File size: 183,627 Bytes
78aa4ee |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "Igc5itf-xMGj"
},
"source": [
"# Masakhane - Reverse Machine Translation for African Languages (Using JoeyNMT)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> ## NB\n",
">### - The purpose of this Notebook is to build models that translate African languages(target language) *into* English(source language). This will allow us to in future be able to make translations from one African language to the other. If you'd like to translate *from* English, please use [this](https://github.com/masakhane-io/masakhane-mt/blob/master/starter_notebook.ipynb) starter notebook instead.\n",
"\n",
">### - We call this reverse training because normally we build models that make translations from the source language(English) to the target language. But in this case we are doing the reverse; building models that make translations from the target language to the source(English)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "x4fXCKCf36IK"
},
"source": [
"## Note before beginning:\n",
"### - The idea is that you should be able to make minimal changes to this in order to get SOME result for your own translation corpus. \n",
"\n",
"### - The tl;dr: Go to the **\"TODO\"** comments which will tell you what to update to get up and running\n",
"\n",
"### - If you actually want to have a clue what you're doing, read the text and peek at the links\n",
"\n",
"### - With 100 epochs, it should take around 7 hours to run in Google Colab\n",
"\n",
"### - Once you've gotten a result for your language, please attach and email your notebook that generated it to [email protected]\n",
"\n",
"### - If you care enough and get a chance, doing a brief background on your language would be amazing. See examples in [(Martinus, 2019)](https://arxiv.org/abs/1906.05685)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "l929HimrxS0a"
},
"source": [
"## Retrieve your data & make a parallel corpus\n",
"\n",
"If you are wanting to use the JW300 data referenced on the Masakhane website or in our GitHub repo, you can use `opus-tools` to convert the data into a convenient format. `opus_read` from that package provides a convenient tool for reading the native aligned XML files and to convert them to TMX format. The tool can also be used to fetch relevant files from OPUS on the fly and to filter the data as necessary. [Read the documentation](https://pypi.org/project/opustools-pkg/) for more details.\n",
"\n",
"Once you have your corpus files in TMX format (an xml structure which will include the sentences in your target language and your source language in a single file), we recommend reading them into a pandas dataframe. Thankfully, Jade wrote a silly `tmx2dataframe` package which converts your tmx file to a pandas dataframe. "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"id": "oGRmDELn7Az0",
"outputId": "807c3318-4a3e-483b-fed0-142c2b9f926a"
},
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'google.colab'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-1-d5df0069828e>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mgoogle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolab\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mdrive\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mdrive\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmount\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'/content/drive'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'google.colab'"
]
}
],
"source": [
"from google.colab import drive\n",
"drive.mount('/content/drive')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"id": "Cn3tgQLzUxwn"
},
"outputs": [],
"source": [
"# TODO: Set your source and target languages. Keep in mind, these traditionally use language codes as found here:\n",
"# These will also become the suffix's of all vocab and corpus files used throughout\n",
"import os\n",
"source_language = \"en\"\n",
"target_language = \"sw\" \n",
"lc = False # If True, lowercase the data.\n",
"seed = 42 # Random seed for shuffling.\n",
"tag = \"baseline\" # Give a unique name to your folder - this is to ensure you don't rewrite any models you've already submitted\n",
"\n",
"os.environ[\"src\"] = source_language # Sets them in bash as well, since we often use bash scripts\n",
"os.environ[\"tgt\"] = target_language\n",
"os.environ[\"tag\"] = tag\n",
"\n",
"# # This will save it to a folder in our gdrive instead!\n",
"# !mkdir -p \"/content/drive/My Drive/masakhane/$tgt-$src-$tag\"\n",
"# os.environ[\"gdrive_path\"] = \"/content/drive/My Drive/masakhane/%s-%s-%s\" % (target_language, source_language, tag)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"id": "kBSgJHEw7Nvx",
"outputId": "3bdb0703-874f-4d53-e5b2-7802a937720b"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/content/drive/My Drive/masakhane/en-sw-baseline\n"
]
}
],
"source": [
"# !echo $gdrive_path"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"id": "gA75Fs9ys8Y9",
"outputId": "e415db4b-66fe-4785-b80f-6e375809c1bf"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting opustools-pkg\n",
" Downloading opustools_pkg-0.0.52-py3-none-any.whl (80 kB)\n",
"\u001b[K |████████████████████████████████| 80 kB 5.6 MB/s eta 0:00:01\n",
"\u001b[?25hInstalling collected packages: opustools-pkg\n",
"Successfully installed opustools-pkg-0.0.52\n"
]
}
],
"source": [
"# Install opus-tools\n",
"! pip install opustools-pkg"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 208
},
"id": "xq-tDZVks7ZD",
"outputId": "c19ee6c0-e652-486c-a1fd-0c5fd265b204"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Alignment file /proj/nlpl/data/OPUS/JW300/latest/xml/en-sw.xml.gz not found. The following files are available for downloading:\n",
"\n",
" ./JW300_latest_xml_en.zip already exists\n",
" ./JW300_latest_xml_sw.zip already exists\n",
" 10 MB https://object.pouta.csc.fi/OPUS-JW300/v1b/xml/en-sw.xml.gz\n",
"\n",
" 10 MB Total size\n",
"./JW300_latest_xml_en-sw.xml.gz ... 100% of 10 MB\n",
"gzip: JW300_latest_xml_en-sw.xml already exists; do you wish to overwrite (y or n)? ^C\n"
]
}
],
"source": [
"# Downloading our corpus\n",
"! opus_read -d JW300 -s $src -t $tgt -wm moses -w jw300.$src jw300.$tgt -q\n",
"\n",
"# extract the corpus file\n",
"! gunzip JW300_latest_xml_$src-$tgt.xml.gz"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 590
},
"id": "n48GDRnP8y2G",
"outputId": "e27c546b-8b90-43c3-9123-738d3473f12a"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--2021-05-10 11:25:43-- https://raw.githubusercontent.com/juliakreutzer/masakhane/master/jw300_utils/test/test.en-any.en\n",
"Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
"Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 277791 (271K) [text/plain]\n",
"Saving to: ‘test.en-any.en.1’\n",
"\n",
"test.en-any.en.1 100%[===================>] 271.28K --.-