0542, "step": 54410 }, { "epoch": 6.76, "learning_rate": 8.669986306485746e-06, "loss": 0.0392, "step": 54420 }, { "epoch": 6.76, "learning_rate": 8.669737333499317e-06, "loss": 0.0449, "step": 54430 }, { "epoch": 6.76, "learning_rate": 8.669488360512885e-06, "loss": 0.0511, "step": 54440 }, { "epoch": 6.76, "learning_rate": 8.669239387526454e-06, "loss": 0.0373, "step": 54450 }, { "epoch": 6.76, "learning_rate": 8.668990414540022e-06, "loss": 0.0377, "step": 54460 }, { "epoch": 6.76, "learning_rate": 8.668741441553592e-06, "loss": 0.0482, "step": 54470 }, { "epoch": 6.77, "learning_rate": 8.668492468567161e-06, "loss": 0.0824, "step": 54480 }, { "epoch": 6.77, "learning_rate": 8.668243495580731e-06, "loss": 0.0531, "step": 54490 }, { "epoch": 6.77, "learning_rate": 8.6679945225943e-06, "loss": 0.0732, "step": 54500 }, { "epoch": 6.77, "learning_rate": 8.667745549607868e-06, "loss": 0.0513, "step": 54510 }, { "epoch": 6.77, "learning_rate": 8.667496576621437e-06, "loss": 0.0571, "step": 54520 }, { "epoch": 6.77, "learning_rate": 8.667247603635007e-06, "loss": 0.0497, "step": 54530 }, { "epoch": 6.77, "learning_rate": 8.666998630648575e-06, "loss": 0.0404, "step": 54540 }, { "epoch": 6.77, "learning_rate": 8.666749657662144e-06, "loss": 0.0573, "step": 54550 }, { "epoch": 6.78, "learning_rate": 8.666500684675714e-06, "loss": 0.0452, "step": 54560 }, { "epoch": 6.78, "learning_rate": 8.666251711689283e-06, "loss": 0.0502, "step": 54570 }, { "epoch": 6.78, "learning_rate": 8.666002738702851e-06, "loss": 0.0653, "step": 54580 }, { "epoch": 6.78, "learning_rate": 8.66575376571642e-06, "loss": 0.0665, "step": 54590 }, { "epoch": 6.78, "learning_rate": 8.66550479272999e-06, "loss": 0.0433, "step": 54600 }, { "epoch": 6.78, "learning_rate": 8.665255819743558e-06, "loss": 0.0363, "step": 54610 }, { "epoch": 6.78, "learning_rate": 8.665006846757129e-06, "loss": 0.0452, "step": 54620 }, { "epoch": 6.78, "learning_rate": 8.664757873770695e-06, "loss": 0.0734, "step": 54630 }, { "epoch": 6.79, "learning_rate": 8.664508900784266e-06, "loss": 0.0737, "step": 54640 }, { "epoch": 6.79, "learning_rate": 8.664259927797834e-06, "loss": 0.0424, "step": 54650 }, { "epoch": 6.79, "learning_rate": 8.664010954811404e-06, "loss": 0.0677, "step": 54660 }, { "epoch": 6.79, "learning_rate": 8.663761981824973e-06, "loss": 0.0527, "step": 54670 }, { "epoch": 6.79, "learning_rate": 8.663513008838541e-06, "loss": 0.0435, "step": 54680 }, { "epoch": 6.79, "learning_rate": 8.66326403585211e-06, "loss": 0.0394, "step": 54690 }, { "epoch": 6.79, "learning_rate": 8.66301506286568e-06, "loss": 0.0639, "step": 54700 }, { "epoch": 6.79, "learning_rate": 8.662766089879249e-06, "loss": 0.0298, "step": 54710 }, { "epoch": 6.79, "learning_rate": 8.662517116892817e-06, "loss": 0.0575, "step": 54720 }, { "epoch": 6.8, "learning_rate": 8.662268143906387e-06, "loss": 0.0563, "step": 54730 }, { "epoch": 6.8, "learning_rate": 8.662019170919956e-06, "loss": 0.0457, "step": 54740 }, { "epoch": 6.8, "learning_rate": 8.661770197933524e-06, "loss": 0.0811, "step": 54750 }, { "epoch": 6.8, "learning_rate": 8.661521224947093e-06, "loss": 0.0356, "step": 54760 }, { "epoch": 6.8, "learning_rate": 8.661272251960663e-06, "loss": 0.0441, "step": 54770 }, { "epoch": 6.8, "learning_rate": 8.661023278974232e-06, "loss": 0.0815, "step": 54780 }, { "epoch": 6.8, "learning_rate": 8.660774305987802e-06, "loss": 0.0538, "step": 54790 }, { "epoch": 6.8, "learning_rate": 8.66052533300137e-06, "loss": 0.0511, "step": 54800 }, { "epoch": 6.81, "learning_rate": 8.660276360014939e-06, "loss": 0.0366, "step": 54810 }, { "epoch": 6.81, "learning_rate": 8.660027387028507e-06, "loss": 0.0289, "step": 54820 }, { "epoch": 6.81, "learning_rate": 8.659778414042078e-06, "loss": 0.063, "step": 54830 }, { "epoch": 6.81, "learning_rate": 8.659529441055646e-06, "loss": 0.0457, "step": 54840 }, { "epoch": 6.81, "learning_rate": 8.659280468069216e-06, "loss": 0.0526, "step": 54850 }, { "epoch": 6.81, "learning_rate": 8.659031495082785e-06, "loss": 0.0481, "step": 54860 }, { "epoch": 6.81, "learning_rate": 8.658782522096353e-06, "loss": 0.0388, "step": 54870 }, { "epoch": 6.81, "learning_rate": 8.658533549109922e-06, "loss": 0.049, "step": 54880 }, { "epoch": 6.82, "learning_rate": 8.658284576123492e-06, "loss": 0.053, "step": 54890 }, { "epoch": 6.82, "learning_rate": 8.65803560313706e-06, "loss": 0.0366, "step": 54900 }, { "epoch": 6.82, "learning_rate": 8.657786630150629e-06, "loss": 0.0679, "step": 54910 }, { "epoch": 6.82, "learning_rate": 8.6575376571642e-06, "loss": 0.0444, "step": 54920 }, { "epoch": 6.82, "learning_rate": 8.657288684177768e-06, "loss": 0.0719, "step": 54930 }, { "epoch": 6.82, "learning_rate": 8.657039711191336e-06, "loss": 0.0622, "step": 54940 }, { "epoch": 6.82, "learning_rate": 8.656790738204905e-06, "loss": 0.0525, "step": 54950 }, { "epoch": 6.82, "learning_rate": 8.656541765218475e-06, "loss": 0.0574, "step": 54960 }, { "epoch": 6.83, "learning_rate": 8.656292792232044e-06, "loss": 0.0613, "step": 54970 }, { "epoch": 6.83, "learning_rate": 8.656043819245614e-06, "loss": 0.0965, "step": 54980 }, { "epoch": 6.83, "learning_rate": 8.65579484625918e-06, "loss": 0.0575, "step": 54990 }, { "epoch": 6.83, "learning_rate": 8.65554587327275e-06, "loss": 0.0501, "step": 55000 }, { "epoch": 6.83, "eval_bleu": 89.3315, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7638, "eval_has_error_f1": 0.6874, "eval_loss": 0.05242938920855522, "eval_runtime": 1324.1745, "eval_samples_per_second": 3.019, "eval_steps_per_second": 0.755, "step": 55000 }, { "epoch": 6.83, "learning_rate": 8.65529690028632e-06, "loss": 0.0421, "step": 55010 }, { "epoch": 6.83, "learning_rate": 8.65504792729989e-06, "loss": 0.0382, "step": 55020 }, { "epoch": 6.83, "learning_rate": 8.654798954313458e-06, "loss": 0.051, "step": 55030 }, { "epoch": 6.83, "learning_rate": 8.654549981327027e-06, "loss": 0.0364, "step": 55040 }, { "epoch": 6.84, "learning_rate": 8.654301008340595e-06, "loss": 0.0393, "step": 55050 }, { "epoch": 6.84, "learning_rate": 8.654052035354165e-06, "loss": 0.0813, "step": 55060 }, { "epoch": 6.84, "learning_rate": 8.653803062367734e-06, "loss": 0.0504, "step": 55070 }, { "epoch": 6.84, "learning_rate": 8.653554089381302e-06, "loss": 0.0549, "step": 55080 }, { "epoch": 6.84, "learning_rate": 8.653305116394873e-06, "loss": 0.0602, "step": 55090 }, { "epoch": 6.84, "learning_rate": 8.653056143408441e-06, "loss": 0.0695, "step": 55100 }, { "epoch": 6.84, "learning_rate": 8.65280717042201e-06, "loss": 0.0359, "step": 55110 }, { "epoch": 6.84, "learning_rate": 8.652558197435578e-06, "loss": 0.0408, "step": 55120 }, { "epoch": 6.85, "learning_rate": 8.652309224449148e-06, "loss": 0.0755, "step": 55130 }, { "epoch": 6.85, "learning_rate": 8.652060251462717e-06, "loss": 0.0323, "step": 55140 }, { "epoch": 6.85, "learning_rate": 8.651811278476287e-06, "loss": 0.0736, "step": 55150 }, { "epoch": 6.85, "learning_rate": 8.651562305489854e-06, "loss": 0.0508, "step": 55160 }, { "epoch": 6.85, "learning_rate": 8.651313332503424e-06, "loss": 0.0627, "step": 55170 }, { "epoch": 6.85, "learning_rate": 8.651064359516993e-06, "loss": 0.0828, "step": 55180 }, { "epoch": 6.85, "learning_rate": 8.650815386530563e-06, "loss": 0.0691, "step": 55190 }, { "epoch": 6.85, "learning_rate": 8.650566413544131e-06, "loss": 0.054, "step": 55200 }, { "epoch": 6.86, "learning_rate": 8.6503174405577e-06, "loss": 0.0701, "step": 55210 }, { "epoch": 6.86, "learning_rate": 8.650068467571268e-06, "loss": 0.0604, "step": 55220 }, { "epoch": 6.86, "learning_rate": 8.649819494584839e-06, "loss": 0.0541, "step": 55230 }, { "epoch": 6.86, "learning_rate": 8.649570521598407e-06, "loss": 0.0398, "step": 55240 }, { "epoch": 6.86, "learning_rate": 8.649321548611976e-06, "loss": 0.0373, "step": 55250 }, { "epoch": 6.86, "learning_rate": 8.649072575625546e-06, "loss": 0.0461, "step": 55260 }, { "epoch": 6.86, "learning_rate": 8.648823602639114e-06, "loss": 0.0461, "step": 55270 }, { "epoch": 6.86, "learning_rate": 8.648574629652683e-06, "loss": 0.0574, "step": 55280 }, { "epoch": 6.87, "learning_rate": 8.648325656666251e-06, "loss": 0.0416, "step": 55290 }, { "epoch": 6.87, "learning_rate": 8.648076683679822e-06, "loss": 0.0655, "step": 55300 }, { "epoch": 6.87, "learning_rate": 8.64782771069339e-06, "loss": 0.0506, "step": 55310 }, { "epoch": 6.87, "learning_rate": 8.64757873770696e-06, "loss": 0.0376, "step": 55320 }, { "epoch": 6.87, "learning_rate": 8.647329764720529e-06, "loss": 0.0681, "step": 55330 }, { "epoch": 6.87, "learning_rate": 8.647080791734097e-06, "loss": 0.064, "step": 55340 }, { "epoch": 6.87, "learning_rate": 8.646831818747666e-06, "loss": 0.0513, "step": 55350 }, { "epoch": 6.87, "learning_rate": 8.646582845761236e-06, "loss": 0.0519, "step": 55360 }, { "epoch": 6.88, "learning_rate": 8.646333872774805e-06, "loss": 0.0399, "step": 55370 }, { "epoch": 6.88, "learning_rate": 8.646084899788375e-06, "loss": 0.0915, "step": 55380 }, { "epoch": 6.88, "learning_rate": 8.645835926801943e-06, "loss": 0.0633, "step": 55390 }, { "epoch": 6.88, "learning_rate": 8.645586953815512e-06, "loss": 0.0391, "step": 55400 }, { "epoch": 6.88, "learning_rate": 8.64533798082908e-06, "loss": 0.047, "step": 55410 }, { "epoch": 6.88, "learning_rate": 8.64508900784265e-06, "loss": 0.0775, "step": 55420 }, { "epoch": 6.88, "learning_rate": 8.644840034856219e-06, "loss": 0.0631, "step": 55430 }, { "epoch": 6.88, "learning_rate": 8.644591061869788e-06, "loss": 0.0594, "step": 55440 }, { "epoch": 6.89, "learning_rate": 8.644342088883358e-06, "loss": 0.063, "step": 55450 }, { "epoch": 6.89, "learning_rate": 8.644093115896926e-06, "loss": 0.0496, "step": 55460 }, { "epoch": 6.89, "learning_rate": 8.643844142910495e-06, "loss": 0.0353, "step": 55470 }, { "epoch": 6.89, "learning_rate": 8.643595169924063e-06, "loss": 0.0585, "step": 55480 }, { "epoch": 6.89, "learning_rate": 8.643346196937633e-06, "loss": 0.0332, "step": 55490 }, { "epoch": 6.89, "learning_rate": 8.643097223951202e-06, "loss": 0.0644, "step": 55500 }, { "epoch": 6.89, "learning_rate": 8.642848250964772e-06, "loss": 0.0584, "step": 55510 }, { "epoch": 6.89, "learning_rate": 8.642599277978339e-06, "loss": 0.03, "step": 55520 }, { "epoch": 6.9, "learning_rate": 8.64235030499191e-06, "loss": 0.0702, "step": 55530 }, { "epoch": 6.9, "learning_rate": 8.642101332005478e-06, "loss": 0.0642, "step": 55540 }, { "epoch": 6.9, "learning_rate": 8.641852359019048e-06, "loss": 0.0417, "step": 55550 }, { "epoch": 6.9, "learning_rate": 8.641603386032616e-06, "loss": 0.0634, "step": 55560 }, { "epoch": 6.9, "learning_rate": 8.641354413046185e-06, "loss": 0.0455, "step": 55570 }, { "epoch": 6.9, "learning_rate": 8.641105440059754e-06, "loss": 0.0632, "step": 55580 }, { "epoch": 6.9, "learning_rate": 8.640856467073324e-06, "loss": 0.041, "step": 55590 }, { "epoch": 6.9, "learning_rate": 8.640607494086892e-06, "loss": 0.0581, "step": 55600 }, { "epoch": 6.91, "learning_rate": 8.64035852110046e-06, "loss": 0.0294, "step": 55610 }, { "epoch": 6.91, "learning_rate": 8.640109548114031e-06, "loss": 0.0572, "step": 55620 }, { "epoch": 6.91, "learning_rate": 8.6398605751276e-06, "loss": 0.0526, "step": 55630 }, { "epoch": 6.91, "learning_rate": 8.639611602141168e-06, "loss": 0.0646, "step": 55640 }, { "epoch": 6.91, "learning_rate": 8.639362629154737e-06, "loss": 0.0695, "step": 55650 }, { "epoch": 6.91, "learning_rate": 8.639113656168307e-06, "loss": 0.0334, "step": 55660 }, { "epoch": 6.91, "learning_rate": 8.638864683181875e-06, "loss": 0.045, "step": 55670 }, { "epoch": 6.91, "learning_rate": 8.638615710195445e-06, "loss": 0.0582, "step": 55680 }, { "epoch": 6.92, "learning_rate": 8.638366737209012e-06, "loss": 0.059, "step": 55690 }, { "epoch": 6.92, "learning_rate": 8.638117764222582e-06, "loss": 0.0663, "step": 55700 }, { "epoch": 6.92, "learning_rate": 8.637868791236151e-06, "loss": 0.038, "step": 55710 }, { "epoch": 6.92, "learning_rate": 8.637619818249721e-06, "loss": 0.0626, "step": 55720 }, { "epoch": 6.92, "learning_rate": 8.63737084526329e-06, "loss": 0.0649, "step": 55730 }, { "epoch": 6.92, "learning_rate": 8.637121872276858e-06, "loss": 0.0749, "step": 55740 }, { "epoch": 6.92, "learning_rate": 8.636872899290427e-06, "loss": 0.0804, "step": 55750 }, { "epoch": 6.92, "learning_rate": 8.636623926303997e-06, "loss": 0.0521, "step": 55760 }, { "epoch": 6.93, "learning_rate": 8.636374953317565e-06, "loss": 0.0933, "step": 55770 }, { "epoch": 6.93, "learning_rate": 8.636125980331134e-06, "loss": 0.0707, "step": 55780 }, { "epoch": 6.93, "learning_rate": 8.635877007344704e-06, "loss": 0.0588, "step": 55790 }, { "epoch": 6.93, "learning_rate": 8.635628034358273e-06, "loss": 0.0561, "step": 55800 }, { "epoch": 6.93, "learning_rate": 8.635379061371841e-06, "loss": 0.0497, "step": 55810 }, { "epoch": 6.93, "learning_rate": 8.63513008838541e-06, "loss": 0.048, "step": 55820 }, { "epoch": 6.93, "learning_rate": 8.63488111539898e-06, "loss": 0.0437, "step": 55830 }, { "epoch": 6.93, "learning_rate": 8.634632142412548e-06, "loss": 0.0577, "step": 55840 }, { "epoch": 6.94, "learning_rate": 8.634383169426119e-06, "loss": 0.0401, "step": 55850 }, { "epoch": 6.94, "learning_rate": 8.634134196439687e-06, "loss": 0.0481, "step": 55860 }, { "epoch": 6.94, "learning_rate": 8.633885223453256e-06, "loss": 0.0512, "step": 55870 }, { "epoch": 6.94, "learning_rate": 8.633636250466824e-06, "loss": 0.0609, "step": 55880 }, { "epoch": 6.94, "learning_rate": 8.633387277480394e-06, "loss": 0.0508, "step": 55890 }, { "epoch": 6.94, "learning_rate": 8.633138304493963e-06, "loss": 0.0478, "step": 55900 }, { "epoch": 6.94, "learning_rate": 8.632889331507533e-06, "loss": 0.057, "step": 55910 }, { "epoch": 6.94, "learning_rate": 8.632640358521102e-06, "loss": 0.0433, "step": 55920 }, { "epoch": 6.95, "learning_rate": 8.63239138553467e-06, "loss": 0.051, "step": 55930 }, { "epoch": 6.95, "learning_rate": 8.632142412548239e-06, "loss": 0.0429, "step": 55940 }, { "epoch": 6.95, "learning_rate": 8.631893439561809e-06, "loss": 0.0733, "step": 55950 }, { "epoch": 6.95, "learning_rate": 8.631644466575377e-06, "loss": 0.0495, "step": 55960 }, { "epoch": 6.95, "learning_rate": 8.631395493588946e-06, "loss": 0.0513, "step": 55970 }, { "epoch": 6.95, "learning_rate": 8.631146520602516e-06, "loss": 0.0537, "step": 55980 }, { "epoch": 6.95, "learning_rate": 8.630897547616085e-06, "loss": 0.064, "step": 55990 }, { "epoch": 6.95, "learning_rate": 8.630648574629653e-06, "loss": 0.0381, "step": 56000 }, { "epoch": 6.96, "learning_rate": 8.630399601643222e-06, "loss": 0.0521, "step": 56010 }, { "epoch": 6.96, "learning_rate": 8.630150628656792e-06, "loss": 0.0674, "step": 56020 }, { "epoch": 6.96, "learning_rate": 8.62990165567036e-06, "loss": 0.0725, "step": 56030 }, { "epoch": 6.96, "learning_rate": 8.62965268268393e-06, "loss": 0.0337, "step": 56040 }, { "epoch": 6.96, "learning_rate": 8.629403709697497e-06, "loss": 0.0444, "step": 56050 }, { "epoch": 6.96, "learning_rate": 8.629154736711068e-06, "loss": 0.0512, "step": 56060 }, { "epoch": 6.96, "learning_rate": 8.628905763724636e-06, "loss": 0.0311, "step": 56070 }, { "epoch": 6.96, "learning_rate": 8.628656790738206e-06, "loss": 0.0482, "step": 56080 }, { "epoch": 6.97, "learning_rate": 8.628407817751775e-06, "loss": 0.0548, "step": 56090 }, { "epoch": 6.97, "learning_rate": 8.628158844765343e-06, "loss": 0.0409, "step": 56100 }, { "epoch": 6.97, "learning_rate": 8.627909871778912e-06, "loss": 0.0437, "step": 56110 }, { "epoch": 6.97, "learning_rate": 8.627660898792482e-06, "loss": 0.0475, "step": 56120 }, { "epoch": 6.97, "learning_rate": 8.62741192580605e-06, "loss": 0.0576, "step": 56130 }, { "epoch": 6.97, "learning_rate": 8.62716295281962e-06, "loss": 0.0681, "step": 56140 }, { "epoch": 6.97, "learning_rate": 8.62691397983319e-06, "loss": 0.0257, "step": 56150 }, { "epoch": 6.97, "learning_rate": 8.626665006846758e-06, "loss": 0.0658, "step": 56160 }, { "epoch": 6.97, "learning_rate": 8.626416033860326e-06, "loss": 0.0591, "step": 56170 }, { "epoch": 6.98, "learning_rate": 8.626167060873895e-06, "loss": 0.0602, "step": 56180 }, { "epoch": 6.98, "learning_rate": 8.625918087887465e-06, "loss": 0.06, "step": 56190 }, { "epoch": 6.98, "learning_rate": 8.625669114901034e-06, "loss": 0.0386, "step": 56200 }, { "epoch": 6.98, "learning_rate": 8.625420141914604e-06, "loss": 0.039, "step": 56210 }, { "epoch": 6.98, "learning_rate": 8.625171168928172e-06, "loss": 0.0629, "step": 56220 }, { "epoch": 6.98, "learning_rate": 8.624922195941741e-06, "loss": 0.0788, "step": 56230 }, { "epoch": 6.98, "learning_rate": 8.62467322295531e-06, "loss": 0.0462, "step": 56240 }, { "epoch": 6.98, "learning_rate": 8.62442424996888e-06, "loss": 0.0435, "step": 56250 }, { "epoch": 6.99, "learning_rate": 8.624175276982448e-06, "loss": 0.0697, "step": 56260 }, { "epoch": 6.99, "learning_rate": 8.623926303996017e-06, "loss": 0.0607, "step": 56270 }, { "epoch": 6.99, "learning_rate": 8.623677331009587e-06, "loss": 0.0576, "step": 56280 }, { "epoch": 6.99, "learning_rate": 8.623428358023155e-06, "loss": 0.0713, "step": 56290 }, { "epoch": 6.99, "learning_rate": 8.623179385036724e-06, "loss": 0.06, "step": 56300 }, { "epoch": 6.99, "learning_rate": 8.622930412050292e-06, "loss": 0.0505, "step": 56310 }, { "epoch": 6.99, "learning_rate": 8.622681439063863e-06, "loss": 0.0461, "step": 56320 }, { "epoch": 6.99, "learning_rate": 8.622432466077431e-06, "loss": 0.0602, "step": 56330 }, { "epoch": 7.0, "learning_rate": 8.622183493091e-06, "loss": 0.0399, "step": 56340 }, { "epoch": 7.0, "learning_rate": 8.621934520104568e-06, "loss": 0.0461, "step": 56350 }, { "epoch": 7.0, "learning_rate": 8.621685547118138e-06, "loss": 0.0434, "step": 56360 }, { "epoch": 7.0, "learning_rate": 8.621436574131707e-06, "loss": 0.0521, "step": 56370 }, { "epoch": 7.0, "learning_rate": 8.621187601145277e-06, "loss": 0.0544, "step": 56380 }, { "epoch": 7.0, "learning_rate": 8.620938628158846e-06, "loss": 0.081, "step": 56390 }, { "epoch": 7.0, "learning_rate": 8.620689655172414e-06, "loss": 0.0433, "step": 56400 }, { "epoch": 7.0, "learning_rate": 8.620440682185983e-06, "loss": 0.066, "step": 56410 }, { "epoch": 7.01, "learning_rate": 8.620191709199553e-06, "loss": 0.0485, "step": 56420 }, { "epoch": 7.01, "learning_rate": 8.619942736213121e-06, "loss": 0.0403, "step": 56430 }, { "epoch": 7.01, "learning_rate": 8.619693763226692e-06, "loss": 0.0595, "step": 56440 }, { "epoch": 7.01, "learning_rate": 8.61944479024026e-06, "loss": 0.06, "step": 56450 }, { "epoch": 7.01, "learning_rate": 8.619195817253829e-06, "loss": 0.0523, "step": 56460 }, { "epoch": 7.01, "learning_rate": 8.618946844267397e-06, "loss": 0.0595, "step": 56470 }, { "epoch": 7.01, "learning_rate": 8.618697871280967e-06, "loss": 0.085, "step": 56480 }, { "epoch": 7.01, "learning_rate": 8.618448898294536e-06, "loss": 0.0547, "step": 56490 }, { "epoch": 7.02, "learning_rate": 8.618199925308104e-06, "loss": 0.0424, "step": 56500 }, { "epoch": 7.02, "learning_rate": 8.617950952321675e-06, "loss": 0.051, "step": 56510 }, { "epoch": 7.02, "learning_rate": 8.617701979335243e-06, "loss": 0.0424, "step": 56520 }, { "epoch": 7.02, "learning_rate": 8.617453006348812e-06, "loss": 0.074, "step": 56530 }, { "epoch": 7.02, "learning_rate": 8.61720403336238e-06, "loss": 0.0497, "step": 56540 }, { "epoch": 7.02, "learning_rate": 8.61695506037595e-06, "loss": 0.0448, "step": 56550 }, { "epoch": 7.02, "learning_rate": 8.616706087389519e-06, "loss": 0.0584, "step": 56560 }, { "epoch": 7.02, "learning_rate": 8.616457114403089e-06, "loss": 0.0601, "step": 56570 }, { "epoch": 7.03, "learning_rate": 8.616208141416656e-06, "loss": 0.046, "step": 56580 }, { "epoch": 7.03, "learning_rate": 8.615959168430226e-06, "loss": 0.0634, "step": 56590 }, { "epoch": 7.03, "learning_rate": 8.615710195443795e-06, "loss": 0.0316, "step": 56600 }, { "epoch": 7.03, "learning_rate": 8.615461222457365e-06, "loss": 0.0365, "step": 56610 }, { "epoch": 7.03, "learning_rate": 8.615212249470933e-06, "loss": 0.0321, "step": 56620 }, { "epoch": 7.03, "learning_rate": 8.614963276484502e-06, "loss": 0.0447, "step": 56630 }, { "epoch": 7.03, "learning_rate": 8.61471430349807e-06, "loss": 0.0625, "step": 56640 }, { "epoch": 7.03, "learning_rate": 8.61446533051164e-06, "loss": 0.0669, "step": 56650 }, { "epoch": 7.04, "learning_rate": 8.614216357525209e-06, "loss": 0.0379, "step": 56660 }, { "epoch": 7.04, "learning_rate": 8.613967384538778e-06, "loss": 0.0697, "step": 56670 }, { "epoch": 7.04, "learning_rate": 8.613718411552348e-06, "loss": 0.0594, "step": 56680 }, { "epoch": 7.04, "learning_rate": 8.613469438565916e-06, "loss": 0.0685, "step": 56690 }, { "epoch": 7.04, "learning_rate": 8.613220465579485e-06, "loss": 0.0388, "step": 56700 }, { "epoch": 7.04, "learning_rate": 8.612971492593053e-06, "loss": 0.0437, "step": 56710 }, { "epoch": 7.04, "learning_rate": 8.612722519606624e-06, "loss": 0.0387, "step": 56720 }, { "epoch": 7.04, "learning_rate": 8.612473546620192e-06, "loss": 0.0606, "step": 56730 }, { "epoch": 7.05, "learning_rate": 8.612224573633762e-06, "loss": 0.0493, "step": 56740 }, { "epoch": 7.05, "learning_rate": 8.61197560064733e-06, "loss": 0.0641, "step": 56750 }, { "epoch": 7.05, "learning_rate": 8.6117266276609e-06, "loss": 0.0186, "step": 56760 }, { "epoch": 7.05, "learning_rate": 8.611477654674468e-06, "loss": 0.0392, "step": 56770 }, { "epoch": 7.05, "learning_rate": 8.611228681688038e-06, "loss": 0.0662, "step": 56780 }, { "epoch": 7.05, "learning_rate": 8.610979708701607e-06, "loss": 0.0549, "step": 56790 }, { "epoch": 7.05, "learning_rate": 8.610730735715175e-06, "loss": 0.0592, "step": 56800 }, { "epoch": 7.05, "learning_rate": 8.610481762728745e-06, "loss": 0.0309, "step": 56810 }, { "epoch": 7.06, "learning_rate": 8.610232789742314e-06, "loss": 0.0344, "step": 56820 }, { "epoch": 7.06, "learning_rate": 8.609983816755882e-06, "loss": 0.0613, "step": 56830 }, { "epoch": 7.06, "learning_rate": 8.609734843769451e-06, "loss": 0.0821, "step": 56840 }, { "epoch": 7.06, "learning_rate": 8.609485870783021e-06, "loss": 0.0471, "step": 56850 }, { "epoch": 7.06, "learning_rate": 8.60923689779659e-06, "loss": 0.0354, "step": 56860 }, { "epoch": 7.06, "learning_rate": 8.60898792481016e-06, "loss": 0.0427, "step": 56870 }, { "epoch": 7.06, "learning_rate": 8.608738951823727e-06, "loss": 0.0674, "step": 56880 }, { "epoch": 7.06, "learning_rate": 8.608489978837297e-06, "loss": 0.057, "step": 56890 }, { "epoch": 7.07, "learning_rate": 8.608241005850865e-06, "loss": 0.0399, "step": 56900 }, { "epoch": 7.07, "learning_rate": 8.607992032864436e-06, "loss": 0.0351, "step": 56910 }, { "epoch": 7.07, "learning_rate": 8.607743059878004e-06, "loss": 0.0364, "step": 56920 }, { "epoch": 7.07, "learning_rate": 8.607494086891574e-06, "loss": 0.044, "step": 56930 }, { "epoch": 7.07, "learning_rate": 8.607245113905141e-06, "loss": 0.0535, "step": 56940 }, { "epoch": 7.07, "learning_rate": 8.606996140918711e-06, "loss": 0.0505, "step": 56950 }, { "epoch": 7.07, "learning_rate": 8.60674716793228e-06, "loss": 0.0599, "step": 56960 }, { "epoch": 7.07, "learning_rate": 8.60649819494585e-06, "loss": 0.0388, "step": 56970 }, { "epoch": 7.08, "learning_rate": 8.606249221959419e-06, "loss": 0.0601, "step": 56980 }, { "epoch": 7.08, "learning_rate": 8.606000248972987e-06, "loss": 0.0397, "step": 56990 }, { "epoch": 7.08, "learning_rate": 8.605751275986556e-06, "loss": 0.046, "step": 57000 }, { "epoch": 7.08, "learning_rate": 8.605502303000126e-06, "loss": 0.0518, "step": 57010 }, { "epoch": 7.08, "learning_rate": 8.605253330013694e-06, "loss": 0.0343, "step": 57020 }, { "epoch": 7.08, "learning_rate": 8.605004357027263e-06, "loss": 0.0329, "step": 57030 }, { "epoch": 7.08, "learning_rate": 8.604755384040833e-06, "loss": 0.0362, "step": 57040 }, { "epoch": 7.08, "learning_rate": 8.604506411054402e-06, "loss": 0.0403, "step": 57050 }, { "epoch": 7.09, "learning_rate": 8.60425743806797e-06, "loss": 0.0323, "step": 57060 }, { "epoch": 7.09, "learning_rate": 8.604008465081539e-06, "loss": 0.0386, "step": 57070 }, { "epoch": 7.09, "learning_rate": 8.603759492095109e-06, "loss": 0.0494, "step": 57080 }, { "epoch": 7.09, "learning_rate": 8.603510519108677e-06, "loss": 0.0755, "step": 57090 }, { "epoch": 7.09, "learning_rate": 8.603261546122248e-06, "loss": 0.0542, "step": 57100 }, { "epoch": 7.09, "learning_rate": 8.603012573135814e-06, "loss": 0.0407, "step": 57110 }, { "epoch": 7.09, "learning_rate": 8.602763600149385e-06, "loss": 0.0257, "step": 57120 }, { "epoch": 7.09, "learning_rate": 8.602514627162953e-06, "loss": 0.0572, "step": 57130 }, { "epoch": 7.1, "learning_rate": 8.602265654176523e-06, "loss": 0.0474, "step": 57140 }, { "epoch": 7.1, "learning_rate": 8.602016681190092e-06, "loss": 0.0413, "step": 57150 }, { "epoch": 7.1, "learning_rate": 8.60176770820366e-06, "loss": 0.0278, "step": 57160 }, { "epoch": 7.1, "learning_rate": 8.601518735217229e-06, "loss": 0.0348, "step": 57170 }, { "epoch": 7.1, "learning_rate": 8.601269762230799e-06, "loss": 0.0571, "step": 57180 }, { "epoch": 7.1, "learning_rate": 8.601020789244368e-06, "loss": 0.0506, "step": 57190 }, { "epoch": 7.1, "learning_rate": 8.600771816257936e-06, "loss": 0.0677, "step": 57200 }, { "epoch": 7.1, "learning_rate": 8.600522843271506e-06, "loss": 0.0382, "step": 57210 }, { "epoch": 7.11, "learning_rate": 8.600273870285075e-06, "loss": 0.0665, "step": 57220 }, { "epoch": 7.11, "learning_rate": 8.600024897298643e-06, "loss": 0.0511, "step": 57230 }, { "epoch": 7.11, "learning_rate": 8.599775924312212e-06, "loss": 0.0601, "step": 57240 }, { "epoch": 7.11, "learning_rate": 8.599526951325782e-06, "loss": 0.0592, "step": 57250 }, { "epoch": 7.11, "learning_rate": 8.59927797833935e-06, "loss": 0.0407, "step": 57260 }, { "epoch": 7.11, "learning_rate": 8.59902900535292e-06, "loss": 0.0276, "step": 57270 }, { "epoch": 7.11, "learning_rate": 8.59878003236649e-06, "loss": 0.0668, "step": 57280 }, { "epoch": 7.11, "learning_rate": 8.598531059380058e-06, "loss": 0.0676, "step": 57290 }, { "epoch": 7.12, "learning_rate": 8.598282086393626e-06, "loss": 0.0412, "step": 57300 }, { "epoch": 7.12, "learning_rate": 8.598033113407197e-06, "loss": 0.0415, "step": 57310 }, { "epoch": 7.12, "learning_rate": 8.597784140420765e-06, "loss": 0.0612, "step": 57320 }, { "epoch": 7.12, "learning_rate": 8.597535167434334e-06, "loss": 0.0597, "step": 57330 }, { "epoch": 7.12, "learning_rate": 8.597286194447904e-06, "loss": 0.0667, "step": 57340 }, { "epoch": 7.12, "learning_rate": 8.597037221461472e-06, "loss": 0.0331, "step": 57350 }, { "epoch": 7.12, "learning_rate": 8.59678824847504e-06, "loss": 0.0498, "step": 57360 }, { "epoch": 7.12, "learning_rate": 8.59653927548861e-06, "loss": 0.0329, "step": 57370 }, { "epoch": 7.13, "learning_rate": 8.59629030250218e-06, "loss": 0.0748, "step": 57380 }, { "epoch": 7.13, "learning_rate": 8.596041329515748e-06, "loss": 0.0355, "step": 57390 }, { "epoch": 7.13, "learning_rate": 8.595792356529318e-06, "loss": 0.051, "step": 57400 }, { "epoch": 7.13, "learning_rate": 8.595543383542885e-06, "loss": 0.0338, "step": 57410 }, { "epoch": 7.13, "learning_rate": 8.595294410556455e-06, "loss": 0.0212, "step": 57420 }, { "epoch": 7.13, "learning_rate": 8.595045437570024e-06, "loss": 0.0501, "step": 57430 }, { "epoch": 7.13, "learning_rate": 8.594796464583594e-06, "loss": 0.0724, "step": 57440 }, { "epoch": 7.13, "learning_rate": 8.594547491597163e-06, "loss": 0.0558, "step": 57450 }, { "epoch": 7.14, "learning_rate": 8.594298518610733e-06, "loss": 0.0401, "step": 57460 }, { "epoch": 7.14, "learning_rate": 8.5940495456243e-06, "loss": 0.0365, "step": 57470 }, { "epoch": 7.14, "learning_rate": 8.59380057263787e-06, "loss": 0.051, "step": 57480 }, { "epoch": 7.14, "learning_rate": 8.593551599651438e-06, "loss": 0.0737, "step": 57490 }, { "epoch": 7.14, "learning_rate": 8.593302626665008e-06, "loss": 0.0518, "step": 57500 }, { "epoch": 7.14, "learning_rate": 8.593053653678577e-06, "loss": 0.0576, "step": 57510 }, { "epoch": 7.14, "learning_rate": 8.592804680692146e-06, "loss": 0.0429, "step": 57520 }, { "epoch": 7.14, "learning_rate": 8.592555707705714e-06, "loss": 0.0654, "step": 57530 }, { "epoch": 7.15, "learning_rate": 8.592306734719284e-06, "loss": 0.0416, "step": 57540 }, { "epoch": 7.15, "learning_rate": 8.592057761732853e-06, "loss": 0.0593, "step": 57550 }, { "epoch": 7.15, "learning_rate": 8.591808788746421e-06, "loss": 0.0526, "step": 57560 }, { "epoch": 7.15, "learning_rate": 8.591559815759991e-06, "loss": 0.0414, "step": 57570 }, { "epoch": 7.15, "learning_rate": 8.59131084277356e-06, "loss": 0.054, "step": 57580 }, { "epoch": 7.15, "learning_rate": 8.591061869787129e-06, "loss": 0.0446, "step": 57590 }, { "epoch": 7.15, "learning_rate": 8.590812896800697e-06, "loss": 0.0417, "step": 57600 }, { "epoch": 7.15, "learning_rate": 8.590563923814267e-06, "loss": 0.0527, "step": 57610 }, { "epoch": 7.16, "learning_rate": 8.590314950827836e-06, "loss": 0.0389, "step": 57620 }, { "epoch": 7.16, "learning_rate": 8.590065977841406e-06, "loss": 0.0653, "step": 57630 }, { "epoch": 7.16, "learning_rate": 8.589817004854973e-06, "loss": 0.0471, "step": 57640 }, { "epoch": 7.16, "learning_rate": 8.589568031868543e-06, "loss": 0.0508, "step": 57650 }, { "epoch": 7.16, "learning_rate": 8.589319058882112e-06, "loss": 0.0687, "step": 57660 }, { "epoch": 7.16, "learning_rate": 8.589070085895682e-06, "loss": 0.0401, "step": 57670 }, { "epoch": 7.16, "learning_rate": 8.58882111290925e-06, "loss": 0.0625, "step": 57680 }, { "epoch": 7.16, "learning_rate": 8.588572139922819e-06, "loss": 0.0513, "step": 57690 }, { "epoch": 7.17, "learning_rate": 8.588323166936387e-06, "loss": 0.0528, "step": 57700 }, { "epoch": 7.17, "learning_rate": 8.588074193949957e-06, "loss": 0.0423, "step": 57710 }, { "epoch": 7.17, "learning_rate": 8.587825220963526e-06, "loss": 0.0722, "step": 57720 }, { "epoch": 7.17, "learning_rate": 8.587576247977095e-06, "loss": 0.0412, "step": 57730 }, { "epoch": 7.17, "learning_rate": 8.587327274990665e-06, "loss": 0.0429, "step": 57740 }, { "epoch": 7.17, "learning_rate": 8.587078302004233e-06, "loss": 0.0507, "step": 57750 }, { "epoch": 7.17, "learning_rate": 8.586829329017802e-06, "loss": 0.0341, "step": 57760 }, { "epoch": 7.17, "learning_rate": 8.58658035603137e-06, "loss": 0.0329, "step": 57770 }, { "epoch": 7.17, "learning_rate": 8.58633138304494e-06, "loss": 0.0549, "step": 57780 }, { "epoch": 7.18, "learning_rate": 8.586082410058509e-06, "loss": 0.0524, "step": 57790 }, { "epoch": 7.18, "learning_rate": 8.58583343707208e-06, "loss": 0.0365, "step": 57800 }, { "epoch": 7.18, "learning_rate": 8.585584464085648e-06, "loss": 0.0571, "step": 57810 }, { "epoch": 7.18, "learning_rate": 8.585335491099216e-06, "loss": 0.0444, "step": 57820 }, { "epoch": 7.18, "learning_rate": 8.585086518112785e-06, "loss": 0.0629, "step": 57830 }, { "epoch": 7.18, "learning_rate": 8.584837545126355e-06, "loss": 0.0481, "step": 57840 }, { "epoch": 7.18, "learning_rate": 8.584588572139923e-06, "loss": 0.085, "step": 57850 }, { "epoch": 7.18, "learning_rate": 8.584339599153492e-06, "loss": 0.0443, "step": 57860 }, { "epoch": 7.19, "learning_rate": 8.584090626167062e-06, "loss": 0.0312, "step": 57870 }, { "epoch": 7.19, "learning_rate": 8.58384165318063e-06, "loss": 0.0579, "step": 57880 }, { "epoch": 7.19, "learning_rate": 8.5835926801942e-06, "loss": 0.0409, "step": 57890 }, { "epoch": 7.19, "learning_rate": 8.583343707207768e-06, "loss": 0.0439, "step": 57900 }, { "epoch": 7.19, "learning_rate": 8.583094734221338e-06, "loss": 0.0389, "step": 57910 }, { "epoch": 7.19, "learning_rate": 8.582845761234906e-06, "loss": 0.036, "step": 57920 }, { "epoch": 7.19, "learning_rate": 8.582596788248477e-06, "loss": 0.0616, "step": 57930 }, { "epoch": 7.19, "learning_rate": 8.582347815262044e-06, "loss": 0.0802, "step": 57940 }, { "epoch": 7.2, "learning_rate": 8.582098842275614e-06, "loss": 0.0336, "step": 57950 }, { "epoch": 7.2, "learning_rate": 8.581849869289182e-06, "loss": 0.0574, "step": 57960 }, { "epoch": 7.2, "learning_rate": 8.581600896302752e-06, "loss": 0.0344, "step": 57970 }, { "epoch": 7.2, "learning_rate": 8.581351923316321e-06, "loss": 0.0915, "step": 57980 }, { "epoch": 7.2, "learning_rate": 8.581102950329891e-06, "loss": 0.086, "step": 57990 }, { "epoch": 7.2, "learning_rate": 8.580853977343458e-06, "loss": 0.0438, "step": 58000 }, { "epoch": 7.2, "learning_rate": 8.580605004357028e-06, "loss": 0.0417, "step": 58010 }, { "epoch": 7.2, "learning_rate": 8.580356031370597e-06, "loss": 0.0393, "step": 58020 }, { "epoch": 7.21, "learning_rate": 8.580107058384167e-06, "loss": 0.0516, "step": 58030 }, { "epoch": 7.21, "learning_rate": 8.579858085397735e-06, "loss": 0.0471, "step": 58040 }, { "epoch": 7.21, "learning_rate": 8.579609112411304e-06, "loss": 0.0784, "step": 58050 }, { "epoch": 7.21, "learning_rate": 8.579360139424872e-06, "loss": 0.0342, "step": 58060 }, { "epoch": 7.21, "learning_rate": 8.579111166438443e-06, "loss": 0.0525, "step": 58070 }, { "epoch": 7.21, "learning_rate": 8.578862193452011e-06, "loss": 0.077, "step": 58080 }, { "epoch": 7.21, "learning_rate": 8.57861322046558e-06, "loss": 0.0538, "step": 58090 }, { "epoch": 7.21, "learning_rate": 8.57836424747915e-06, "loss": 0.0514, "step": 58100 }, { "epoch": 7.22, "learning_rate": 8.578115274492718e-06, "loss": 0.0526, "step": 58110 }, { "epoch": 7.22, "learning_rate": 8.577866301506287e-06, "loss": 0.0566, "step": 58120 }, { "epoch": 7.22, "learning_rate": 8.577617328519855e-06, "loss": 0.0721, "step": 58130 }, { "epoch": 7.22, "learning_rate": 8.577368355533426e-06, "loss": 0.0495, "step": 58140 }, { "epoch": 7.22, "learning_rate": 8.577119382546994e-06, "loss": 0.0562, "step": 58150 }, { "epoch": 7.22, "learning_rate": 8.576870409560564e-06, "loss": 0.0636, "step": 58160 }, { "epoch": 7.22, "learning_rate": 8.576621436574133e-06, "loss": 0.0401, "step": 58170 }, { "epoch": 7.22, "learning_rate": 8.576372463587701e-06, "loss": 0.0629, "step": 58180 }, { "epoch": 7.23, "learning_rate": 8.57612349060127e-06, "loss": 0.0454, "step": 58190 }, { "epoch": 7.23, "learning_rate": 8.57587451761484e-06, "loss": 0.0428, "step": 58200 }, { "epoch": 7.23, "learning_rate": 8.575625544628409e-06, "loss": 0.0484, "step": 58210 }, { "epoch": 7.23, "learning_rate": 8.575376571641977e-06, "loss": 0.0265, "step": 58220 }, { "epoch": 7.23, "learning_rate": 8.575127598655547e-06, "loss": 0.0764, "step": 58230 }, { "epoch": 7.23, "learning_rate": 8.574878625669116e-06, "loss": 0.0649, "step": 58240 }, { "epoch": 7.23, "learning_rate": 8.574629652682684e-06, "loss": 0.0532, "step": 58250 }, { "epoch": 7.23, "learning_rate": 8.574380679696253e-06, "loss": 0.0471, "step": 58260 }, { "epoch": 7.24, "learning_rate": 8.574131706709823e-06, "loss": 0.0551, "step": 58270 }, { "epoch": 7.24, "learning_rate": 8.573882733723392e-06, "loss": 0.0542, "step": 58280 }, { "epoch": 7.24, "learning_rate": 8.57363376073696e-06, "loss": 0.0541, "step": 58290 }, { "epoch": 7.24, "learning_rate": 8.573384787750529e-06, "loss": 0.0342, "step": 58300 }, { "epoch": 7.24, "learning_rate": 8.573135814764099e-06, "loss": 0.0464, "step": 58310 }, { "epoch": 7.24, "learning_rate": 8.572886841777667e-06, "loss": 0.0296, "step": 58320 }, { "epoch": 7.24, "learning_rate": 8.572637868791238e-06, "loss": 0.0606, "step": 58330 }, { "epoch": 7.24, "learning_rate": 8.572388895804806e-06, "loss": 0.059, "step": 58340 }, { "epoch": 7.25, "learning_rate": 8.572139922818375e-06, "loss": 0.0607, "step": 58350 }, { "epoch": 7.25, "learning_rate": 8.571890949831943e-06, "loss": 0.0333, "step": 58360 }, { "epoch": 7.25, "learning_rate": 8.571641976845513e-06, "loss": 0.0503, "step": 58370 }, { "epoch": 7.25, "learning_rate": 8.571393003859082e-06, "loss": 0.0476, "step": 58380 }, { "epoch": 7.25, "learning_rate": 8.57114403087265e-06, "loss": 0.0452, "step": 58390 }, { "epoch": 7.25, "learning_rate": 8.57089505788622e-06, "loss": 0.0351, "step": 58400 }, { "epoch": 7.25, "learning_rate": 8.57064608489979e-06, "loss": 0.043, "step": 58410 }, { "epoch": 7.25, "learning_rate": 8.570397111913358e-06, "loss": 0.0209, "step": 58420 }, { "epoch": 7.26, "learning_rate": 8.570148138926926e-06, "loss": 0.0478, "step": 58430 }, { "epoch": 7.26, "learning_rate": 8.569899165940496e-06, "loss": 0.055, "step": 58440 }, { "epoch": 7.26, "learning_rate": 8.569650192954065e-06, "loss": 0.0504, "step": 58450 }, { "epoch": 7.26, "learning_rate": 8.569401219967635e-06, "loss": 0.0552, "step": 58460 }, { "epoch": 7.26, "learning_rate": 8.569152246981202e-06, "loss": 0.0469, "step": 58470 }, { "epoch": 7.26, "learning_rate": 8.568903273994772e-06, "loss": 0.0459, "step": 58480 }, { "epoch": 7.26, "learning_rate": 8.56865430100834e-06, "loss": 0.0713, "step": 58490 }, { "epoch": 7.26, "learning_rate": 8.568405328021911e-06, "loss": 0.0585, "step": 58500 }, { "epoch": 7.27, "learning_rate": 8.56815635503548e-06, "loss": 0.0334, "step": 58510 }, { "epoch": 7.27, "learning_rate": 8.56790738204905e-06, "loss": 0.0572, "step": 58520 }, { "epoch": 7.27, "learning_rate": 8.567658409062616e-06, "loss": 0.0741, "step": 58530 }, { "epoch": 7.27, "learning_rate": 8.567409436076187e-06, "loss": 0.0602, "step": 58540 }, { "epoch": 7.27, "learning_rate": 8.567160463089755e-06, "loss": 0.0308, "step": 58550 }, { "epoch": 7.27, "learning_rate": 8.566911490103325e-06, "loss": 0.0482, "step": 58560 }, { "epoch": 7.27, "learning_rate": 8.566662517116894e-06, "loss": 0.0342, "step": 58570 }, { "epoch": 7.27, "learning_rate": 8.566413544130462e-06, "loss": 0.0601, "step": 58580 }, { "epoch": 7.28, "learning_rate": 8.566164571144031e-06, "loss": 0.0561, "step": 58590 }, { "epoch": 7.28, "learning_rate": 8.565915598157601e-06, "loss": 0.074, "step": 58600 }, { "epoch": 7.28, "learning_rate": 8.56566662517117e-06, "loss": 0.0516, "step": 58610 }, { "epoch": 7.28, "learning_rate": 8.565417652184738e-06, "loss": 0.0488, "step": 58620 }, { "epoch": 7.28, "learning_rate": 8.565168679198308e-06, "loss": 0.0744, "step": 58630 }, { "epoch": 7.28, "learning_rate": 8.564919706211877e-06, "loss": 0.0406, "step": 58640 }, { "epoch": 7.28, "learning_rate": 8.564670733225445e-06, "loss": 0.0508, "step": 58650 }, { "epoch": 7.28, "learning_rate": 8.564421760239014e-06, "loss": 0.0357, "step": 58660 }, { "epoch": 7.29, "learning_rate": 8.564172787252584e-06, "loss": 0.0456, "step": 58670 }, { "epoch": 7.29, "learning_rate": 8.563923814266153e-06, "loss": 0.065, "step": 58680 }, { "epoch": 7.29, "learning_rate": 8.563674841279723e-06, "loss": 0.048, "step": 58690 }, { "epoch": 7.29, "learning_rate": 8.563425868293291e-06, "loss": 0.0466, "step": 58700 }, { "epoch": 7.29, "learning_rate": 8.56317689530686e-06, "loss": 0.0465, "step": 58710 }, { "epoch": 7.29, "learning_rate": 8.562927922320428e-06, "loss": 0.0295, "step": 58720 }, { "epoch": 7.29, "learning_rate": 8.562678949333999e-06, "loss": 0.065, "step": 58730 }, { "epoch": 7.29, "learning_rate": 8.562429976347567e-06, "loss": 0.0572, "step": 58740 }, { "epoch": 7.3, "learning_rate": 8.562181003361136e-06, "loss": 0.0443, "step": 58750 }, { "epoch": 7.3, "learning_rate": 8.561932030374706e-06, "loss": 0.0427, "step": 58760 }, { "epoch": 7.3, "learning_rate": 8.561683057388274e-06, "loss": 0.036, "step": 58770 }, { "epoch": 7.3, "learning_rate": 8.561434084401843e-06, "loss": 0.0434, "step": 58780 }, { "epoch": 7.3, "learning_rate": 8.561185111415411e-06, "loss": 0.0364, "step": 58790 }, { "epoch": 7.3, "learning_rate": 8.560936138428982e-06, "loss": 0.0664, "step": 58800 }, { "epoch": 7.3, "learning_rate": 8.56068716544255e-06, "loss": 0.0582, "step": 58810 }, { "epoch": 7.3, "learning_rate": 8.56043819245612e-06, "loss": 0.0337, "step": 58820 }, { "epoch": 7.31, "learning_rate": 8.560189219469687e-06, "loss": 0.0431, "step": 58830 }, { "epoch": 7.31, "learning_rate": 8.559940246483257e-06, "loss": 0.0694, "step": 58840 }, { "epoch": 7.31, "learning_rate": 8.559691273496826e-06, "loss": 0.0551, "step": 58850 }, { "epoch": 7.31, "learning_rate": 8.559442300510396e-06, "loss": 0.0677, "step": 58860 }, { "epoch": 7.31, "learning_rate": 8.559193327523965e-06, "loss": 0.0411, "step": 58870 }, { "epoch": 7.31, "learning_rate": 8.558944354537533e-06, "loss": 0.064, "step": 58880 }, { "epoch": 7.31, "learning_rate": 8.558695381551102e-06, "loss": 0.0437, "step": 58890 }, { "epoch": 7.31, "learning_rate": 8.558446408564672e-06, "loss": 0.0562, "step": 58900 }, { "epoch": 7.32, "learning_rate": 8.55819743557824e-06, "loss": 0.0642, "step": 58910 }, { "epoch": 7.32, "learning_rate": 8.557948462591809e-06, "loss": 0.0347, "step": 58920 }, { "epoch": 7.32, "learning_rate": 8.557699489605379e-06, "loss": 0.065, "step": 58930 }, { "epoch": 7.32, "learning_rate": 8.557450516618948e-06, "loss": 0.049, "step": 58940 }, { "epoch": 7.32, "learning_rate": 8.557201543632516e-06, "loss": 0.0408, "step": 58950 }, { "epoch": 7.32, "learning_rate": 8.556952570646085e-06, "loss": 0.0752, "step": 58960 }, { "epoch": 7.32, "learning_rate": 8.556703597659655e-06, "loss": 0.055, "step": 58970 }, { "epoch": 7.32, "learning_rate": 8.556454624673223e-06, "loss": 0.0549, "step": 58980 }, { "epoch": 7.33, "learning_rate": 8.556205651686794e-06, "loss": 0.0486, "step": 58990 }, { "epoch": 7.33, "learning_rate": 8.55595667870036e-06, "loss": 0.0629, "step": 59000 }, { "epoch": 7.33, "learning_rate": 8.55570770571393e-06, "loss": 0.0575, "step": 59010 }, { "epoch": 7.33, "learning_rate": 8.555458732727499e-06, "loss": 0.0592, "step": 59020 }, { "epoch": 7.33, "learning_rate": 8.55520975974107e-06, "loss": 0.0641, "step": 59030 }, { "epoch": 7.33, "learning_rate": 8.554960786754638e-06, "loss": 0.0548, "step": 59040 }, { "epoch": 7.33, "learning_rate": 8.554711813768208e-06, "loss": 0.0656, "step": 59050 }, { "epoch": 7.33, "learning_rate": 8.554462840781775e-06, "loss": 0.0356, "step": 59060 }, { "epoch": 7.34, "learning_rate": 8.554213867795345e-06, "loss": 0.0388, "step": 59070 }, { "epoch": 7.34, "learning_rate": 8.553964894808914e-06, "loss": 0.0517, "step": 59080 }, { "epoch": 7.34, "learning_rate": 8.553715921822484e-06, "loss": 0.0533, "step": 59090 }, { "epoch": 7.34, "learning_rate": 8.553466948836052e-06, "loss": 0.055, "step": 59100 }, { "epoch": 7.34, "learning_rate": 8.55321797584962e-06, "loss": 0.0642, "step": 59110 }, { "epoch": 7.34, "learning_rate": 8.55296900286319e-06, "loss": 0.0303, "step": 59120 }, { "epoch": 7.34, "learning_rate": 8.55272002987676e-06, "loss": 0.0676, "step": 59130 }, { "epoch": 7.34, "learning_rate": 8.552471056890328e-06, "loss": 0.039, "step": 59140 }, { "epoch": 7.35, "learning_rate": 8.552222083903897e-06, "loss": 0.028, "step": 59150 }, { "epoch": 7.35, "learning_rate": 8.551973110917467e-06, "loss": 0.0343, "step": 59160 }, { "epoch": 7.35, "learning_rate": 8.551724137931035e-06, "loss": 0.0361, "step": 59170 }, { "epoch": 7.35, "learning_rate": 8.551475164944604e-06, "loss": 0.0572, "step": 59180 }, { "epoch": 7.35, "learning_rate": 8.551226191958172e-06, "loss": 0.0536, "step": 59190 }, { "epoch": 7.35, "learning_rate": 8.550977218971743e-06, "loss": 0.0558, "step": 59200 }, { "epoch": 7.35, "learning_rate": 8.550728245985311e-06, "loss": 0.0388, "step": 59210 }, { "epoch": 7.35, "learning_rate": 8.550479272998881e-06, "loss": 0.0423, "step": 59220 }, { "epoch": 7.36, "learning_rate": 8.55023030001245e-06, "loss": 0.0592, "step": 59230 }, { "epoch": 7.36, "learning_rate": 8.549981327026018e-06, "loss": 0.0422, "step": 59240 }, { "epoch": 7.36, "learning_rate": 8.549732354039587e-06, "loss": 0.0438, "step": 59250 }, { "epoch": 7.36, "learning_rate": 8.549483381053157e-06, "loss": 0.0314, "step": 59260 }, { "epoch": 7.36, "learning_rate": 8.549234408066726e-06, "loss": 0.0369, "step": 59270 }, { "epoch": 7.36, "learning_rate": 8.548985435080294e-06, "loss": 0.0423, "step": 59280 }, { "epoch": 7.36, "learning_rate": 8.548736462093864e-06, "loss": 0.1089, "step": 59290 }, { "epoch": 7.36, "learning_rate": 8.548487489107433e-06, "loss": 0.0356, "step": 59300 }, { "epoch": 7.36, "learning_rate": 8.548238516121001e-06, "loss": 0.0478, "step": 59310 }, { "epoch": 7.37, "learning_rate": 8.54798954313457e-06, "loss": 0.044, "step": 59320 }, { "epoch": 7.37, "learning_rate": 8.54774057014814e-06, "loss": 0.0418, "step": 59330 }, { "epoch": 7.37, "learning_rate": 8.547491597161709e-06, "loss": 0.0713, "step": 59340 }, { "epoch": 7.37, "learning_rate": 8.547242624175279e-06, "loss": 0.042, "step": 59350 }, { "epoch": 7.37, "learning_rate": 8.546993651188846e-06, "loss": 0.0257, "step": 59360 }, { "epoch": 7.37, "learning_rate": 8.546744678202416e-06, "loss": 0.0428, "step": 59370 }, { "epoch": 7.37, "learning_rate": 8.546495705215984e-06, "loss": 0.0643, "step": 59380 }, { "epoch": 7.37, "learning_rate": 8.546246732229555e-06, "loss": 0.0563, "step": 59390 }, { "epoch": 7.38, "learning_rate": 8.545997759243123e-06, "loss": 0.0366, "step": 59400 }, { "epoch": 7.38, "learning_rate": 8.545748786256692e-06, "loss": 0.0581, "step": 59410 }, { "epoch": 7.38, "learning_rate": 8.54549981327026e-06, "loss": 0.0398, "step": 59420 }, { "epoch": 7.38, "learning_rate": 8.54525084028383e-06, "loss": 0.0608, "step": 59430 }, { "epoch": 7.38, "learning_rate": 8.545001867297399e-06, "loss": 0.0359, "step": 59440 }, { "epoch": 7.38, "learning_rate": 8.544752894310967e-06, "loss": 0.044, "step": 59450 }, { "epoch": 7.38, "learning_rate": 8.544503921324538e-06, "loss": 0.0722, "step": 59460 }, { "epoch": 7.38, "learning_rate": 8.544254948338106e-06, "loss": 0.0407, "step": 59470 }, { "epoch": 7.39, "learning_rate": 8.544005975351675e-06, "loss": 0.0732, "step": 59480 }, { "epoch": 7.39, "learning_rate": 8.543757002365243e-06, "loss": 0.0696, "step": 59490 }, { "epoch": 7.39, "learning_rate": 8.543508029378813e-06, "loss": 0.0511, "step": 59500 }, { "epoch": 7.39, "learning_rate": 8.543259056392382e-06, "loss": 0.0331, "step": 59510 }, { "epoch": 7.39, "learning_rate": 8.543010083405952e-06, "loss": 0.0414, "step": 59520 }, { "epoch": 7.39, "learning_rate": 8.54276111041952e-06, "loss": 0.0731, "step": 59530 }, { "epoch": 7.39, "learning_rate": 8.542512137433089e-06, "loss": 0.0439, "step": 59540 }, { "epoch": 7.39, "learning_rate": 8.542263164446658e-06, "loss": 0.0503, "step": 59550 }, { "epoch": 7.4, "learning_rate": 8.542014191460228e-06, "loss": 0.0456, "step": 59560 }, { "epoch": 7.4, "learning_rate": 8.541765218473796e-06, "loss": 0.0466, "step": 59570 }, { "epoch": 7.4, "learning_rate": 8.541516245487366e-06, "loss": 0.054, "step": 59580 }, { "epoch": 7.4, "learning_rate": 8.541267272500933e-06, "loss": 0.034, "step": 59590 }, { "epoch": 7.4, "learning_rate": 8.541018299514504e-06, "loss": 0.065, "step": 59600 }, { "epoch": 7.4, "learning_rate": 8.540769326528072e-06, "loss": 0.0537, "step": 59610 }, { "epoch": 7.4, "learning_rate": 8.540520353541642e-06, "loss": 0.0421, "step": 59620 }, { "epoch": 7.4, "learning_rate": 8.54027138055521e-06, "loss": 0.0381, "step": 59630 }, { "epoch": 7.41, "learning_rate": 8.54002240756878e-06, "loss": 0.0872, "step": 59640 }, { "epoch": 7.41, "learning_rate": 8.539773434582348e-06, "loss": 0.0192, "step": 59650 }, { "epoch": 7.41, "learning_rate": 8.539524461595918e-06, "loss": 0.0413, "step": 59660 }, { "epoch": 7.41, "learning_rate": 8.539275488609487e-06, "loss": 0.0403, "step": 59670 }, { "epoch": 7.41, "learning_rate": 8.539026515623055e-06, "loss": 0.0489, "step": 59680 }, { "epoch": 7.41, "learning_rate": 8.538777542636625e-06, "loss": 0.0561, "step": 59690 }, { "epoch": 7.41, "learning_rate": 8.538528569650194e-06, "loss": 0.0285, "step": 59700 }, { "epoch": 7.41, "learning_rate": 8.538279596663762e-06, "loss": 0.0676, "step": 59710 }, { "epoch": 7.42, "learning_rate": 8.53803062367733e-06, "loss": 0.0441, "step": 59720 }, { "epoch": 7.42, "learning_rate": 8.537781650690901e-06, "loss": 0.0745, "step": 59730 }, { "epoch": 7.42, "learning_rate": 8.53753267770447e-06, "loss": 0.0724, "step": 59740 }, { "epoch": 7.42, "learning_rate": 8.53728370471804e-06, "loss": 0.0562, "step": 59750 }, { "epoch": 7.42, "learning_rate": 8.537034731731608e-06, "loss": 0.0471, "step": 59760 }, { "epoch": 7.42, "learning_rate": 8.536785758745177e-06, "loss": 0.0542, "step": 59770 }, { "epoch": 7.42, "learning_rate": 8.536536785758745e-06, "loss": 0.0372, "step": 59780 }, { "epoch": 7.42, "learning_rate": 8.536287812772315e-06, "loss": 0.079, "step": 59790 }, { "epoch": 7.43, "learning_rate": 8.536038839785884e-06, "loss": 0.0393, "step": 59800 }, { "epoch": 7.43, "learning_rate": 8.535789866799453e-06, "loss": 0.0667, "step": 59810 }, { "epoch": 7.43, "learning_rate": 8.535540893813023e-06, "loss": 0.051, "step": 59820 }, { "epoch": 7.43, "learning_rate": 8.535291920826591e-06, "loss": 0.0715, "step": 59830 }, { "epoch": 7.43, "learning_rate": 8.53504294784016e-06, "loss": 0.0686, "step": 59840 }, { "epoch": 7.43, "learning_rate": 8.534793974853728e-06, "loss": 0.0648, "step": 59850 }, { "epoch": 7.43, "learning_rate": 8.534545001867298e-06, "loss": 0.0483, "step": 59860 }, { "epoch": 7.43, "learning_rate": 8.534296028880867e-06, "loss": 0.0414, "step": 59870 }, { "epoch": 7.44, "learning_rate": 8.534047055894437e-06, "loss": 0.0643, "step": 59880 }, { "epoch": 7.44, "learning_rate": 8.533798082908004e-06, "loss": 0.0436, "step": 59890 }, { "epoch": 7.44, "learning_rate": 8.533549109921574e-06, "loss": 0.037, "step": 59900 }, { "epoch": 7.44, "learning_rate": 8.533300136935143e-06, "loss": 0.0377, "step": 59910 }, { "epoch": 7.44, "learning_rate": 8.533051163948713e-06, "loss": 0.0407, "step": 59920 }, { "epoch": 7.44, "learning_rate": 8.532802190962281e-06, "loss": 0.0612, "step": 59930 }, { "epoch": 7.44, "learning_rate": 8.53255321797585e-06, "loss": 0.0497, "step": 59940 }, { "epoch": 7.44, "learning_rate": 8.532304244989419e-06, "loss": 0.0424, "step": 59950 }, { "epoch": 7.45, "learning_rate": 8.532055272002989e-06, "loss": 0.0513, "step": 59960 }, { "epoch": 7.45, "learning_rate": 8.531806299016557e-06, "loss": 0.0594, "step": 59970 }, { "epoch": 7.45, "learning_rate": 8.531557326030126e-06, "loss": 0.0444, "step": 59980 }, { "epoch": 7.45, "learning_rate": 8.531308353043696e-06, "loss": 0.0348, "step": 59990 }, { "epoch": 7.45, "learning_rate": 8.531059380057264e-06, "loss": 0.047, "step": 60000 }, { "epoch": 7.45, "eval_bleu": 89.3645, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7588, "eval_has_error_f1": 0.668, "eval_loss": 0.05351456254720688, "eval_runtime": 1327.0468, "eval_samples_per_second": 3.013, "eval_steps_per_second": 0.754, "step": 60000 }, { "epoch": 7.45, "learning_rate": 8.530810407070833e-06, "loss": 0.0412, "step": 60010 }, { "epoch": 7.45, "learning_rate": 8.530561434084402e-06, "loss": 0.0304, "step": 60020 }, { "epoch": 7.45, "learning_rate": 8.530312461097972e-06, "loss": 0.0511, "step": 60030 }, { "epoch": 7.46, "learning_rate": 8.53006348811154e-06, "loss": 0.0594, "step": 60040 }, { "epoch": 7.46, "learning_rate": 8.52981451512511e-06, "loss": 0.0594, "step": 60050 }, { "epoch": 7.46, "learning_rate": 8.529565542138679e-06, "loss": 0.0504, "step": 60060 }, { "epoch": 7.46, "learning_rate": 8.529316569152247e-06, "loss": 0.0493, "step": 60070 }, { "epoch": 7.46, "learning_rate": 8.529067596165816e-06, "loss": 0.0684, "step": 60080 }, { "epoch": 7.46, "learning_rate": 8.528818623179386e-06, "loss": 0.0338, "step": 60090 }, { "epoch": 7.46, "learning_rate": 8.528569650192955e-06, "loss": 0.061, "step": 60100 }, { "epoch": 7.46, "learning_rate": 8.528320677206525e-06, "loss": 0.0468, "step": 60110 }, { "epoch": 7.47, "learning_rate": 8.528071704220093e-06, "loss": 0.017, "step": 60120 }, { "epoch": 7.47, "learning_rate": 8.527822731233662e-06, "loss": 0.0572, "step": 60130 }, { "epoch": 7.47, "learning_rate": 8.52757375824723e-06, "loss": 0.0599, "step": 60140 }, { "epoch": 7.47, "learning_rate": 8.5273247852608e-06, "loss": 0.0549, "step": 60150 }, { "epoch": 7.47, "learning_rate": 8.52707581227437e-06, "loss": 0.0618, "step": 60160 }, { "epoch": 7.47, "learning_rate": 8.526826839287938e-06, "loss": 0.0494, "step": 60170 }, { "epoch": 7.47, "learning_rate": 8.526577866301508e-06, "loss": 0.0669, "step": 60180 }, { "epoch": 7.47, "learning_rate": 8.526328893315076e-06, "loss": 0.0384, "step": 60190 }, { "epoch": 7.48, "learning_rate": 8.526079920328645e-06, "loss": 0.0678, "step": 60200 }, { "epoch": 7.48, "learning_rate": 8.525830947342213e-06, "loss": 0.0364, "step": 60210 }, { "epoch": 7.48, "learning_rate": 8.525581974355784e-06, "loss": 0.0553, "step": 60220 }, { "epoch": 7.48, "learning_rate": 8.525333001369352e-06, "loss": 0.0823, "step": 60230 }, { "epoch": 7.48, "learning_rate": 8.52508402838292e-06, "loss": 0.0807, "step": 60240 }, { "epoch": 7.48, "learning_rate": 8.52483505539649e-06, "loss": 0.0569, "step": 60250 }, { "epoch": 7.48, "learning_rate": 8.52458608241006e-06, "loss": 0.0596, "step": 60260 }, { "epoch": 7.48, "learning_rate": 8.524337109423628e-06, "loss": 0.0511, "step": 60270 }, { "epoch": 7.49, "learning_rate": 8.524088136437198e-06, "loss": 0.0584, "step": 60280 }, { "epoch": 7.49, "learning_rate": 8.523839163450767e-06, "loss": 0.0416, "step": 60290 }, { "epoch": 7.49, "learning_rate": 8.523590190464335e-06, "loss": 0.045, "step": 60300 }, { "epoch": 7.49, "learning_rate": 8.523341217477904e-06, "loss": 0.0441, "step": 60310 }, { "epoch": 7.49, "learning_rate": 8.523092244491474e-06, "loss": 0.0529, "step": 60320 }, { "epoch": 7.49, "learning_rate": 8.522843271505042e-06, "loss": 0.0502, "step": 60330 }, { "epoch": 7.49, "learning_rate": 8.522594298518611e-06, "loss": 0.0351, "step": 60340 }, { "epoch": 7.49, "learning_rate": 8.522345325532181e-06, "loss": 0.0419, "step": 60350 }, { "epoch": 7.5, "learning_rate": 8.52209635254575e-06, "loss": 0.0858, "step": 60360 }, { "epoch": 7.5, "learning_rate": 8.521847379559318e-06, "loss": 0.0363, "step": 60370 }, { "epoch": 7.5, "learning_rate": 8.521598406572887e-06, "loss": 0.045, "step": 60380 }, { "epoch": 7.5, "learning_rate": 8.521349433586457e-06, "loss": 0.0666, "step": 60390 }, { "epoch": 7.5, "learning_rate": 8.521100460600025e-06, "loss": 0.0529, "step": 60400 }, { "epoch": 7.5, "learning_rate": 8.520851487613596e-06, "loss": 0.0418, "step": 60410 }, { "epoch": 7.5, "learning_rate": 8.520602514627162e-06, "loss": 0.0507, "step": 60420 }, { "epoch": 7.5, "learning_rate": 8.520353541640733e-06, "loss": 0.0432, "step": 60430 }, { "epoch": 7.51, "learning_rate": 8.520104568654301e-06, "loss": 0.0745, "step": 60440 }, { "epoch": 7.51, "learning_rate": 8.519855595667871e-06, "loss": 0.0757, "step": 60450 }, { "epoch": 7.51, "learning_rate": 8.51960662268144e-06, "loss": 0.0531, "step": 60460 }, { "epoch": 7.51, "learning_rate": 8.519357649695008e-06, "loss": 0.0404, "step": 60470 }, { "epoch": 7.51, "learning_rate": 8.519108676708577e-06, "loss": 0.0762, "step": 60480 }, { "epoch": 7.51, "learning_rate": 8.518859703722147e-06, "loss": 0.0344, "step": 60490 }, { "epoch": 7.51, "learning_rate": 8.518610730735716e-06, "loss": 0.0494, "step": 60500 }, { "epoch": 7.51, "learning_rate": 8.518361757749284e-06, "loss": 0.0537, "step": 60510 }, { "epoch": 7.52, "learning_rate": 8.518112784762854e-06, "loss": 0.0265, "step": 60520 }, { "epoch": 7.52, "learning_rate": 8.517863811776423e-06, "loss": 0.0582, "step": 60530 }, { "epoch": 7.52, "learning_rate": 8.517614838789991e-06, "loss": 0.0739, "step": 60540 }, { "epoch": 7.52, "learning_rate": 8.51736586580356e-06, "loss": 0.0522, "step": 60550 }, { "epoch": 7.52, "learning_rate": 8.51711689281713e-06, "loss": 0.0425, "step": 60560 }, { "epoch": 7.52, "learning_rate": 8.516867919830699e-06, "loss": 0.0438, "step": 60570 }, { "epoch": 7.52, "learning_rate": 8.516618946844269e-06, "loss": 0.0609, "step": 60580 }, { "epoch": 7.52, "learning_rate": 8.516369973857837e-06, "loss": 0.0557, "step": 60590 }, { "epoch": 7.53, "learning_rate": 8.516121000871406e-06, "loss": 0.0425, "step": 60600 }, { "epoch": 7.53, "learning_rate": 8.515872027884974e-06, "loss": 0.0614, "step": 60610 }, { "epoch": 7.53, "learning_rate": 8.515623054898545e-06, "loss": 0.0485, "step": 60620 }, { "epoch": 7.53, "learning_rate": 8.515374081912113e-06, "loss": 0.0552, "step": 60630 }, { "epoch": 7.53, "learning_rate": 8.515125108925683e-06, "loss": 0.0404, "step": 60640 }, { "epoch": 7.53, "learning_rate": 8.514876135939252e-06, "loss": 0.0688, "step": 60650 }, { "epoch": 7.53, "learning_rate": 8.51462716295282e-06, "loss": 0.0517, "step": 60660 }, { "epoch": 7.53, "learning_rate": 8.514378189966389e-06, "loss": 0.041, "step": 60670 }, { "epoch": 7.54, "learning_rate": 8.514129216979959e-06, "loss": 0.0654, "step": 60680 }, { "epoch": 7.54, "learning_rate": 8.513880243993528e-06, "loss": 0.0623, "step": 60690 }, { "epoch": 7.54, "learning_rate": 8.513631271007096e-06, "loss": 0.0604, "step": 60700 }, { "epoch": 7.54, "learning_rate": 8.513382298020666e-06, "loss": 0.0329, "step": 60710 }, { "epoch": 7.54, "learning_rate": 8.513133325034235e-06, "loss": 0.0423, "step": 60720 }, { "epoch": 7.54, "learning_rate": 8.512884352047803e-06, "loss": 0.0502, "step": 60730 }, { "epoch": 7.54, "learning_rate": 8.512635379061372e-06, "loss": 0.0508, "step": 60740 }, { "epoch": 7.54, "learning_rate": 8.512386406074942e-06, "loss": 0.0471, "step": 60750 }, { "epoch": 7.54, "learning_rate": 8.51213743308851e-06, "loss": 0.0506, "step": 60760 }, { "epoch": 7.55, "learning_rate": 8.511888460102081e-06, "loss": 0.0374, "step": 60770 }, { "epoch": 7.55, "learning_rate": 8.511639487115648e-06, "loss": 0.0669, "step": 60780 }, { "epoch": 7.55, "learning_rate": 8.511390514129218e-06, "loss": 0.047, "step": 60790 }, { "epoch": 7.55, "learning_rate": 8.511141541142786e-06, "loss": 0.0446, "step": 60800 }, { "epoch": 7.55, "learning_rate": 8.510892568156357e-06, "loss": 0.046, "step": 60810 }, { "epoch": 7.55, "learning_rate": 8.510643595169925e-06, "loss": 0.0395, "step": 60820 }, { "epoch": 7.55, "learning_rate": 8.510394622183494e-06, "loss": 0.0654, "step": 60830 }, { "epoch": 7.55, "learning_rate": 8.510145649197062e-06, "loss": 0.0377, "step": 60840 }, { "epoch": 7.56, "learning_rate": 8.509896676210632e-06, "loss": 0.0393, "step": 60850 }, { "epoch": 7.56, "learning_rate": 8.509647703224201e-06, "loss": 0.0586, "step": 60860 }, { "epoch": 7.56, "learning_rate": 8.50939873023777e-06, "loss": 0.0423, "step": 60870 }, { "epoch": 7.56, "learning_rate": 8.50914975725134e-06, "loss": 0.0515, "step": 60880 }, { "epoch": 7.56, "learning_rate": 8.508900784264908e-06, "loss": 0.0614, "step": 60890 }, { "epoch": 7.56, "learning_rate": 8.508651811278477e-06, "loss": 0.0484, "step": 60900 }, { "epoch": 7.56, "learning_rate": 8.508402838292045e-06, "loss": 0.0648, "step": 60910 }, { "epoch": 7.56, "learning_rate": 8.508153865305615e-06, "loss": 0.0589, "step": 60920 }, { "epoch": 7.57, "learning_rate": 8.507904892319184e-06, "loss": 0.0574, "step": 60930 }, { "epoch": 7.57, "learning_rate": 8.507655919332754e-06, "loss": 0.0539, "step": 60940 }, { "epoch": 7.57, "learning_rate": 8.507406946346321e-06, "loss": 0.0522, "step": 60950 }, { "epoch": 7.57, "learning_rate": 8.507157973359891e-06, "loss": 0.0387, "step": 60960 }, { "epoch": 7.57, "learning_rate": 8.50690900037346e-06, "loss": 0.059, "step": 60970 }, { "epoch": 7.57, "learning_rate": 8.50666002738703e-06, "loss": 0.0457, "step": 60980 }, { "epoch": 7.57, "learning_rate": 8.506411054400598e-06, "loss": 0.0617, "step": 60990 }, { "epoch": 7.57, "learning_rate": 8.506162081414167e-06, "loss": 0.0756, "step": 61000 }, { "epoch": 7.58, "learning_rate": 8.505913108427735e-06, "loss": 0.0377, "step": 61010 }, { "epoch": 7.58, "learning_rate": 8.505664135441306e-06, "loss": 0.0338, "step": 61020 }, { "epoch": 7.58, "learning_rate": 8.505415162454874e-06, "loss": 0.0528, "step": 61030 }, { "epoch": 7.58, "learning_rate": 8.505166189468443e-06, "loss": 0.0451, "step": 61040 }, { "epoch": 7.58, "learning_rate": 8.504917216482013e-06, "loss": 0.0435, "step": 61050 }, { "epoch": 7.58, "learning_rate": 8.504668243495581e-06, "loss": 0.0285, "step": 61060 }, { "epoch": 7.58, "learning_rate": 8.50441927050915e-06, "loss": 0.0436, "step": 61070 }, { "epoch": 7.58, "learning_rate": 8.504170297522718e-06, "loss": 0.0705, "step": 61080 }, { "epoch": 7.59, "learning_rate": 8.503921324536289e-06, "loss": 0.0338, "step": 61090 }, { "epoch": 7.59, "learning_rate": 8.503672351549857e-06, "loss": 0.0461, "step": 61100 }, { "epoch": 7.59, "learning_rate": 8.503423378563427e-06, "loss": 0.0529, "step": 61110 }, { "epoch": 7.59, "learning_rate": 8.503174405576996e-06, "loss": 0.0543, "step": 61120 }, { "epoch": 7.59, "learning_rate": 8.502925432590564e-06, "loss": 0.0448, "step": 61130 }, { "epoch": 7.59, "learning_rate": 8.502676459604133e-06, "loss": 0.0429, "step": 61140 }, { "epoch": 7.59, "learning_rate": 8.502427486617703e-06, "loss": 0.0522, "step": 61150 }, { "epoch": 7.59, "learning_rate": 8.502178513631272e-06, "loss": 0.0458, "step": 61160 }, { "epoch": 7.6, "learning_rate": 8.501929540644842e-06, "loss": 0.0443, "step": 61170 }, { "epoch": 7.6, "learning_rate": 8.50168056765841e-06, "loss": 0.0712, "step": 61180 }, { "epoch": 7.6, "learning_rate": 8.501431594671979e-06, "loss": 0.0533, "step": 61190 }, { "epoch": 7.6, "learning_rate": 8.501182621685547e-06, "loss": 0.0566, "step": 61200 }, { "epoch": 7.6, "learning_rate": 8.500933648699118e-06, "loss": 0.0462, "step": 61210 }, { "epoch": 7.6, "learning_rate": 8.500684675712686e-06, "loss": 0.0215, "step": 61220 }, { "epoch": 7.6, "learning_rate": 8.500435702726255e-06, "loss": 0.0577, "step": 61230 }, { "epoch": 7.6, "learning_rate": 8.500186729739825e-06, "loss": 0.0558, "step": 61240 }, { "epoch": 7.61, "learning_rate": 8.499937756753393e-06, "loss": 0.0448, "step": 61250 }, { "epoch": 7.61, "learning_rate": 8.499688783766962e-06, "loss": 0.0652, "step": 61260 }, { "epoch": 7.61, "learning_rate": 8.49943981078053e-06, "loss": 0.0343, "step": 61270 }, { "epoch": 7.61, "learning_rate": 8.4991908377941e-06, "loss": 0.0711, "step": 61280 }, { "epoch": 7.61, "learning_rate": 8.498941864807669e-06, "loss": 0.0452, "step": 61290 }, { "epoch": 7.61, "learning_rate": 8.49869289182124e-06, "loss": 0.0631, "step": 61300 }, { "epoch": 7.61, "learning_rate": 8.498443918834806e-06, "loss": 0.0641, "step": 61310 }, { "epoch": 7.61, "learning_rate": 8.498194945848376e-06, "loss": 0.0397, "step": 61320 }, { "epoch": 7.62, "learning_rate": 8.497945972861945e-06, "loss": 0.0946, "step": 61330 }, { "epoch": 7.62, "learning_rate": 8.497696999875515e-06, "loss": 0.0474, "step": 61340 }, { "epoch": 7.62, "learning_rate": 8.497448026889084e-06, "loss": 0.0573, "step": 61350 }, { "epoch": 7.62, "learning_rate": 8.497199053902652e-06, "loss": 0.0493, "step": 61360 }, { "epoch": 7.62, "learning_rate": 8.49695008091622e-06, "loss": 0.0408, "step": 61370 }, { "epoch": 7.62, "learning_rate": 8.49670110792979e-06, "loss": 0.0588, "step": 61380 }, { "epoch": 7.62, "learning_rate": 8.49645213494336e-06, "loss": 0.0459, "step": 61390 }, { "epoch": 7.62, "learning_rate": 8.496203161956928e-06, "loss": 0.0403, "step": 61400 }, { "epoch": 7.63, "learning_rate": 8.495954188970498e-06, "loss": 0.0493, "step": 61410 }, { "epoch": 7.63, "learning_rate": 8.495705215984067e-06, "loss": 0.0584, "step": 61420 }, { "epoch": 7.63, "learning_rate": 8.495456242997635e-06, "loss": 0.053, "step": 61430 }, { "epoch": 7.63, "learning_rate": 8.495207270011204e-06, "loss": 0.0583, "step": 61440 }, { "epoch": 7.63, "learning_rate": 8.494958297024774e-06, "loss": 0.0411, "step": 61450 }, { "epoch": 7.63, "learning_rate": 8.494709324038342e-06, "loss": 0.0383, "step": 61460 }, { "epoch": 7.63, "learning_rate": 8.494460351051913e-06, "loss": 0.0586, "step": 61470 }, { "epoch": 7.63, "learning_rate": 8.494211378065481e-06, "loss": 0.047, "step": 61480 }, { "epoch": 7.64, "learning_rate": 8.49396240507905e-06, "loss": 0.0895, "step": 61490 }, { "epoch": 7.64, "learning_rate": 8.493713432092618e-06, "loss": 0.0577, "step": 61500 }, { "epoch": 7.64, "learning_rate": 8.493464459106188e-06, "loss": 0.0273, "step": 61510 }, { "epoch": 7.64, "learning_rate": 8.493215486119757e-06, "loss": 0.0311, "step": 61520 }, { "epoch": 7.64, "learning_rate": 8.492966513133325e-06, "loss": 0.0601, "step": 61530 }, { "epoch": 7.64, "learning_rate": 8.492717540146896e-06, "loss": 0.0684, "step": 61540 }, { "epoch": 7.64, "learning_rate": 8.492468567160464e-06, "loss": 0.0423, "step": 61550 }, { "epoch": 7.64, "learning_rate": 8.492219594174033e-06, "loss": 0.0358, "step": 61560 }, { "epoch": 7.65, "learning_rate": 8.491970621187601e-06, "loss": 0.0464, "step": 61570 }, { "epoch": 7.65, "learning_rate": 8.491721648201171e-06, "loss": 0.0501, "step": 61580 }, { "epoch": 7.65, "learning_rate": 8.49147267521474e-06, "loss": 0.0472, "step": 61590 }, { "epoch": 7.65, "learning_rate": 8.491223702228308e-06, "loss": 0.0678, "step": 61600 }, { "epoch": 7.65, "learning_rate": 8.490974729241877e-06, "loss": 0.0508, "step": 61610 }, { "epoch": 7.65, "learning_rate": 8.490725756255447e-06, "loss": 0.0767, "step": 61620 }, { "epoch": 7.65, "learning_rate": 8.490476783269016e-06, "loss": 0.0654, "step": 61630 }, { "epoch": 7.65, "learning_rate": 8.490227810282586e-06, "loss": 0.0523, "step": 61640 }, { "epoch": 7.66, "learning_rate": 8.489978837296154e-06, "loss": 0.0566, "step": 61650 }, { "epoch": 7.66, "learning_rate": 8.489729864309723e-06, "loss": 0.0366, "step": 61660 }, { "epoch": 7.66, "learning_rate": 8.489480891323291e-06, "loss": 0.0437, "step": 61670 }, { "epoch": 7.66, "learning_rate": 8.489231918336862e-06, "loss": 0.0542, "step": 61680 }, { "epoch": 7.66, "learning_rate": 8.48898294535043e-06, "loss": 0.0367, "step": 61690 }, { "epoch": 7.66, "learning_rate": 8.488733972364e-06, "loss": 0.0532, "step": 61700 }, { "epoch": 7.66, "learning_rate": 8.488484999377569e-06, "loss": 0.0474, "step": 61710 }, { "epoch": 7.66, "learning_rate": 8.488236026391137e-06, "loss": 0.067, "step": 61720 }, { "epoch": 7.67, "learning_rate": 8.487987053404706e-06, "loss": 0.0845, "step": 61730 }, { "epoch": 7.67, "learning_rate": 8.487738080418276e-06, "loss": 0.0811, "step": 61740 }, { "epoch": 7.67, "learning_rate": 8.487489107431845e-06, "loss": 0.0523, "step": 61750 }, { "epoch": 7.67, "learning_rate": 8.487240134445413e-06, "loss": 0.0501, "step": 61760 }, { "epoch": 7.67, "learning_rate": 8.486991161458983e-06, "loss": 0.0457, "step": 61770 }, { "epoch": 7.67, "learning_rate": 8.486742188472552e-06, "loss": 0.0458, "step": 61780 }, { "epoch": 7.67, "learning_rate": 8.48649321548612e-06, "loss": 0.0542, "step": 61790 }, { "epoch": 7.67, "learning_rate": 8.486244242499689e-06, "loss": 0.0646, "step": 61800 }, { "epoch": 7.68, "learning_rate": 8.485995269513259e-06, "loss": 0.044, "step": 61810 }, { "epoch": 7.68, "learning_rate": 8.485746296526828e-06, "loss": 0.0295, "step": 61820 }, { "epoch": 7.68, "learning_rate": 8.485497323540398e-06, "loss": 0.0732, "step": 61830 }, { "epoch": 7.68, "learning_rate": 8.485248350553965e-06, "loss": 0.0597, "step": 61840 }, { "epoch": 7.68, "learning_rate": 8.484999377567535e-06, "loss": 0.0628, "step": 61850 }, { "epoch": 7.68, "learning_rate": 8.484750404581103e-06, "loss": 0.0431, "step": 61860 }, { "epoch": 7.68, "learning_rate": 8.484501431594673e-06, "loss": 0.0287, "step": 61870 }, { "epoch": 7.68, "learning_rate": 8.484252458608242e-06, "loss": 0.0608, "step": 61880 }, { "epoch": 7.69, "learning_rate": 8.48400348562181e-06, "loss": 0.0365, "step": 61890 }, { "epoch": 7.69, "learning_rate": 8.483754512635379e-06, "loss": 0.056, "step": 61900 }, { "epoch": 7.69, "learning_rate": 8.48350553964895e-06, "loss": 0.0389, "step": 61910 }, { "epoch": 7.69, "learning_rate": 8.483256566662518e-06, "loss": 0.0384, "step": 61920 }, { "epoch": 7.69, "learning_rate": 8.483007593676086e-06, "loss": 0.0549, "step": 61930 }, { "epoch": 7.69, "learning_rate": 8.482758620689656e-06, "loss": 0.0436, "step": 61940 }, { "epoch": 7.69, "learning_rate": 8.482509647703225e-06, "loss": 0.0431, "step": 61950 }, { "epoch": 7.69, "learning_rate": 8.482260674716794e-06, "loss": 0.0386, "step": 61960 }, { "epoch": 7.7, "learning_rate": 8.482011701730362e-06, "loss": 0.0276, "step": 61970 }, { "epoch": 7.7, "learning_rate": 8.481762728743932e-06, "loss": 0.0413, "step": 61980 }, { "epoch": 7.7, "learning_rate": 8.4815137557575e-06, "loss": 0.0692, "step": 61990 }, { "epoch": 7.7, "learning_rate": 8.481264782771071e-06, "loss": 0.0405, "step": 62000 }, { "epoch": 7.7, "learning_rate": 8.48101580978464e-06, "loss": 0.0428, "step": 62010 }, { "epoch": 7.7, "learning_rate": 8.480766836798208e-06, "loss": 0.0383, "step": 62020 }, { "epoch": 7.7, "learning_rate": 8.480517863811777e-06, "loss": 0.0799, "step": 62030 }, { "epoch": 7.7, "learning_rate": 8.480268890825347e-06, "loss": 0.0636, "step": 62040 }, { "epoch": 7.71, "learning_rate": 8.480019917838915e-06, "loss": 0.0533, "step": 62050 }, { "epoch": 7.71, "learning_rate": 8.479770944852484e-06, "loss": 0.0412, "step": 62060 }, { "epoch": 7.71, "learning_rate": 8.479521971866054e-06, "loss": 0.0624, "step": 62070 }, { "epoch": 7.71, "learning_rate": 8.479272998879622e-06, "loss": 0.0705, "step": 62080 }, { "epoch": 7.71, "learning_rate": 8.479024025893191e-06, "loss": 0.0421, "step": 62090 }, { "epoch": 7.71, "learning_rate": 8.47877505290676e-06, "loss": 0.044, "step": 62100 }, { "epoch": 7.71, "learning_rate": 8.47852607992033e-06, "loss": 0.047, "step": 62110 }, { "epoch": 7.71, "learning_rate": 8.478277106933898e-06, "loss": 0.0437, "step": 62120 }, { "epoch": 7.72, "learning_rate": 8.478028133947468e-06, "loss": 0.0973, "step": 62130 }, { "epoch": 7.72, "learning_rate": 8.477779160961035e-06, "loss": 0.0437, "step": 62140 }, { "epoch": 7.72, "learning_rate": 8.477530187974605e-06, "loss": 0.0403, "step": 62150 }, { "epoch": 7.72, "learning_rate": 8.477281214988174e-06, "loss": 0.0484, "step": 62160 }, { "epoch": 7.72, "learning_rate": 8.477032242001744e-06, "loss": 0.0313, "step": 62170 }, { "epoch": 7.72, "learning_rate": 8.476783269015313e-06, "loss": 0.0605, "step": 62180 }, { "epoch": 7.72, "learning_rate": 8.476534296028883e-06, "loss": 0.0519, "step": 62190 }, { "epoch": 7.72, "learning_rate": 8.47628532304245e-06, "loss": 0.0409, "step": 62200 }, { "epoch": 7.73, "learning_rate": 8.47603635005602e-06, "loss": 0.0399, "step": 62210 }, { "epoch": 7.73, "learning_rate": 8.475787377069588e-06, "loss": 0.032, "step": 62220 }, { "epoch": 7.73, "learning_rate": 8.475538404083159e-06, "loss": 0.0498, "step": 62230 }, { "epoch": 7.73, "learning_rate": 8.475289431096727e-06, "loss": 0.042, "step": 62240 }, { "epoch": 7.73, "learning_rate": 8.475040458110296e-06, "loss": 0.0337, "step": 62250 }, { "epoch": 7.73, "learning_rate": 8.474791485123864e-06, "loss": 0.0568, "step": 62260 }, { "epoch": 7.73, "learning_rate": 8.474542512137434e-06, "loss": 0.0399, "step": 62270 }, { "epoch": 7.73, "learning_rate": 8.474293539151003e-06, "loss": 0.0416, "step": 62280 }, { "epoch": 7.73, "learning_rate": 8.474044566164571e-06, "loss": 0.0361, "step": 62290 }, { "epoch": 7.74, "learning_rate": 8.473795593178142e-06, "loss": 0.0381, "step": 62300 }, { "epoch": 7.74, "learning_rate": 8.47354662019171e-06, "loss": 0.0361, "step": 62310 }, { "epoch": 7.74, "learning_rate": 8.473297647205279e-06, "loss": 0.0413, "step": 62320 }, { "epoch": 7.74, "learning_rate": 8.473048674218847e-06, "loss": 0.102, "step": 62330 }, { "epoch": 7.74, "learning_rate": 8.472799701232417e-06, "loss": 0.0572, "step": 62340 }, { "epoch": 7.74, "learning_rate": 8.472550728245986e-06, "loss": 0.0374, "step": 62350 }, { "epoch": 7.74, "learning_rate": 8.472301755259556e-06, "loss": 0.0491, "step": 62360 }, { "epoch": 7.74, "learning_rate": 8.472052782273123e-06, "loss": 0.0561, "step": 62370 }, { "epoch": 7.75, "learning_rate": 8.471803809286693e-06, "loss": 0.0581, "step": 62380 }, { "epoch": 7.75, "learning_rate": 8.471554836300262e-06, "loss": 0.0635, "step": 62390 }, { "epoch": 7.75, "learning_rate": 8.471305863313832e-06, "loss": 0.0571, "step": 62400 }, { "epoch": 7.75, "learning_rate": 8.4710568903274e-06, "loss": 0.0381, "step": 62410 }, { "epoch": 7.75, "learning_rate": 8.470807917340969e-06, "loss": 0.0353, "step": 62420 }, { "epoch": 7.75, "learning_rate": 8.470558944354537e-06, "loss": 0.0531, "step": 62430 }, { "epoch": 7.75, "learning_rate": 8.470309971368108e-06, "loss": 0.0332, "step": 62440 }, { "epoch": 7.75, "learning_rate": 8.470060998381676e-06, "loss": 0.0633, "step": 62450 }, { "epoch": 7.76, "learning_rate": 8.469812025395245e-06, "loss": 0.0537, "step": 62460 }, { "epoch": 7.76, "learning_rate": 8.469563052408815e-06, "loss": 0.0289, "step": 62470 }, { "epoch": 7.76, "learning_rate": 8.469314079422383e-06, "loss": 0.0712, "step": 62480 }, { "epoch": 7.76, "learning_rate": 8.469065106435952e-06, "loss": 0.057, "step": 62490 }, { "epoch": 7.76, "learning_rate": 8.46881613344952e-06, "loss": 0.0715, "step": 62500 }, { "epoch": 7.76, "learning_rate": 8.46856716046309e-06, "loss": 0.0319, "step": 62510 }, { "epoch": 7.76, "learning_rate": 8.46831818747666e-06, "loss": 0.0481, "step": 62520 }, { "epoch": 7.76, "learning_rate": 8.46806921449023e-06, "loss": 0.1025, "step": 62530 }, { "epoch": 7.77, "learning_rate": 8.467820241503798e-06, "loss": 0.0414, "step": 62540 }, { "epoch": 7.77, "learning_rate": 8.467571268517366e-06, "loss": 0.0381, "step": 62550 }, { "epoch": 7.77, "learning_rate": 8.467322295530935e-06, "loss": 0.0487, "step": 62560 }, { "epoch": 7.77, "learning_rate": 8.467073322544505e-06, "loss": 0.0304, "step": 62570 }, { "epoch": 7.77, "learning_rate": 8.466824349558074e-06, "loss": 0.043, "step": 62580 }, { "epoch": 7.77, "learning_rate": 8.466575376571642e-06, "loss": 0.0425, "step": 62590 }, { "epoch": 7.77, "learning_rate": 8.466326403585212e-06, "loss": 0.0297, "step": 62600 }, { "epoch": 7.77, "learning_rate": 8.466077430598781e-06, "loss": 0.0324, "step": 62610 }, { "epoch": 7.78, "learning_rate": 8.46582845761235e-06, "loss": 0.0299, "step": 62620 }, { "epoch": 7.78, "learning_rate": 8.465579484625918e-06, "loss": 0.0561, "step": 62630 }, { "epoch": 7.78, "learning_rate": 8.465330511639488e-06, "loss": 0.0357, "step": 62640 }, { "epoch": 7.78, "learning_rate": 8.465081538653057e-06, "loss": 0.0791, "step": 62650 }, { "epoch": 7.78, "learning_rate": 8.464832565666627e-06, "loss": 0.0443, "step": 62660 }, { "epoch": 7.78, "learning_rate": 8.464583592680194e-06, "loss": 0.0477, "step": 62670 }, { "epoch": 7.78, "learning_rate": 8.464334619693764e-06, "loss": 0.0522, "step": 62680 }, { "epoch": 7.78, "learning_rate": 8.464085646707332e-06, "loss": 0.0378, "step": 62690 }, { "epoch": 7.79, "learning_rate": 8.463836673720903e-06, "loss": 0.0683, "step": 62700 }, { "epoch": 7.79, "learning_rate": 8.463587700734471e-06, "loss": 0.0462, "step": 62710 }, { "epoch": 7.79, "learning_rate": 8.463338727748041e-06, "loss": 0.046, "step": 62720 }, { "epoch": 7.79, "learning_rate": 8.463089754761608e-06, "loss": 0.0644, "step": 62730 }, { "epoch": 7.79, "learning_rate": 8.462840781775178e-06, "loss": 0.0671, "step": 62740 }, { "epoch": 7.79, "learning_rate": 8.462591808788747e-06, "loss": 0.0506, "step": 62750 }, { "epoch": 7.79, "learning_rate": 8.462342835802317e-06, "loss": 0.0473, "step": 62760 }, { "epoch": 7.79, "learning_rate": 8.462093862815886e-06, "loss": 0.0405, "step": 62770 }, { "epoch": 7.8, "learning_rate": 8.461844889829454e-06, "loss": 0.0476, "step": 62780 }, { "epoch": 7.8, "learning_rate": 8.461595916843023e-06, "loss": 0.0329, "step": 62790 }, { "epoch": 7.8, "learning_rate": 8.461346943856593e-06, "loss": 0.0292, "step": 62800 }, { "epoch": 7.8, "learning_rate": 8.461097970870161e-06, "loss": 0.0583, "step": 62810 }, { "epoch": 7.8, "learning_rate": 8.46084899788373e-06, "loss": 0.0438, "step": 62820 }, { "epoch": 7.8, "learning_rate": 8.4606000248973e-06, "loss": 0.0598, "step": 62830 }, { "epoch": 7.8, "learning_rate": 8.460351051910869e-06, "loss": 0.043, "step": 62840 }, { "epoch": 7.8, "learning_rate": 8.460102078924437e-06, "loss": 0.0633, "step": 62850 }, { "epoch": 7.81, "learning_rate": 8.459853105938006e-06, "loss": 0.0573, "step": 62860 }, { "epoch": 7.81, "learning_rate": 8.459604132951576e-06, "loss": 0.0427, "step": 62870 }, { "epoch": 7.81, "learning_rate": 8.459355159965144e-06, "loss": 0.0643, "step": 62880 }, { "epoch": 7.81, "learning_rate": 8.459106186978715e-06, "loss": 0.0844, "step": 62890 }, { "epoch": 7.81, "learning_rate": 8.458857213992281e-06, "loss": 0.0596, "step": 62900 }, { "epoch": 7.81, "learning_rate": 8.458608241005852e-06, "loss": 0.0326, "step": 62910 }, { "epoch": 7.81, "learning_rate": 8.45835926801942e-06, "loss": 0.037, "step": 62920 }, { "epoch": 7.81, "learning_rate": 8.45811029503299e-06, "loss": 0.0756, "step": 62930 }, { "epoch": 7.82, "learning_rate": 8.457861322046559e-06, "loss": 0.0765, "step": 62940 }, { "epoch": 7.82, "learning_rate": 8.457612349060127e-06, "loss": 0.0473, "step": 62950 }, { "epoch": 7.82, "learning_rate": 8.457363376073696e-06, "loss": 0.0486, "step": 62960 }, { "epoch": 7.82, "learning_rate": 8.457114403087266e-06, "loss": 0.0384, "step": 62970 }, { "epoch": 7.82, "learning_rate": 8.456865430100835e-06, "loss": 0.0432, "step": 62980 }, { "epoch": 7.82, "learning_rate": 8.456616457114403e-06, "loss": 0.0388, "step": 62990 }, { "epoch": 7.82, "learning_rate": 8.456367484127973e-06, "loss": 0.0598, "step": 63000 }, { "epoch": 7.82, "learning_rate": 8.456118511141542e-06, "loss": 0.0454, "step": 63010 }, { "epoch": 7.83, "learning_rate": 8.45586953815511e-06, "loss": 0.0382, "step": 63020 }, { "epoch": 7.83, "learning_rate": 8.455620565168679e-06, "loss": 0.0579, "step": 63030 }, { "epoch": 7.83, "learning_rate": 8.455371592182249e-06, "loss": 0.0513, "step": 63040 }, { "epoch": 7.83, "learning_rate": 8.455122619195818e-06, "loss": 0.0475, "step": 63050 }, { "epoch": 7.83, "learning_rate": 8.454873646209388e-06, "loss": 0.0527, "step": 63060 }, { "epoch": 7.83, "learning_rate": 8.454624673222956e-06, "loss": 0.076, "step": 63070 }, { "epoch": 7.83, "learning_rate": 8.454375700236525e-06, "loss": 0.0572, "step": 63080 }, { "epoch": 7.83, "learning_rate": 8.454126727250093e-06, "loss": 0.0694, "step": 63090 }, { "epoch": 7.84, "learning_rate": 8.453877754263664e-06, "loss": 0.0494, "step": 63100 }, { "epoch": 7.84, "learning_rate": 8.453628781277232e-06, "loss": 0.0489, "step": 63110 }, { "epoch": 7.84, "learning_rate": 8.4533798082908e-06, "loss": 0.033, "step": 63120 }, { "epoch": 7.84, "learning_rate": 8.453130835304371e-06, "loss": 0.0468, "step": 63130 }, { "epoch": 7.84, "learning_rate": 8.45288186231794e-06, "loss": 0.0632, "step": 63140 }, { "epoch": 7.84, "learning_rate": 8.452632889331508e-06, "loss": 0.0891, "step": 63150 }, { "epoch": 7.84, "learning_rate": 8.452383916345076e-06, "loss": 0.0454, "step": 63160 }, { "epoch": 7.84, "learning_rate": 8.452134943358647e-06, "loss": 0.03, "step": 63170 }, { "epoch": 7.85, "learning_rate": 8.451885970372215e-06, "loss": 0.079, "step": 63180 }, { "epoch": 7.85, "learning_rate": 8.451636997385785e-06, "loss": 0.0429, "step": 63190 }, { "epoch": 7.85, "learning_rate": 8.451388024399352e-06, "loss": 0.047, "step": 63200 }, { "epoch": 7.85, "learning_rate": 8.451139051412922e-06, "loss": 0.0445, "step": 63210 }, { "epoch": 7.85, "learning_rate": 8.450890078426491e-06, "loss": 0.0591, "step": 63220 }, { "epoch": 7.85, "learning_rate": 8.450641105440061e-06, "loss": 0.0481, "step": 63230 }, { "epoch": 7.85, "learning_rate": 8.45039213245363e-06, "loss": 0.0443, "step": 63240 }, { "epoch": 7.85, "learning_rate": 8.4501431594672e-06, "loss": 0.0444, "step": 63250 }, { "epoch": 7.86, "learning_rate": 8.449894186480767e-06, "loss": 0.0436, "step": 63260 }, { "epoch": 7.86, "learning_rate": 8.449645213494337e-06, "loss": 0.0307, "step": 63270 }, { "epoch": 7.86, "learning_rate": 8.449396240507905e-06, "loss": 0.0442, "step": 63280 }, { "epoch": 7.86, "learning_rate": 8.449147267521476e-06, "loss": 0.0539, "step": 63290 }, { "epoch": 7.86, "learning_rate": 8.448898294535044e-06, "loss": 0.0441, "step": 63300 }, { "epoch": 7.86, "learning_rate": 8.448649321548613e-06, "loss": 0.0395, "step": 63310 }, { "epoch": 7.86, "learning_rate": 8.448400348562181e-06, "loss": 0.0457, "step": 63320 }, { "epoch": 7.86, "learning_rate": 8.44815137557575e-06, "loss": 0.0478, "step": 63330 }, { "epoch": 7.87, "learning_rate": 8.44790240258932e-06, "loss": 0.0804, "step": 63340 }, { "epoch": 7.87, "learning_rate": 8.447653429602888e-06, "loss": 0.0663, "step": 63350 }, { "epoch": 7.87, "learning_rate": 8.447404456616459e-06, "loss": 0.0471, "step": 63360 }, { "epoch": 7.87, "learning_rate": 8.447155483630027e-06, "loss": 0.0391, "step": 63370 }, { "epoch": 7.87, "learning_rate": 8.446906510643596e-06, "loss": 0.0576, "step": 63380 }, { "epoch": 7.87, "learning_rate": 8.446657537657164e-06, "loss": 0.064, "step": 63390 }, { "epoch": 7.87, "learning_rate": 8.446408564670734e-06, "loss": 0.0385, "step": 63400 }, { "epoch": 7.87, "learning_rate": 8.446159591684303e-06, "loss": 0.0517, "step": 63410 }, { "epoch": 7.88, "learning_rate": 8.445910618697873e-06, "loss": 0.0538, "step": 63420 }, { "epoch": 7.88, "learning_rate": 8.445661645711442e-06, "loss": 0.0625, "step": 63430 }, { "epoch": 7.88, "learning_rate": 8.44541267272501e-06, "loss": 0.068, "step": 63440 }, { "epoch": 7.88, "learning_rate": 8.445163699738579e-06, "loss": 0.0568, "step": 63450 }, { "epoch": 7.88, "learning_rate": 8.444914726752149e-06, "loss": 0.0573, "step": 63460 }, { "epoch": 7.88, "learning_rate": 8.444665753765717e-06, "loss": 0.046, "step": 63470 }, { "epoch": 7.88, "learning_rate": 8.444416780779286e-06, "loss": 0.0635, "step": 63480 }, { "epoch": 7.88, "learning_rate": 8.444167807792856e-06, "loss": 0.0654, "step": 63490 }, { "epoch": 7.89, "learning_rate": 8.443918834806425e-06, "loss": 0.0526, "step": 63500 }, { "epoch": 7.89, "learning_rate": 8.443669861819993e-06, "loss": 0.0536, "step": 63510 }, { "epoch": 7.89, "learning_rate": 8.443420888833562e-06, "loss": 0.0354, "step": 63520 }, { "epoch": 7.89, "learning_rate": 8.443171915847132e-06, "loss": 0.0519, "step": 63530 }, { "epoch": 7.89, "learning_rate": 8.4429229428607e-06, "loss": 0.0329, "step": 63540 }, { "epoch": 7.89, "learning_rate": 8.442673969874269e-06, "loss": 0.0557, "step": 63550 }, { "epoch": 7.89, "learning_rate": 8.442424996887837e-06, "loss": 0.058, "step": 63560 }, { "epoch": 7.89, "learning_rate": 8.442176023901408e-06, "loss": 0.0387, "step": 63570 }, { "epoch": 7.9, "learning_rate": 8.441927050914976e-06, "loss": 0.0655, "step": 63580 }, { "epoch": 7.9, "learning_rate": 8.441678077928546e-06, "loss": 0.0504, "step": 63590 }, { "epoch": 7.9, "learning_rate": 8.441429104942115e-06, "loss": 0.0258, "step": 63600 }, { "epoch": 7.9, "learning_rate": 8.441180131955683e-06, "loss": 0.0333, "step": 63610 }, { "epoch": 7.9, "learning_rate": 8.440931158969252e-06, "loss": 0.0219, "step": 63620 }, { "epoch": 7.9, "learning_rate": 8.440682185982822e-06, "loss": 0.0616, "step": 63630 }, { "epoch": 7.9, "learning_rate": 8.44043321299639e-06, "loss": 0.0733, "step": 63640 }, { "epoch": 7.9, "learning_rate": 8.440184240009959e-06, "loss": 0.0565, "step": 63650 }, { "epoch": 7.91, "learning_rate": 8.43993526702353e-06, "loss": 0.0387, "step": 63660 }, { "epoch": 7.91, "learning_rate": 8.439686294037098e-06, "loss": 0.0278, "step": 63670 }, { "epoch": 7.91, "learning_rate": 8.439437321050666e-06, "loss": 0.0581, "step": 63680 }, { "epoch": 7.91, "learning_rate": 8.439188348064235e-06, "loss": 0.0848, "step": 63690 }, { "epoch": 7.91, "learning_rate": 8.438939375077805e-06, "loss": 0.0445, "step": 63700 }, { "epoch": 7.91, "learning_rate": 8.438690402091374e-06, "loss": 0.0559, "step": 63710 }, { "epoch": 7.91, "learning_rate": 8.438441429104944e-06, "loss": 0.0374, "step": 63720 }, { "epoch": 7.91, "learning_rate": 8.43819245611851e-06, "loss": 0.0684, "step": 63730 }, { "epoch": 7.92, "learning_rate": 8.43794348313208e-06, "loss": 0.0826, "step": 63740 }, { "epoch": 7.92, "learning_rate": 8.43769451014565e-06, "loss": 0.0477, "step": 63750 }, { "epoch": 7.92, "learning_rate": 8.43744553715922e-06, "loss": 0.0366, "step": 63760 }, { "epoch": 7.92, "learning_rate": 8.437196564172788e-06, "loss": 0.0327, "step": 63770 }, { "epoch": 7.92, "learning_rate": 8.436947591186357e-06, "loss": 0.0476, "step": 63780 }, { "epoch": 7.92, "learning_rate": 8.436698618199925e-06, "loss": 0.0448, "step": 63790 }, { "epoch": 7.92, "learning_rate": 8.436449645213495e-06, "loss": 0.0514, "step": 63800 }, { "epoch": 7.92, "learning_rate": 8.436200672227064e-06, "loss": 0.0502, "step": 63810 }, { "epoch": 7.92, "learning_rate": 8.435951699240632e-06, "loss": 0.0487, "step": 63820 }, { "epoch": 7.93, "learning_rate": 8.435702726254203e-06, "loss": 0.0401, "step": 63830 }, { "epoch": 7.93, "learning_rate": 8.435453753267771e-06, "loss": 0.0558, "step": 63840 }, { "epoch": 7.93, "learning_rate": 8.43520478028134e-06, "loss": 0.0627, "step": 63850 }, { "epoch": 7.93, "learning_rate": 8.434955807294908e-06, "loss": 0.0594, "step": 63860 }, { "epoch": 7.93, "learning_rate": 8.434706834308478e-06, "loss": 0.0262, "step": 63870 }, { "epoch": 7.93, "learning_rate": 8.434457861322047e-06, "loss": 0.0575, "step": 63880 }, { "epoch": 7.93, "learning_rate": 8.434208888335617e-06, "loss": 0.063, "step": 63890 }, { "epoch": 7.93, "learning_rate": 8.433959915349186e-06, "loss": 0.0685, "step": 63900 }, { "epoch": 7.94, "learning_rate": 8.433710942362754e-06, "loss": 0.0717, "step": 63910 }, { "epoch": 7.94, "learning_rate": 8.433461969376323e-06, "loss": 0.0445, "step": 63920 }, { "epoch": 7.94, "learning_rate": 8.433212996389893e-06, "loss": 0.045, "step": 63930 }, { "epoch": 7.94, "learning_rate": 8.432964023403461e-06, "loss": 0.0261, "step": 63940 }, { "epoch": 7.94, "learning_rate": 8.432715050417032e-06, "loss": 0.037, "step": 63950 }, { "epoch": 7.94, "learning_rate": 8.4324660774306e-06, "loss": 0.0323, "step": 63960 }, { "epoch": 7.94, "learning_rate": 8.432217104444169e-06, "loss": 0.047, "step": 63970 }, { "epoch": 7.94, "learning_rate": 8.431968131457737e-06, "loss": 0.069, "step": 63980 }, { "epoch": 7.95, "learning_rate": 8.431719158471307e-06, "loss": 0.0701, "step": 63990 }, { "epoch": 7.95, "learning_rate": 8.431470185484876e-06, "loss": 0.0534, "step": 64000 }, { "epoch": 7.95, "learning_rate": 8.431221212498444e-06, "loss": 0.0496, "step": 64010 }, { "epoch": 7.95, "learning_rate": 8.430972239512015e-06, "loss": 0.054, "step": 64020 }, { "epoch": 7.95, "learning_rate": 8.430723266525583e-06, "loss": 0.0423, "step": 64030 }, { "epoch": 7.95, "learning_rate": 8.430474293539152e-06, "loss": 0.0505, "step": 64040 }, { "epoch": 7.95, "learning_rate": 8.43022532055272e-06, "loss": 0.0552, "step": 64050 }, { "epoch": 7.95, "learning_rate": 8.42997634756629e-06, "loss": 0.0467, "step": 64060 }, { "epoch": 7.96, "learning_rate": 8.429727374579859e-06, "loss": 0.054, "step": 64070 }, { "epoch": 7.96, "learning_rate": 8.429478401593429e-06, "loss": 0.0514, "step": 64080 }, { "epoch": 7.96, "learning_rate": 8.429229428606996e-06, "loss": 0.0392, "step": 64090 }, { "epoch": 7.96, "learning_rate": 8.428980455620566e-06, "loss": 0.0526, "step": 64100 }, { "epoch": 7.96, "learning_rate": 8.428731482634135e-06, "loss": 0.0435, "step": 64110 }, { "epoch": 7.96, "learning_rate": 8.428482509647705e-06, "loss": 0.0388, "step": 64120 }, { "epoch": 7.96, "learning_rate": 8.428233536661273e-06, "loss": 0.0395, "step": 64130 }, { "epoch": 7.96, "learning_rate": 8.427984563674842e-06, "loss": 0.0732, "step": 64140 }, { "epoch": 7.97, "learning_rate": 8.42773559068841e-06, "loss": 0.0603, "step": 64150 }, { "epoch": 7.97, "learning_rate": 8.42748661770198e-06, "loss": 0.0364, "step": 64160 }, { "epoch": 7.97, "learning_rate": 8.427237644715549e-06, "loss": 0.0451, "step": 64170 }, { "epoch": 7.97, "learning_rate": 8.426988671729118e-06, "loss": 0.0738, "step": 64180 }, { "epoch": 7.97, "learning_rate": 8.426739698742688e-06, "loss": 0.0601, "step": 64190 }, { "epoch": 7.97, "learning_rate": 8.426490725756256e-06, "loss": 0.0431, "step": 64200 }, { "epoch": 7.97, "learning_rate": 8.426241752769825e-06, "loss": 0.0605, "step": 64210 }, { "epoch": 7.97, "learning_rate": 8.425992779783393e-06, "loss": 0.0466, "step": 64220 }, { "epoch": 7.98, "learning_rate": 8.425743806796964e-06, "loss": 0.0456, "step": 64230 }, { "epoch": 7.98, "learning_rate": 8.425494833810532e-06, "loss": 0.0366, "step": 64240 }, { "epoch": 7.98, "learning_rate": 8.425245860824102e-06, "loss": 0.059, "step": 64250 }, { "epoch": 7.98, "learning_rate": 8.424996887837669e-06, "loss": 0.0406, "step": 64260 }, { "epoch": 7.98, "learning_rate": 8.42474791485124e-06, "loss": 0.0304, "step": 64270 }, { "epoch": 7.98, "learning_rate": 8.424498941864808e-06, "loss": 0.0439, "step": 64280 }, { "epoch": 7.98, "learning_rate": 8.424249968878378e-06, "loss": 0.0777, "step": 64290 }, { "epoch": 7.98, "learning_rate": 8.424000995891947e-06, "loss": 0.0413, "step": 64300 }, { "epoch": 7.99, "learning_rate": 8.423752022905515e-06, "loss": 0.0448, "step": 64310 }, { "epoch": 7.99, "learning_rate": 8.423503049919084e-06, "loss": 0.0443, "step": 64320 }, { "epoch": 7.99, "learning_rate": 8.423254076932654e-06, "loss": 0.0884, "step": 64330 }, { "epoch": 7.99, "learning_rate": 8.423005103946222e-06, "loss": 0.0756, "step": 64340 }, { "epoch": 7.99, "learning_rate": 8.42275613095979e-06, "loss": 0.0486, "step": 64350 }, { "epoch": 7.99, "learning_rate": 8.422507157973361e-06, "loss": 0.085, "step": 64360 }, { "epoch": 7.99, "learning_rate": 8.42225818498693e-06, "loss": 0.0276, "step": 64370 }, { "epoch": 7.99, "learning_rate": 8.422009212000498e-06, "loss": 0.0763, "step": 64380 }, { "epoch": 8.0, "learning_rate": 8.421760239014067e-06, "loss": 0.0551, "step": 64390 }, { "epoch": 8.0, "learning_rate": 8.421511266027637e-06, "loss": 0.0607, "step": 64400 }, { "epoch": 8.0, "learning_rate": 8.421262293041205e-06, "loss": 0.0393, "step": 64410 }, { "epoch": 8.0, "learning_rate": 8.421013320054775e-06, "loss": 0.0423, "step": 64420 }, { "epoch": 8.0, "learning_rate": 8.420764347068344e-06, "loss": 0.0662, "step": 64430 }, { "epoch": 8.0, "learning_rate": 8.420515374081912e-06, "loss": 0.0597, "step": 64440 }, { "epoch": 8.0, "learning_rate": 8.420266401095481e-06, "loss": 0.0503, "step": 64450 }, { "epoch": 8.0, "learning_rate": 8.420017428109051e-06, "loss": 0.0528, "step": 64460 }, { "epoch": 8.01, "learning_rate": 8.41976845512262e-06, "loss": 0.0356, "step": 64470 }, { "epoch": 8.01, "learning_rate": 8.41951948213619e-06, "loss": 0.057, "step": 64480 }, { "epoch": 8.01, "learning_rate": 8.419270509149758e-06, "loss": 0.0501, "step": 64490 }, { "epoch": 8.01, "learning_rate": 8.419021536163327e-06, "loss": 0.0424, "step": 64500 }, { "epoch": 8.01, "learning_rate": 8.418772563176895e-06, "loss": 0.0449, "step": 64510 }, { "epoch": 8.01, "learning_rate": 8.418523590190466e-06, "loss": 0.0694, "step": 64520 }, { "epoch": 8.01, "learning_rate": 8.418274617204034e-06, "loss": 0.0691, "step": 64530 }, { "epoch": 8.01, "learning_rate": 8.418025644217603e-06, "loss": 0.0551, "step": 64540 }, { "epoch": 8.02, "learning_rate": 8.417776671231173e-06, "loss": 0.0418, "step": 64550 }, { "epoch": 8.02, "learning_rate": 8.417527698244741e-06, "loss": 0.0457, "step": 64560 }, { "epoch": 8.02, "learning_rate": 8.41727872525831e-06, "loss": 0.0479, "step": 64570 }, { "epoch": 8.02, "learning_rate": 8.417029752271878e-06, "loss": 0.0414, "step": 64580 }, { "epoch": 8.02, "learning_rate": 8.416780779285449e-06, "loss": 0.0548, "step": 64590 }, { "epoch": 8.02, "learning_rate": 8.416531806299017e-06, "loss": 0.0494, "step": 64600 }, { "epoch": 8.02, "learning_rate": 8.416282833312587e-06, "loss": 0.0779, "step": 64610 }, { "epoch": 8.02, "learning_rate": 8.416033860326154e-06, "loss": 0.0496, "step": 64620 }, { "epoch": 8.03, "learning_rate": 8.415784887339724e-06, "loss": 0.0577, "step": 64630 }, { "epoch": 8.03, "learning_rate": 8.415535914353293e-06, "loss": 0.0456, "step": 64640 }, { "epoch": 8.03, "learning_rate": 8.415286941366863e-06, "loss": 0.0445, "step": 64650 }, { "epoch": 8.03, "learning_rate": 8.415037968380432e-06, "loss": 0.0458, "step": 64660 }, { "epoch": 8.03, "learning_rate": 8.414788995394e-06, "loss": 0.0298, "step": 64670 }, { "epoch": 8.03, "learning_rate": 8.414540022407569e-06, "loss": 0.0814, "step": 64680 }, { "epoch": 8.03, "learning_rate": 8.414291049421139e-06, "loss": 0.0562, "step": 64690 }, { "epoch": 8.03, "learning_rate": 8.414042076434707e-06, "loss": 0.0582, "step": 64700 }, { "epoch": 8.04, "learning_rate": 8.413793103448276e-06, "loss": 0.0397, "step": 64710 }, { "epoch": 8.04, "learning_rate": 8.413544130461846e-06, "loss": 0.0309, "step": 64720 }, { "epoch": 8.04, "learning_rate": 8.413295157475415e-06, "loss": 0.0686, "step": 64730 }, { "epoch": 8.04, "learning_rate": 8.413046184488983e-06, "loss": 0.0555, "step": 64740 }, { "epoch": 8.04, "learning_rate": 8.412797211502552e-06, "loss": 0.0413, "step": 64750 }, { "epoch": 8.04, "learning_rate": 8.412548238516122e-06, "loss": 0.0489, "step": 64760 }, { "epoch": 8.04, "learning_rate": 8.41229926552969e-06, "loss": 0.0346, "step": 64770 }, { "epoch": 8.04, "learning_rate": 8.41205029254326e-06, "loss": 0.0489, "step": 64780 }, { "epoch": 8.05, "learning_rate": 8.41180131955683e-06, "loss": 0.0644, "step": 64790 }, { "epoch": 8.05, "learning_rate": 8.411552346570398e-06, "loss": 0.0431, "step": 64800 }, { "epoch": 8.05, "learning_rate": 8.411303373583966e-06, "loss": 0.037, "step": 64810 }, { "epoch": 8.05, "learning_rate": 8.411054400597536e-06, "loss": 0.0362, "step": 64820 }, { "epoch": 8.05, "learning_rate": 8.410805427611105e-06, "loss": 0.0465, "step": 64830 }, { "epoch": 8.05, "learning_rate": 8.410556454624673e-06, "loss": 0.0574, "step": 64840 }, { "epoch": 8.05, "learning_rate": 8.410307481638242e-06, "loss": 0.0571, "step": 64850 }, { "epoch": 8.05, "learning_rate": 8.410058508651812e-06, "loss": 0.0474, "step": 64860 }, { "epoch": 8.06, "learning_rate": 8.40980953566538e-06, "loss": 0.0277, "step": 64870 }, { "epoch": 8.06, "learning_rate": 8.40956056267895e-06, "loss": 0.0436, "step": 64880 }, { "epoch": 8.06, "learning_rate": 8.40931158969252e-06, "loss": 0.0476, "step": 64890 }, { "epoch": 8.06, "learning_rate": 8.409062616706088e-06, "loss": 0.0874, "step": 64900 }, { "epoch": 8.06, "learning_rate": 8.408813643719656e-06, "loss": 0.0611, "step": 64910 }, { "epoch": 8.06, "learning_rate": 8.408564670733225e-06, "loss": 0.0437, "step": 64920 }, { "epoch": 8.06, "learning_rate": 8.408315697746795e-06, "loss": 0.04, "step": 64930 }, { "epoch": 8.06, "learning_rate": 8.408066724760364e-06, "loss": 0.0632, "step": 64940 }, { "epoch": 8.07, "learning_rate": 8.407817751773934e-06, "loss": 0.0459, "step": 64950 }, { "epoch": 8.07, "learning_rate": 8.407568778787502e-06, "loss": 0.0478, "step": 64960 }, { "epoch": 8.07, "learning_rate": 8.407319805801071e-06, "loss": 0.0414, "step": 64970 }, { "epoch": 8.07, "learning_rate": 8.40707083281464e-06, "loss": 0.0432, "step": 64980 }, { "epoch": 8.07, "learning_rate": 8.40682185982821e-06, "loss": 0.0642, "step": 64990 }, { "epoch": 8.07, "learning_rate": 8.406572886841778e-06, "loss": 0.0349, "step": 65000 }, { "epoch": 8.07, "eval_bleu": 89.343, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7558, "eval_has_error_f1": 0.6625, "eval_loss": 0.05383080616593361, "eval_runtime": 1320.382, "eval_samples_per_second": 3.028, "eval_steps_per_second": 0.757, "step": 65000 }, { "epoch": 8.07, "learning_rate": 8.406323913855348e-06, "loss": 0.0408, "step": 65010 }, { "epoch": 8.07, "learning_rate": 8.406074940868917e-06, "loss": 0.0454, "step": 65020 }, { "epoch": 8.08, "learning_rate": 8.405825967882485e-06, "loss": 0.07, "step": 65030 }, { "epoch": 8.08, "learning_rate": 8.405576994896054e-06, "loss": 0.0641, "step": 65040 }, { "epoch": 8.08, "learning_rate": 8.405328021909624e-06, "loss": 0.072, "step": 65050 }, { "epoch": 8.08, "learning_rate": 8.405079048923193e-06, "loss": 0.0429, "step": 65060 }, { "epoch": 8.08, "learning_rate": 8.404830075936761e-06, "loss": 0.0338, "step": 65070 }, { "epoch": 8.08, "learning_rate": 8.404581102950331e-06, "loss": 0.0684, "step": 65080 }, { "epoch": 8.08, "learning_rate": 8.4043321299639e-06, "loss": 0.0519, "step": 65090 }, { "epoch": 8.08, "learning_rate": 8.404083156977468e-06, "loss": 0.0349, "step": 65100 }, { "epoch": 8.09, "learning_rate": 8.403834183991037e-06, "loss": 0.0547, "step": 65110 }, { "epoch": 8.09, "learning_rate": 8.403585211004607e-06, "loss": 0.04, "step": 65120 }, { "epoch": 8.09, "learning_rate": 8.403336238018176e-06, "loss": 0.0541, "step": 65130 }, { "epoch": 8.09, "learning_rate": 8.403087265031746e-06, "loss": 0.0843, "step": 65140 }, { "epoch": 8.09, "learning_rate": 8.402838292045313e-06, "loss": 0.075, "step": 65150 }, { "epoch": 8.09, "learning_rate": 8.402589319058883e-06, "loss": 0.0646, "step": 65160 }, { "epoch": 8.09, "learning_rate": 8.402340346072451e-06, "loss": 0.0336, "step": 65170 }, { "epoch": 8.09, "learning_rate": 8.402091373086022e-06, "loss": 0.0341, "step": 65180 }, { "epoch": 8.1, "learning_rate": 8.40184240009959e-06, "loss": 0.0467, "step": 65190 }, { "epoch": 8.1, "learning_rate": 8.401593427113159e-06, "loss": 0.0481, "step": 65200 }, { "epoch": 8.1, "learning_rate": 8.401344454126727e-06, "loss": 0.0424, "step": 65210 }, { "epoch": 8.1, "learning_rate": 8.401095481140297e-06, "loss": 0.0559, "step": 65220 }, { "epoch": 8.1, "learning_rate": 8.400846508153866e-06, "loss": 0.0364, "step": 65230 }, { "epoch": 8.1, "learning_rate": 8.400597535167434e-06, "loss": 0.073, "step": 65240 }, { "epoch": 8.1, "learning_rate": 8.400348562181005e-06, "loss": 0.0521, "step": 65250 }, { "epoch": 8.1, "learning_rate": 8.400099589194573e-06, "loss": 0.0386, "step": 65260 }, { "epoch": 8.11, "learning_rate": 8.399850616208142e-06, "loss": 0.0687, "step": 65270 }, { "epoch": 8.11, "learning_rate": 8.39960164322171e-06, "loss": 0.0568, "step": 65280 }, { "epoch": 8.11, "learning_rate": 8.39935267023528e-06, "loss": 0.0648, "step": 65290 }, { "epoch": 8.11, "learning_rate": 8.399103697248849e-06, "loss": 0.0581, "step": 65300 }, { "epoch": 8.11, "learning_rate": 8.398854724262419e-06, "loss": 0.0321, "step": 65310 }, { "epoch": 8.11, "learning_rate": 8.398605751275988e-06, "loss": 0.0323, "step": 65320 }, { "epoch": 8.11, "learning_rate": 8.398356778289556e-06, "loss": 0.0707, "step": 65330 }, { "epoch": 8.11, "learning_rate": 8.398107805303125e-06, "loss": 0.0454, "step": 65340 }, { "epoch": 8.11, "learning_rate": 8.397858832316695e-06, "loss": 0.0535, "step": 65350 }, { "epoch": 8.12, "learning_rate": 8.397609859330263e-06, "loss": 0.0483, "step": 65360 }, { "epoch": 8.12, "learning_rate": 8.397360886343832e-06, "loss": 0.0499, "step": 65370 }, { "epoch": 8.12, "learning_rate": 8.397111913357402e-06, "loss": 0.0779, "step": 65380 }, { "epoch": 8.12, "learning_rate": 8.39686294037097e-06, "loss": 0.0461, "step": 65390 }, { "epoch": 8.12, "learning_rate": 8.396613967384539e-06, "loss": 0.0456, "step": 65400 }, { "epoch": 8.12, "learning_rate": 8.396364994398108e-06, "loss": 0.0417, "step": 65410 }, { "epoch": 8.12, "learning_rate": 8.396116021411678e-06, "loss": 0.0573, "step": 65420 }, { "epoch": 8.12, "learning_rate": 8.395867048425246e-06, "loss": 0.0721, "step": 65430 }, { "epoch": 8.13, "learning_rate": 8.395618075438817e-06, "loss": 0.0711, "step": 65440 }, { "epoch": 8.13, "learning_rate": 8.395369102452383e-06, "loss": 0.0392, "step": 65450 }, { "epoch": 8.13, "learning_rate": 8.395120129465954e-06, "loss": 0.0359, "step": 65460 }, { "epoch": 8.13, "learning_rate": 8.394871156479522e-06, "loss": 0.0401, "step": 65470 }, { "epoch": 8.13, "learning_rate": 8.394622183493092e-06, "loss": 0.05, "step": 65480 }, { "epoch": 8.13, "learning_rate": 8.394373210506661e-06, "loss": 0.0628, "step": 65490 }, { "epoch": 8.13, "learning_rate": 8.39412423752023e-06, "loss": 0.0673, "step": 65500 }, { "epoch": 8.13, "learning_rate": 8.393875264533798e-06, "loss": 0.0446, "step": 65510 }, { "epoch": 8.14, "learning_rate": 8.393626291547368e-06, "loss": 0.0365, "step": 65520 }, { "epoch": 8.14, "learning_rate": 8.393377318560937e-06, "loss": 0.0572, "step": 65530 }, { "epoch": 8.14, "learning_rate": 8.393128345574507e-06, "loss": 0.0431, "step": 65540 }, { "epoch": 8.14, "learning_rate": 8.392879372588075e-06, "loss": 0.0322, "step": 65550 }, { "epoch": 8.14, "learning_rate": 8.392630399601644e-06, "loss": 0.0374, "step": 65560 }, { "epoch": 8.14, "learning_rate": 8.392381426615212e-06, "loss": 0.0618, "step": 65570 }, { "epoch": 8.14, "learning_rate": 8.392132453628783e-06, "loss": 0.037, "step": 65580 }, { "epoch": 8.14, "learning_rate": 8.391883480642351e-06, "loss": 0.054, "step": 65590 }, { "epoch": 8.15, "learning_rate": 8.39163450765592e-06, "loss": 0.0522, "step": 65600 }, { "epoch": 8.15, "learning_rate": 8.39138553466949e-06, "loss": 0.04, "step": 65610 }, { "epoch": 8.15, "learning_rate": 8.391136561683058e-06, "loss": 0.0703, "step": 65620 }, { "epoch": 8.15, "learning_rate": 8.390887588696627e-06, "loss": 0.0653, "step": 65630 }, { "epoch": 8.15, "learning_rate": 8.390638615710195e-06, "loss": 0.0407, "step": 65640 }, { "epoch": 8.15, "learning_rate": 8.390389642723766e-06, "loss": 0.0271, "step": 65650 }, { "epoch": 8.15, "learning_rate": 8.390140669737334e-06, "loss": 0.0571, "step": 65660 }, { "epoch": 8.15, "learning_rate": 8.389891696750904e-06, "loss": 0.0335, "step": 65670 }, { "epoch": 8.16, "learning_rate": 8.389642723764471e-06, "loss": 0.045, "step": 65680 }, { "epoch": 8.16, "learning_rate": 8.389393750778041e-06, "loss": 0.0447, "step": 65690 }, { "epoch": 8.16, "learning_rate": 8.38914477779161e-06, "loss": 0.0529, "step": 65700 }, { "epoch": 8.16, "learning_rate": 8.38889580480518e-06, "loss": 0.0496, "step": 65710 }, { "epoch": 8.16, "learning_rate": 8.388646831818749e-06, "loss": 0.045, "step": 65720 }, { "epoch": 8.16, "learning_rate": 8.388397858832317e-06, "loss": 0.0453, "step": 65730 }, { "epoch": 8.16, "learning_rate": 8.388148885845886e-06, "loss": 0.0606, "step": 65740 }, { "epoch": 8.16, "learning_rate": 8.387899912859456e-06, "loss": 0.0749, "step": 65750 }, { "epoch": 8.17, "learning_rate": 8.387650939873024e-06, "loss": 0.0354, "step": 65760 }, { "epoch": 8.17, "learning_rate": 8.387401966886593e-06, "loss": 0.0601, "step": 65770 }, { "epoch": 8.17, "learning_rate": 8.387152993900163e-06, "loss": 0.0579, "step": 65780 }, { "epoch": 8.17, "learning_rate": 8.386904020913732e-06, "loss": 0.0442, "step": 65790 }, { "epoch": 8.17, "learning_rate": 8.3866550479273e-06, "loss": 0.0787, "step": 65800 }, { "epoch": 8.17, "learning_rate": 8.386406074940869e-06, "loss": 0.0505, "step": 65810 }, { "epoch": 8.17, "learning_rate": 8.386157101954439e-06, "loss": 0.0425, "step": 65820 }, { "epoch": 8.17, "learning_rate": 8.385908128968007e-06, "loss": 0.0702, "step": 65830 }, { "epoch": 8.18, "learning_rate": 8.385659155981578e-06, "loss": 0.0532, "step": 65840 }, { "epoch": 8.18, "learning_rate": 8.385410182995146e-06, "loss": 0.039, "step": 65850 }, { "epoch": 8.18, "learning_rate": 8.385161210008715e-06, "loss": 0.0443, "step": 65860 }, { "epoch": 8.18, "learning_rate": 8.384912237022283e-06, "loss": 0.0403, "step": 65870 }, { "epoch": 8.18, "learning_rate": 8.384663264035853e-06, "loss": 0.0602, "step": 65880 }, { "epoch": 8.18, "learning_rate": 8.384414291049422e-06, "loss": 0.0457, "step": 65890 }, { "epoch": 8.18, "learning_rate": 8.38416531806299e-06, "loss": 0.0594, "step": 65900 }, { "epoch": 8.18, "learning_rate": 8.38391634507656e-06, "loss": 0.0353, "step": 65910 }, { "epoch": 8.19, "learning_rate": 8.383667372090129e-06, "loss": 0.0261, "step": 65920 }, { "epoch": 8.19, "learning_rate": 8.383418399103698e-06, "loss": 0.0466, "step": 65930 }, { "epoch": 8.19, "learning_rate": 8.383169426117266e-06, "loss": 0.0401, "step": 65940 }, { "epoch": 8.19, "learning_rate": 8.382920453130836e-06, "loss": 0.0343, "step": 65950 }, { "epoch": 8.19, "learning_rate": 8.382671480144405e-06, "loss": 0.0296, "step": 65960 }, { "epoch": 8.19, "learning_rate": 8.382422507157975e-06, "loss": 0.0709, "step": 65970 }, { "epoch": 8.19, "learning_rate": 8.382173534171542e-06, "loss": 0.0441, "step": 65980 }, { "epoch": 8.19, "learning_rate": 8.381924561185112e-06, "loss": 0.0391, "step": 65990 }, { "epoch": 8.2, "learning_rate": 8.38167558819868e-06, "loss": 0.0499, "step": 66000 }, { "epoch": 8.2, "learning_rate": 8.38142661521225e-06, "loss": 0.0544, "step": 66010 }, { "epoch": 8.2, "learning_rate": 8.38117764222582e-06, "loss": 0.0471, "step": 66020 }, { "epoch": 8.2, "learning_rate": 8.38092866923939e-06, "loss": 0.0645, "step": 66030 }, { "epoch": 8.2, "learning_rate": 8.380679696252956e-06, "loss": 0.0487, "step": 66040 }, { "epoch": 8.2, "learning_rate": 8.380430723266527e-06, "loss": 0.0497, "step": 66050 }, { "epoch": 8.2, "learning_rate": 8.380181750280095e-06, "loss": 0.0342, "step": 66060 }, { "epoch": 8.2, "learning_rate": 8.379932777293665e-06, "loss": 0.0487, "step": 66070 }, { "epoch": 8.21, "learning_rate": 8.379683804307234e-06, "loss": 0.0405, "step": 66080 }, { "epoch": 8.21, "learning_rate": 8.379434831320802e-06, "loss": 0.0539, "step": 66090 }, { "epoch": 8.21, "learning_rate": 8.37918585833437e-06, "loss": 0.074, "step": 66100 }, { "epoch": 8.21, "learning_rate": 8.378936885347941e-06, "loss": 0.0297, "step": 66110 }, { "epoch": 8.21, "learning_rate": 8.37868791236151e-06, "loss": 0.0436, "step": 66120 }, { "epoch": 8.21, "learning_rate": 8.378438939375078e-06, "loss": 0.0646, "step": 66130 }, { "epoch": 8.21, "learning_rate": 8.378189966388648e-06, "loss": 0.0438, "step": 66140 }, { "epoch": 8.21, "learning_rate": 8.377940993402217e-06, "loss": 0.0322, "step": 66150 }, { "epoch": 8.22, "learning_rate": 8.377692020415785e-06, "loss": 0.0601, "step": 66160 }, { "epoch": 8.22, "learning_rate": 8.377443047429354e-06, "loss": 0.0376, "step": 66170 }, { "epoch": 8.22, "learning_rate": 8.377194074442924e-06, "loss": 0.079, "step": 66180 }, { "epoch": 8.22, "learning_rate": 8.376945101456493e-06, "loss": 0.0572, "step": 66190 }, { "epoch": 8.22, "learning_rate": 8.376696128470063e-06, "loss": 0.0491, "step": 66200 }, { "epoch": 8.22, "learning_rate": 8.37644715548363e-06, "loss": 0.0409, "step": 66210 }, { "epoch": 8.22, "learning_rate": 8.3761981824972e-06, "loss": 0.0426, "step": 66220 }, { "epoch": 8.22, "learning_rate": 8.375949209510768e-06, "loss": 0.0523, "step": 66230 }, { "epoch": 8.23, "learning_rate": 8.375700236524339e-06, "loss": 0.0836, "step": 66240 }, { "epoch": 8.23, "learning_rate": 8.375451263537907e-06, "loss": 0.0579, "step": 66250 }, { "epoch": 8.23, "learning_rate": 8.375202290551476e-06, "loss": 0.0406, "step": 66260 }, { "epoch": 8.23, "learning_rate": 8.374953317565044e-06, "loss": 0.0498, "step": 66270 }, { "epoch": 8.23, "learning_rate": 8.374704344578614e-06, "loss": 0.0545, "step": 66280 }, { "epoch": 8.23, "learning_rate": 8.374455371592183e-06, "loss": 0.0309, "step": 66290 }, { "epoch": 8.23, "learning_rate": 8.374206398605751e-06, "loss": 0.0543, "step": 66300 }, { "epoch": 8.23, "learning_rate": 8.373957425619322e-06, "loss": 0.0325, "step": 66310 }, { "epoch": 8.24, "learning_rate": 8.37370845263289e-06, "loss": 0.0446, "step": 66320 }, { "epoch": 8.24, "learning_rate": 8.373459479646459e-06, "loss": 0.047, "step": 66330 }, { "epoch": 8.24, "learning_rate": 8.373210506660027e-06, "loss": 0.0915, "step": 66340 }, { "epoch": 8.24, "learning_rate": 8.372961533673597e-06, "loss": 0.0529, "step": 66350 }, { "epoch": 8.24, "learning_rate": 8.372712560687166e-06, "loss": 0.0356, "step": 66360 }, { "epoch": 8.24, "learning_rate": 8.372463587700736e-06, "loss": 0.0319, "step": 66370 }, { "epoch": 8.24, "learning_rate": 8.372214614714305e-06, "loss": 0.065, "step": 66380 }, { "epoch": 8.24, "learning_rate": 8.371965641727873e-06, "loss": 0.0372, "step": 66390 }, { "epoch": 8.25, "learning_rate": 8.371716668741442e-06, "loss": 0.0472, "step": 66400 }, { "epoch": 8.25, "learning_rate": 8.371467695755012e-06, "loss": 0.0291, "step": 66410 }, { "epoch": 8.25, "learning_rate": 8.37121872276858e-06, "loss": 0.0445, "step": 66420 }, { "epoch": 8.25, "learning_rate": 8.370969749782149e-06, "loss": 0.0726, "step": 66430 }, { "epoch": 8.25, "learning_rate": 8.370720776795719e-06, "loss": 0.0435, "step": 66440 }, { "epoch": 8.25, "learning_rate": 8.370471803809288e-06, "loss": 0.0515, "step": 66450 }, { "epoch": 8.25, "learning_rate": 8.370222830822856e-06, "loss": 0.0414, "step": 66460 }, { "epoch": 8.25, "learning_rate": 8.369973857836425e-06, "loss": 0.0303, "step": 66470 }, { "epoch": 8.26, "learning_rate": 8.369724884849995e-06, "loss": 0.0535, "step": 66480 }, { "epoch": 8.26, "learning_rate": 8.369475911863563e-06, "loss": 0.0614, "step": 66490 }, { "epoch": 8.26, "learning_rate": 8.369226938877133e-06, "loss": 0.0458, "step": 66500 }, { "epoch": 8.26, "learning_rate": 8.3689779658907e-06, "loss": 0.0516, "step": 66510 }, { "epoch": 8.26, "learning_rate": 8.36872899290427e-06, "loss": 0.0327, "step": 66520 }, { "epoch": 8.26, "learning_rate": 8.368480019917839e-06, "loss": 0.0358, "step": 66530 }, { "epoch": 8.26, "learning_rate": 8.36823104693141e-06, "loss": 0.0596, "step": 66540 }, { "epoch": 8.26, "learning_rate": 8.367982073944978e-06, "loss": 0.0509, "step": 66550 }, { "epoch": 8.27, "learning_rate": 8.367733100958548e-06, "loss": 0.0573, "step": 66560 }, { "epoch": 8.27, "learning_rate": 8.367484127972115e-06, "loss": 0.0423, "step": 66570 }, { "epoch": 8.27, "learning_rate": 8.367235154985685e-06, "loss": 0.0752, "step": 66580 }, { "epoch": 8.27, "learning_rate": 8.366986181999254e-06, "loss": 0.0703, "step": 66590 }, { "epoch": 8.27, "learning_rate": 8.366737209012824e-06, "loss": 0.0483, "step": 66600 }, { "epoch": 8.27, "learning_rate": 8.366488236026392e-06, "loss": 0.0532, "step": 66610 }, { "epoch": 8.27, "learning_rate": 8.36623926303996e-06, "loss": 0.0415, "step": 66620 }, { "epoch": 8.27, "learning_rate": 8.36599029005353e-06, "loss": 0.0717, "step": 66630 }, { "epoch": 8.28, "learning_rate": 8.3657413170671e-06, "loss": 0.0808, "step": 66640 }, { "epoch": 8.28, "learning_rate": 8.365492344080668e-06, "loss": 0.0517, "step": 66650 }, { "epoch": 8.28, "learning_rate": 8.365243371094237e-06, "loss": 0.0536, "step": 66660 }, { "epoch": 8.28, "learning_rate": 8.364994398107807e-06, "loss": 0.0469, "step": 66670 }, { "epoch": 8.28, "learning_rate": 8.364745425121375e-06, "loss": 0.0271, "step": 66680 }, { "epoch": 8.28, "learning_rate": 8.364496452134944e-06, "loss": 0.0362, "step": 66690 }, { "epoch": 8.28, "learning_rate": 8.364247479148512e-06, "loss": 0.0421, "step": 66700 }, { "epoch": 8.28, "learning_rate": 8.363998506162082e-06, "loss": 0.0581, "step": 66710 }, { "epoch": 8.29, "learning_rate": 8.363749533175651e-06, "loss": 0.0415, "step": 66720 }, { "epoch": 8.29, "learning_rate": 8.363500560189221e-06, "loss": 0.0529, "step": 66730 }, { "epoch": 8.29, "learning_rate": 8.36325158720279e-06, "loss": 0.069, "step": 66740 }, { "epoch": 8.29, "learning_rate": 8.363002614216358e-06, "loss": 0.0488, "step": 66750 }, { "epoch": 8.29, "learning_rate": 8.362753641229927e-06, "loss": 0.0465, "step": 66760 }, { "epoch": 8.29, "learning_rate": 8.362504668243497e-06, "loss": 0.0249, "step": 66770 }, { "epoch": 8.29, "learning_rate": 8.362255695257065e-06, "loss": 0.0735, "step": 66780 }, { "epoch": 8.29, "learning_rate": 8.362006722270634e-06, "loss": 0.0553, "step": 66790 }, { "epoch": 8.3, "learning_rate": 8.361757749284203e-06, "loss": 0.0442, "step": 66800 }, { "epoch": 8.3, "learning_rate": 8.361508776297773e-06, "loss": 0.0675, "step": 66810 }, { "epoch": 8.3, "learning_rate": 8.361259803311341e-06, "loss": 0.0297, "step": 66820 }, { "epoch": 8.3, "learning_rate": 8.36101083032491e-06, "loss": 0.0566, "step": 66830 }, { "epoch": 8.3, "learning_rate": 8.36076185733848e-06, "loss": 0.0835, "step": 66840 }, { "epoch": 8.3, "learning_rate": 8.360512884352048e-06, "loss": 0.0404, "step": 66850 }, { "epoch": 8.3, "learning_rate": 8.360263911365617e-06, "loss": 0.0424, "step": 66860 }, { "epoch": 8.3, "learning_rate": 8.360014938379186e-06, "loss": 0.0391, "step": 66870 }, { "epoch": 8.3, "learning_rate": 8.359765965392756e-06, "loss": 0.0454, "step": 66880 }, { "epoch": 8.31, "learning_rate": 8.359516992406324e-06, "loss": 0.0413, "step": 66890 }, { "epoch": 8.31, "learning_rate": 8.359268019419894e-06, "loss": 0.0336, "step": 66900 }, { "epoch": 8.31, "learning_rate": 8.359019046433463e-06, "loss": 0.0343, "step": 66910 }, { "epoch": 8.31, "learning_rate": 8.358770073447031e-06, "loss": 0.0587, "step": 66920 }, { "epoch": 8.31, "learning_rate": 8.3585211004606e-06, "loss": 0.0447, "step": 66930 }, { "epoch": 8.31, "learning_rate": 8.35827212747417e-06, "loss": 0.0473, "step": 66940 }, { "epoch": 8.31, "learning_rate": 8.358023154487739e-06, "loss": 0.0592, "step": 66950 }, { "epoch": 8.31, "learning_rate": 8.357774181501307e-06, "loss": 0.0398, "step": 66960 }, { "epoch": 8.32, "learning_rate": 8.357525208514877e-06, "loss": 0.0409, "step": 66970 }, { "epoch": 8.32, "learning_rate": 8.357276235528446e-06, "loss": 0.0595, "step": 66980 }, { "epoch": 8.32, "learning_rate": 8.357027262542014e-06, "loss": 0.0647, "step": 66990 }, { "epoch": 8.32, "learning_rate": 8.356778289555583e-06, "loss": 0.0407, "step": 67000 }, { "epoch": 8.32, "learning_rate": 8.356529316569153e-06, "loss": 0.0481, "step": 67010 }, { "epoch": 8.32, "learning_rate": 8.356280343582722e-06, "loss": 0.0653, "step": 67020 }, { "epoch": 8.32, "learning_rate": 8.356031370596292e-06, "loss": 0.0401, "step": 67030 }, { "epoch": 8.32, "learning_rate": 8.355782397609859e-06, "loss": 0.0406, "step": 67040 }, { "epoch": 8.33, "learning_rate": 8.355533424623429e-06, "loss": 0.0693, "step": 67050 }, { "epoch": 8.33, "learning_rate": 8.355284451636997e-06, "loss": 0.0278, "step": 67060 }, { "epoch": 8.33, "learning_rate": 8.355035478650568e-06, "loss": 0.0592, "step": 67070 }, { "epoch": 8.33, "learning_rate": 8.354786505664136e-06, "loss": 0.0365, "step": 67080 }, { "epoch": 8.33, "learning_rate": 8.354537532677706e-06, "loss": 0.0397, "step": 67090 }, { "epoch": 8.33, "learning_rate": 8.354288559691273e-06, "loss": 0.0609, "step": 67100 }, { "epoch": 8.33, "learning_rate": 8.354039586704843e-06, "loss": 0.0523, "step": 67110 }, { "epoch": 8.33, "learning_rate": 8.353790613718412e-06, "loss": 0.0448, "step": 67120 }, { "epoch": 8.34, "learning_rate": 8.353541640731982e-06, "loss": 0.0461, "step": 67130 }, { "epoch": 8.34, "learning_rate": 8.35329266774555e-06, "loss": 0.0362, "step": 67140 }, { "epoch": 8.34, "learning_rate": 8.35304369475912e-06, "loss": 0.0604, "step": 67150 }, { "epoch": 8.34, "learning_rate": 8.352794721772688e-06, "loss": 0.059, "step": 67160 }, { "epoch": 8.34, "learning_rate": 8.352545748786258e-06, "loss": 0.0619, "step": 67170 }, { "epoch": 8.34, "learning_rate": 8.352296775799826e-06, "loss": 0.0384, "step": 67180 }, { "epoch": 8.34, "learning_rate": 8.352047802813395e-06, "loss": 0.0553, "step": 67190 }, { "epoch": 8.34, "learning_rate": 8.351798829826965e-06, "loss": 0.0599, "step": 67200 }, { "epoch": 8.35, "learning_rate": 8.351549856840534e-06, "loss": 0.0607, "step": 67210 }, { "epoch": 8.35, "learning_rate": 8.351300883854102e-06, "loss": 0.0306, "step": 67220 }, { "epoch": 8.35, "learning_rate": 8.35105191086767e-06, "loss": 0.0598, "step": 67230 }, { "epoch": 8.35, "learning_rate": 8.350802937881241e-06, "loss": 0.0564, "step": 67240 }, { "epoch": 8.35, "learning_rate": 8.35055396489481e-06, "loss": 0.0565, "step": 67250 }, { "epoch": 8.35, "learning_rate": 8.35030499190838e-06, "loss": 0.0402, "step": 67260 }, { "epoch": 8.35, "learning_rate": 8.350056018921948e-06, "loss": 0.0225, "step": 67270 }, { "epoch": 8.35, "learning_rate": 8.349807045935517e-06, "loss": 0.0517, "step": 67280 }, { "epoch": 8.36, "learning_rate": 8.349558072949085e-06, "loss": 0.0559, "step": 67290 }, { "epoch": 8.36, "learning_rate": 8.349309099962655e-06, "loss": 0.0387, "step": 67300 }, { "epoch": 8.36, "learning_rate": 8.349060126976224e-06, "loss": 0.0651, "step": 67310 }, { "epoch": 8.36, "learning_rate": 8.348811153989792e-06, "loss": 0.0278, "step": 67320 }, { "epoch": 8.36, "learning_rate": 8.348562181003363e-06, "loss": 0.0361, "step": 67330 }, { "epoch": 8.36, "learning_rate": 8.348313208016931e-06, "loss": 0.0426, "step": 67340 }, { "epoch": 8.36, "learning_rate": 8.3480642350305e-06, "loss": 0.055, "step": 67350 }, { "epoch": 8.36, "learning_rate": 8.347815262044068e-06, "loss": 0.0496, "step": 67360 }, { "epoch": 8.37, "learning_rate": 8.347566289057638e-06, "loss": 0.0377, "step": 67370 }, { "epoch": 8.37, "learning_rate": 8.347317316071207e-06, "loss": 0.0632, "step": 67380 }, { "epoch": 8.37, "learning_rate": 8.347068343084777e-06, "loss": 0.0574, "step": 67390 }, { "epoch": 8.37, "learning_rate": 8.346819370098344e-06, "loss": 0.0566, "step": 67400 }, { "epoch": 8.37, "learning_rate": 8.346570397111914e-06, "loss": 0.052, "step": 67410 }, { "epoch": 8.37, "learning_rate": 8.346321424125483e-06, "loss": 0.0472, "step": 67420 }, { "epoch": 8.37, "learning_rate": 8.346072451139053e-06, "loss": 0.0579, "step": 67430 }, { "epoch": 8.37, "learning_rate": 8.345823478152621e-06, "loss": 0.0497, "step": 67440 }, { "epoch": 8.38, "learning_rate": 8.34557450516619e-06, "loss": 0.0354, "step": 67450 }, { "epoch": 8.38, "learning_rate": 8.345325532179758e-06, "loss": 0.0524, "step": 67460 }, { "epoch": 8.38, "learning_rate": 8.345076559193329e-06, "loss": 0.0351, "step": 67470 }, { "epoch": 8.38, "learning_rate": 8.344827586206897e-06, "loss": 0.0364, "step": 67480 }, { "epoch": 8.38, "learning_rate": 8.344578613220466e-06, "loss": 0.0389, "step": 67490 }, { "epoch": 8.38, "learning_rate": 8.344329640234036e-06, "loss": 0.056, "step": 67500 }, { "epoch": 8.38, "learning_rate": 8.344080667247604e-06, "loss": 0.0343, "step": 67510 }, { "epoch": 8.38, "learning_rate": 8.343831694261173e-06, "loss": 0.0597, "step": 67520 }, { "epoch": 8.39, "learning_rate": 8.343582721274741e-06, "loss": 0.0481, "step": 67530 }, { "epoch": 8.39, "learning_rate": 8.343333748288312e-06, "loss": 0.0624, "step": 67540 }, { "epoch": 8.39, "learning_rate": 8.34308477530188e-06, "loss": 0.048, "step": 67550 }, { "epoch": 8.39, "learning_rate": 8.34283580231545e-06, "loss": 0.0406, "step": 67560 }, { "epoch": 8.39, "learning_rate": 8.342586829329017e-06, "loss": 0.0386, "step": 67570 }, { "epoch": 8.39, "learning_rate": 8.342337856342587e-06, "loss": 0.0605, "step": 67580 }, { "epoch": 8.39, "learning_rate": 8.342088883356156e-06, "loss": 0.0271, "step": 67590 }, { "epoch": 8.39, "learning_rate": 8.341839910369726e-06, "loss": 0.0571, "step": 67600 }, { "epoch": 8.4, "learning_rate": 8.341590937383295e-06, "loss": 0.0342, "step": 67610 }, { "epoch": 8.4, "learning_rate": 8.341341964396865e-06, "loss": 0.0538, "step": 67620 }, { "epoch": 8.4, "learning_rate": 8.341092991410432e-06, "loss": 0.0417, "step": 67630 }, { "epoch": 8.4, "learning_rate": 8.340844018424002e-06, "loss": 0.0406, "step": 67640 }, { "epoch": 8.4, "learning_rate": 8.34059504543757e-06, "loss": 0.051, "step": 67650 }, { "epoch": 8.4, "learning_rate": 8.34034607245114e-06, "loss": 0.0471, "step": 67660 }, { "epoch": 8.4, "learning_rate": 8.340097099464709e-06, "loss": 0.0354, "step": 67670 }, { "epoch": 8.4, "learning_rate": 8.339848126478278e-06, "loss": 0.0381, "step": 67680 }, { "epoch": 8.41, "learning_rate": 8.339599153491846e-06, "loss": 0.0294, "step": 67690 }, { "epoch": 8.41, "learning_rate": 8.339350180505416e-06, "loss": 0.0598, "step": 67700 }, { "epoch": 8.41, "learning_rate": 8.339101207518985e-06, "loss": 0.0708, "step": 67710 }, { "epoch": 8.41, "learning_rate": 8.338852234532553e-06, "loss": 0.0291, "step": 67720 }, { "epoch": 8.41, "learning_rate": 8.338603261546124e-06, "loss": 0.0414, "step": 67730 }, { "epoch": 8.41, "learning_rate": 8.338354288559692e-06, "loss": 0.0538, "step": 67740 }, { "epoch": 8.41, "learning_rate": 8.33810531557326e-06, "loss": 0.0494, "step": 67750 }, { "epoch": 8.41, "learning_rate": 8.337856342586829e-06, "loss": 0.0637, "step": 67760 }, { "epoch": 8.42, "learning_rate": 8.3376073696004e-06, "loss": 0.0507, "step": 67770 }, { "epoch": 8.42, "learning_rate": 8.337358396613968e-06, "loss": 0.0442, "step": 67780 }, { "epoch": 8.42, "learning_rate": 8.337109423627538e-06, "loss": 0.0507, "step": 67790 }, { "epoch": 8.42, "learning_rate": 8.336860450641107e-06, "loss": 0.0475, "step": 67800 }, { "epoch": 8.42, "learning_rate": 8.336611477654675e-06, "loss": 0.0463, "step": 67810 }, { "epoch": 8.42, "learning_rate": 8.336362504668244e-06, "loss": 0.0427, "step": 67820 }, { "epoch": 8.42, "learning_rate": 8.336113531681814e-06, "loss": 0.0386, "step": 67830 }, { "epoch": 8.42, "learning_rate": 8.335864558695382e-06, "loss": 0.0418, "step": 67840 }, { "epoch": 8.43, "learning_rate": 8.335615585708951e-06, "loss": 0.049, "step": 67850 }, { "epoch": 8.43, "learning_rate": 8.335366612722521e-06, "loss": 0.05, "step": 67860 }, { "epoch": 8.43, "learning_rate": 8.33511763973609e-06, "loss": 0.051, "step": 67870 }, { "epoch": 8.43, "learning_rate": 8.334868666749658e-06, "loss": 0.031, "step": 67880 }, { "epoch": 8.43, "learning_rate": 8.334619693763227e-06, "loss": 0.0272, "step": 67890 }, { "epoch": 8.43, "learning_rate": 8.334370720776797e-06, "loss": 0.0578, "step": 67900 }, { "epoch": 8.43, "learning_rate": 8.334121747790365e-06, "loss": 0.0533, "step": 67910 }, { "epoch": 8.43, "learning_rate": 8.333872774803936e-06, "loss": 0.0423, "step": 67920 }, { "epoch": 8.44, "learning_rate": 8.333623801817502e-06, "loss": 0.0395, "step": 67930 }, { "epoch": 8.44, "learning_rate": 8.333374828831073e-06, "loss": 0.0618, "step": 67940 }, { "epoch": 8.44, "learning_rate": 8.333125855844641e-06, "loss": 0.0327, "step": 67950 }, { "epoch": 8.44, "learning_rate": 8.332876882858211e-06, "loss": 0.0385, "step": 67960 }, { "epoch": 8.44, "learning_rate": 8.33262790987178e-06, "loss": 0.0362, "step": 67970 }, { "epoch": 8.44, "learning_rate": 8.332378936885348e-06, "loss": 0.0504, "step": 67980 }, { "epoch": 8.44, "learning_rate": 8.332129963898917e-06, "loss": 0.0506, "step": 67990 }, { "epoch": 8.44, "learning_rate": 8.331880990912487e-06, "loss": 0.048, "step": 68000 }, { "epoch": 8.45, "learning_rate": 8.331632017926056e-06, "loss": 0.0401, "step": 68010 }, { "epoch": 8.45, "learning_rate": 8.331383044939624e-06, "loss": 0.0353, "step": 68020 }, { "epoch": 8.45, "learning_rate": 8.331134071953194e-06, "loss": 0.0457, "step": 68030 }, { "epoch": 8.45, "learning_rate": 8.330885098966763e-06, "loss": 0.0597, "step": 68040 }, { "epoch": 8.45, "learning_rate": 8.330636125980331e-06, "loss": 0.0431, "step": 68050 }, { "epoch": 8.45, "learning_rate": 8.3303871529939e-06, "loss": 0.0524, "step": 68060 }, { "epoch": 8.45, "learning_rate": 8.33013818000747e-06, "loss": 0.0463, "step": 68070 }, { "epoch": 8.45, "learning_rate": 8.329889207021039e-06, "loss": 0.0698, "step": 68080 }, { "epoch": 8.46, "learning_rate": 8.329640234034609e-06, "loss": 0.0472, "step": 68090 }, { "epoch": 8.46, "learning_rate": 8.329391261048176e-06, "loss": 0.0419, "step": 68100 }, { "epoch": 8.46, "learning_rate": 8.329142288061746e-06, "loss": 0.0539, "step": 68110 }, { "epoch": 8.46, "learning_rate": 8.328893315075314e-06, "loss": 0.0373, "step": 68120 }, { "epoch": 8.46, "learning_rate": 8.328644342088885e-06, "loss": 0.0537, "step": 68130 }, { "epoch": 8.46, "learning_rate": 8.328395369102453e-06, "loss": 0.0619, "step": 68140 }, { "epoch": 8.46, "learning_rate": 8.328146396116023e-06, "loss": 0.0465, "step": 68150 }, { "epoch": 8.46, "learning_rate": 8.32789742312959e-06, "loss": 0.0384, "step": 68160 }, { "epoch": 8.47, "learning_rate": 8.32764845014316e-06, "loss": 0.0314, "step": 68170 }, { "epoch": 8.47, "learning_rate": 8.327399477156729e-06, "loss": 0.0298, "step": 68180 }, { "epoch": 8.47, "learning_rate": 8.327150504170299e-06, "loss": 0.0566, "step": 68190 }, { "epoch": 8.47, "learning_rate": 8.326901531183868e-06, "loss": 0.0422, "step": 68200 }, { "epoch": 8.47, "learning_rate": 8.326652558197436e-06, "loss": 0.0485, "step": 68210 }, { "epoch": 8.47, "learning_rate": 8.326403585211005e-06, "loss": 0.0401, "step": 68220 }, { "epoch": 8.47, "learning_rate": 8.326154612224575e-06, "loss": 0.0371, "step": 68230 }, { "epoch": 8.47, "learning_rate": 8.325905639238143e-06, "loss": 0.0635, "step": 68240 }, { "epoch": 8.48, "learning_rate": 8.325656666251712e-06, "loss": 0.0418, "step": 68250 }, { "epoch": 8.48, "learning_rate": 8.325407693265282e-06, "loss": 0.0617, "step": 68260 }, { "epoch": 8.48, "learning_rate": 8.32515872027885e-06, "loss": 0.0458, "step": 68270 }, { "epoch": 8.48, "learning_rate": 8.324909747292419e-06, "loss": 0.0617, "step": 68280 }, { "epoch": 8.48, "learning_rate": 8.324660774305988e-06, "loss": 0.078, "step": 68290 }, { "epoch": 8.48, "learning_rate": 8.324411801319558e-06, "loss": 0.0368, "step": 68300 }, { "epoch": 8.48, "learning_rate": 8.324162828333126e-06, "loss": 0.0415, "step": 68310 }, { "epoch": 8.48, "learning_rate": 8.323913855346697e-06, "loss": 0.0415, "step": 68320 }, { "epoch": 8.49, "learning_rate": 8.323664882360265e-06, "loss": 0.0661, "step": 68330 }, { "epoch": 8.49, "learning_rate": 8.323415909373834e-06, "loss": 0.0427, "step": 68340 }, { "epoch": 8.49, "learning_rate": 8.323166936387402e-06, "loss": 0.0485, "step": 68350 }, { "epoch": 8.49, "learning_rate": 8.322917963400972e-06, "loss": 0.0364, "step": 68360 }, { "epoch": 8.49, "learning_rate": 8.32266899041454e-06, "loss": 0.0397, "step": 68370 }, { "epoch": 8.49, "learning_rate": 8.32242001742811e-06, "loss": 0.044, "step": 68380 }, { "epoch": 8.49, "learning_rate": 8.32217104444168e-06, "loss": 0.0536, "step": 68390 }, { "epoch": 8.49, "learning_rate": 8.321922071455248e-06, "loss": 0.0834, "step": 68400 }, { "epoch": 8.49, "learning_rate": 8.321673098468817e-06, "loss": 0.0367, "step": 68410 }, { "epoch": 8.5, "learning_rate": 8.321424125482385e-06, "loss": 0.0273, "step": 68420 }, { "epoch": 8.5, "learning_rate": 8.321175152495955e-06, "loss": 0.0412, "step": 68430 }, { "epoch": 8.5, "learning_rate": 8.320926179509524e-06, "loss": 0.092, "step": 68440 }, { "epoch": 8.5, "learning_rate": 8.320677206523094e-06, "loss": 0.0576, "step": 68450 }, { "epoch": 8.5, "learning_rate": 8.32042823353666e-06, "loss": 0.0494, "step": 68460 }, { "epoch": 8.5, "learning_rate": 8.320179260550231e-06, "loss": 0.0342, "step": 68470 }, { "epoch": 8.5, "learning_rate": 8.3199302875638e-06, "loss": 0.0764, "step": 68480 }, { "epoch": 8.5, "learning_rate": 8.31968131457737e-06, "loss": 0.0429, "step": 68490 }, { "epoch": 8.51, "learning_rate": 8.319432341590938e-06, "loss": 0.0369, "step": 68500 }, { "epoch": 8.51, "learning_rate": 8.319183368604507e-06, "loss": 0.0301, "step": 68510 }, { "epoch": 8.51, "learning_rate": 8.318934395618075e-06, "loss": 0.045, "step": 68520 }, { "epoch": 8.51, "learning_rate": 8.318685422631646e-06, "loss": 0.0723, "step": 68530 }, { "epoch": 8.51, "learning_rate": 8.318436449645214e-06, "loss": 0.0428, "step": 68540 }, { "epoch": 8.51, "learning_rate": 8.318187476658783e-06, "loss": 0.0624, "step": 68550 }, { "epoch": 8.51, "learning_rate": 8.317938503672353e-06, "loss": 0.0526, "step": 68560 }, { "epoch": 8.51, "learning_rate": 8.317689530685921e-06, "loss": 0.045, "step": 68570 }, { "epoch": 8.52, "learning_rate": 8.31744055769949e-06, "loss": 0.0596, "step": 68580 }, { "epoch": 8.52, "learning_rate": 8.317191584713058e-06, "loss": 0.0714, "step": 68590 }, { "epoch": 8.52, "learning_rate": 8.316942611726629e-06, "loss": 0.0474, "step": 68600 }, { "epoch": 8.52, "learning_rate": 8.316693638740197e-06, "loss": 0.0472, "step": 68610 }, { "epoch": 8.52, "learning_rate": 8.316444665753767e-06, "loss": 0.0303, "step": 68620 }, { "epoch": 8.52, "learning_rate": 8.316195692767336e-06, "loss": 0.0369, "step": 68630 }, { "epoch": 8.52, "learning_rate": 8.315946719780904e-06, "loss": 0.0633, "step": 68640 }, { "epoch": 8.52, "learning_rate": 8.315697746794473e-06, "loss": 0.0377, "step": 68650 }, { "epoch": 8.53, "learning_rate": 8.315448773808043e-06, "loss": 0.0415, "step": 68660 }, { "epoch": 8.53, "learning_rate": 8.315199800821612e-06, "loss": 0.0338, "step": 68670 }, { "epoch": 8.53, "learning_rate": 8.314950827835182e-06, "loss": 0.046, "step": 68680 }, { "epoch": 8.53, "learning_rate": 8.31470185484875e-06, "loss": 0.0692, "step": 68690 }, { "epoch": 8.53, "learning_rate": 8.314452881862319e-06, "loss": 0.0387, "step": 68700 }, { "epoch": 8.53, "learning_rate": 8.314203908875887e-06, "loss": 0.0393, "step": 68710 }, { "epoch": 8.53, "learning_rate": 8.313954935889457e-06, "loss": 0.038, "step": 68720 }, { "epoch": 8.53, "learning_rate": 8.313705962903026e-06, "loss": 0.0545, "step": 68730 }, { "epoch": 8.54, "learning_rate": 8.313456989916595e-06, "loss": 0.0722, "step": 68740 }, { "epoch": 8.54, "learning_rate": 8.313208016930163e-06, "loss": 0.0376, "step": 68750 }, { "epoch": 8.54, "learning_rate": 8.312959043943733e-06, "loss": 0.0413, "step": 68760 }, { "epoch": 8.54, "learning_rate": 8.312710070957302e-06, "loss": 0.0376, "step": 68770 }, { "epoch": 8.54, "learning_rate": 8.31246109797087e-06, "loss": 0.066, "step": 68780 }, { "epoch": 8.54, "learning_rate": 8.31221212498444e-06, "loss": 0.0647, "step": 68790 }, { "epoch": 8.54, "learning_rate": 8.311963151998009e-06, "loss": 0.0387, "step": 68800 }, { "epoch": 8.54, "learning_rate": 8.311714179011578e-06, "loss": 0.0393, "step": 68810 }, { "epoch": 8.55, "learning_rate": 8.311465206025146e-06, "loss": 0.0374, "step": 68820 }, { "epoch": 8.55, "learning_rate": 8.311216233038716e-06, "loss": 0.0487, "step": 68830 }, { "epoch": 8.55, "learning_rate": 8.310967260052285e-06, "loss": 0.0559, "step": 68840 }, { "epoch": 8.55, "learning_rate": 8.310718287065855e-06, "loss": 0.0459, "step": 68850 }, { "epoch": 8.55, "learning_rate": 8.310469314079423e-06, "loss": 0.0281, "step": 68860 }, { "epoch": 8.55, "learning_rate": 8.310220341092992e-06, "loss": 0.049, "step": 68870 }, { "epoch": 8.55, "learning_rate": 8.30997136810656e-06, "loss": 0.0545, "step": 68880 }, { "epoch": 8.55, "learning_rate": 8.30972239512013e-06, "loss": 0.0604, "step": 68890 }, { "epoch": 8.56, "learning_rate": 8.3094734221337e-06, "loss": 0.0527, "step": 68900 }, { "epoch": 8.56, "learning_rate": 8.309224449147268e-06, "loss": 0.0601, "step": 68910 }, { "epoch": 8.56, "learning_rate": 8.308975476160838e-06, "loss": 0.0637, "step": 68920 }, { "epoch": 8.56, "learning_rate": 8.308726503174406e-06, "loss": 0.0505, "step": 68930 }, { "epoch": 8.56, "learning_rate": 8.308477530187975e-06, "loss": 0.0626, "step": 68940 }, { "epoch": 8.56, "learning_rate": 8.308228557201544e-06, "loss": 0.0631, "step": 68950 }, { "epoch": 8.56, "learning_rate": 8.307979584215114e-06, "loss": 0.0536, "step": 68960 }, { "epoch": 8.56, "learning_rate": 8.307730611228682e-06, "loss": 0.0624, "step": 68970 }, { "epoch": 8.57, "learning_rate": 8.307481638242252e-06, "loss": 0.0336, "step": 68980 }, { "epoch": 8.57, "learning_rate": 8.30723266525582e-06, "loss": 0.0822, "step": 68990 }, { "epoch": 8.57, "learning_rate": 8.30698369226939e-06, "loss": 0.0344, "step": 69000 }, { "epoch": 8.57, "learning_rate": 8.306734719282958e-06, "loss": 0.0383, "step": 69010 }, { "epoch": 8.57, "learning_rate": 8.306485746296528e-06, "loss": 0.0441, "step": 69020 }, { "epoch": 8.57, "learning_rate": 8.306236773310097e-06, "loss": 0.0434, "step": 69030 }, { "epoch": 8.57, "learning_rate": 8.305987800323665e-06, "loss": 0.0574, "step": 69040 }, { "epoch": 8.57, "learning_rate": 8.305738827337234e-06, "loss": 0.0599, "step": 69050 }, { "epoch": 8.58, "learning_rate": 8.305489854350804e-06, "loss": 0.056, "step": 69060 }, { "epoch": 8.58, "learning_rate": 8.305240881364372e-06, "loss": 0.0388, "step": 69070 }, { "epoch": 8.58, "learning_rate": 8.304991908377941e-06, "loss": 0.0487, "step": 69080 }, { "epoch": 8.58, "learning_rate": 8.304742935391511e-06, "loss": 0.045, "step": 69090 }, { "epoch": 8.58, "learning_rate": 8.30449396240508e-06, "loss": 0.0779, "step": 69100 }, { "epoch": 8.58, "learning_rate": 8.304244989418648e-06, "loss": 0.0629, "step": 69110 }, { "epoch": 8.58, "learning_rate": 8.303996016432217e-06, "loss": 0.0368, "step": 69120 }, { "epoch": 8.58, "learning_rate": 8.303747043445787e-06, "loss": 0.0467, "step": 69130 }, { "epoch": 8.59, "learning_rate": 8.303498070459355e-06, "loss": 0.0363, "step": 69140 }, { "epoch": 8.59, "learning_rate": 8.303249097472926e-06, "loss": 0.0614, "step": 69150 }, { "epoch": 8.59, "learning_rate": 8.303000124486494e-06, "loss": 0.0925, "step": 69160 }, { "epoch": 8.59, "learning_rate": 8.302751151500063e-06, "loss": 0.043, "step": 69170 }, { "epoch": 8.59, "learning_rate": 8.302502178513631e-06, "loss": 0.0544, "step": 69180 }, { "epoch": 8.59, "learning_rate": 8.302253205527201e-06, "loss": 0.0767, "step": 69190 }, { "epoch": 8.59, "learning_rate": 8.30200423254077e-06, "loss": 0.0538, "step": 69200 }, { "epoch": 8.59, "learning_rate": 8.30175525955434e-06, "loss": 0.0521, "step": 69210 }, { "epoch": 8.6, "learning_rate": 8.301506286567909e-06, "loss": 0.0489, "step": 69220 }, { "epoch": 8.6, "learning_rate": 8.301257313581477e-06, "loss": 0.0495, "step": 69230 }, { "epoch": 8.6, "learning_rate": 8.301008340595046e-06, "loss": 0.0608, "step": 69240 }, { "epoch": 8.6, "learning_rate": 8.300759367608616e-06, "loss": 0.0577, "step": 69250 }, { "epoch": 8.6, "learning_rate": 8.300510394622184e-06, "loss": 0.0398, "step": 69260 }, { "epoch": 8.6, "learning_rate": 8.300261421635753e-06, "loss": 0.041, "step": 69270 }, { "epoch": 8.6, "learning_rate": 8.300012448649323e-06, "loss": 0.04, "step": 69280 }, { "epoch": 8.6, "learning_rate": 8.299763475662892e-06, "loss": 0.0809, "step": 69290 }, { "epoch": 8.61, "learning_rate": 8.29951450267646e-06, "loss": 0.0396, "step": 69300 }, { "epoch": 8.61, "learning_rate": 8.299265529690029e-06, "loss": 0.0492, "step": 69310 }, { "epoch": 8.61, "learning_rate": 8.299016556703599e-06, "loss": 0.0402, "step": 69320 }, { "epoch": 8.61, "learning_rate": 8.298767583717167e-06, "loss": 0.0318, "step": 69330 }, { "epoch": 8.61, "learning_rate": 8.298518610730738e-06, "loss": 0.0591, "step": 69340 }, { "epoch": 8.61, "learning_rate": 8.298269637744304e-06, "loss": 0.07, "step": 69350 }, { "epoch": 8.61, "learning_rate": 8.298020664757875e-06, "loss": 0.0644, "step": 69360 }, { "epoch": 8.61, "learning_rate": 8.297771691771443e-06, "loss": 0.0445, "step": 69370 }, { "epoch": 8.62, "learning_rate": 8.297522718785013e-06, "loss": 0.0323, "step": 69380 }, { "epoch": 8.62, "learning_rate": 8.297273745798582e-06, "loss": 0.0552, "step": 69390 }, { "epoch": 8.62, "learning_rate": 8.29702477281215e-06, "loss": 0.043, "step": 69400 }, { "epoch": 8.62, "learning_rate": 8.296775799825719e-06, "loss": 0.0494, "step": 69410 }, { "epoch": 8.62, "learning_rate": 8.29652682683929e-06, "loss": 0.024, "step": 69420 }, { "epoch": 8.62, "learning_rate": 8.296277853852858e-06, "loss": 0.0454, "step": 69430 }, { "epoch": 8.62, "learning_rate": 8.296028880866426e-06, "loss": 0.0778, "step": 69440 }, { "epoch": 8.62, "learning_rate": 8.295779907879996e-06, "loss": 0.0469, "step": 69450 }, { "epoch": 8.63, "learning_rate": 8.295530934893565e-06, "loss": 0.0644, "step": 69460 }, { "epoch": 8.63, "learning_rate": 8.295281961907133e-06, "loss": 0.0463, "step": 69470 }, { "epoch": 8.63, "learning_rate": 8.295032988920702e-06, "loss": 0.0492, "step": 69480 }, { "epoch": 8.63, "learning_rate": 8.294784015934272e-06, "loss": 0.0386, "step": 69490 }, { "epoch": 8.63, "learning_rate": 8.29453504294784e-06, "loss": 0.0477, "step": 69500 }, { "epoch": 8.63, "learning_rate": 8.294286069961411e-06, "loss": 0.0336, "step": 69510 }, { "epoch": 8.63, "learning_rate": 8.294037096974978e-06, "loss": 0.0294, "step": 69520 }, { "epoch": 8.63, "learning_rate": 8.293788123988548e-06, "loss": 0.0648, "step": 69530 }, { "epoch": 8.64, "learning_rate": 8.293539151002116e-06, "loss": 0.0607, "step": 69540 }, { "epoch": 8.64, "learning_rate": 8.293290178015687e-06, "loss": 0.0895, "step": 69550 }, { "epoch": 8.64, "learning_rate": 8.293041205029255e-06, "loss": 0.0341, "step": 69560 }, { "epoch": 8.64, "learning_rate": 8.292792232042824e-06, "loss": 0.0464, "step": 69570 }, { "epoch": 8.64, "learning_rate": 8.292543259056392e-06, "loss": 0.0528, "step": 69580 }, { "epoch": 8.64, "learning_rate": 8.292294286069962e-06, "loss": 0.0465, "step": 69590 }, { "epoch": 8.64, "learning_rate": 8.292045313083531e-06, "loss": 0.0413, "step": 69600 }, { "epoch": 8.64, "learning_rate": 8.2917963400971e-06, "loss": 0.0738, "step": 69610 }, { "epoch": 8.65, "learning_rate": 8.29154736711067e-06, "loss": 0.029, "step": 69620 }, { "epoch": 8.65, "learning_rate": 8.291298394124238e-06, "loss": 0.0517, "step": 69630 }, { "epoch": 8.65, "learning_rate": 8.291049421137807e-06, "loss": 0.0504, "step": 69640 }, { "epoch": 8.65, "learning_rate": 8.290800448151375e-06, "loss": 0.0592, "step": 69650 }, { "epoch": 8.65, "learning_rate": 8.290551475164945e-06, "loss": 0.0659, "step": 69660 }, { "epoch": 8.65, "learning_rate": 8.290302502178514e-06, "loss": 0.0526, "step": 69670 }, { "epoch": 8.65, "learning_rate": 8.290053529192084e-06, "loss": 0.0485, "step": 69680 }, { "epoch": 8.65, "learning_rate": 8.289804556205653e-06, "loss": 0.0475, "step": 69690 }, { "epoch": 8.66, "learning_rate": 8.289555583219221e-06, "loss": 0.0693, "step": 69700 }, { "epoch": 8.66, "learning_rate": 8.28930661023279e-06, "loss": 0.0395, "step": 69710 }, { "epoch": 8.66, "learning_rate": 8.28905763724636e-06, "loss": 0.0482, "step": 69720 }, { "epoch": 8.66, "learning_rate": 8.288808664259928e-06, "loss": 0.0402, "step": 69730 }, { "epoch": 8.66, "learning_rate": 8.288559691273499e-06, "loss": 0.0697, "step": 69740 }, { "epoch": 8.66, "learning_rate": 8.288310718287067e-06, "loss": 0.0459, "step": 69750 }, { "epoch": 8.66, "learning_rate": 8.288061745300636e-06, "loss": 0.0249, "step": 69760 }, { "epoch": 8.66, "learning_rate": 8.287812772314204e-06, "loss": 0.0379, "step": 69770 }, { "epoch": 8.67, "learning_rate": 8.287563799327774e-06, "loss": 0.0586, "step": 69780 }, { "epoch": 8.67, "learning_rate": 8.287314826341343e-06, "loss": 0.0518, "step": 69790 }, { "epoch": 8.67, "learning_rate": 8.287065853354911e-06, "loss": 0.0572, "step": 69800 }, { "epoch": 8.67, "learning_rate": 8.286816880368482e-06, "loss": 0.0334, "step": 69810 }, { "epoch": 8.67, "learning_rate": 8.28656790738205e-06, "loss": 0.0348, "step": 69820 }, { "epoch": 8.67, "learning_rate": 8.286318934395619e-06, "loss": 0.0535, "step": 69830 }, { "epoch": 8.67, "learning_rate": 8.286069961409187e-06, "loss": 0.0497, "step": 69840 }, { "epoch": 8.67, "learning_rate": 8.285820988422757e-06, "loss": 0.0355, "step": 69850 }, { "epoch": 8.67, "learning_rate": 8.285572015436326e-06, "loss": 0.0281, "step": 69860 }, { "epoch": 8.68, "learning_rate": 8.285323042449896e-06, "loss": 0.0278, "step": 69870 }, { "epoch": 8.68, "learning_rate": 8.285074069463463e-06, "loss": 0.029, "step": 69880 }, { "epoch": 8.68, "learning_rate": 8.284825096477033e-06, "loss": 0.0608, "step": 69890 }, { "epoch": 8.68, "learning_rate": 8.284576123490602e-06, "loss": 0.0538, "step": 69900 }, { "epoch": 8.68, "learning_rate": 8.284327150504172e-06, "loss": 0.0718, "step": 69910 }, { "epoch": 8.68, "learning_rate": 8.28407817751774e-06, "loss": 0.0256, "step": 69920 }, { "epoch": 8.68, "learning_rate": 8.283829204531309e-06, "loss": 0.0327, "step": 69930 }, { "epoch": 8.68, "learning_rate": 8.283580231544877e-06, "loss": 0.0509, "step": 69940 }, { "epoch": 8.69, "learning_rate": 8.283331258558448e-06, "loss": 0.0559, "step": 69950 }, { "epoch": 8.69, "learning_rate": 8.283082285572016e-06, "loss": 0.0489, "step": 69960 }, { "epoch": 8.69, "learning_rate": 8.282833312585585e-06, "loss": 0.0383, "step": 69970 }, { "epoch": 8.69, "learning_rate": 8.282584339599155e-06, "loss": 0.0572, "step": 69980 }, { "epoch": 8.69, "learning_rate": 8.282335366612723e-06, "loss": 0.0458, "step": 69990 }, { "epoch": 8.69, "learning_rate": 8.282086393626292e-06, "loss": 0.0585, "step": 70000 }, { "epoch": 8.69, "eval_bleu": 89.492, "eval_gen_len_ratio": 1.0, "eval_has_error_acc": 0.7703, "eval_has_error_f1": 0.6974, "eval_loss": 0.053506676107645035, "eval_runtime": 1365.4911, "eval_samples_per_second": 2.928, "eval_steps_per_second": 0.732, "step": 70000 } ], "max_steps": 402650, "num_train_epochs": 50, "total_flos": 5.226203595417846e+17, "trial_name": null, "trial_params": null }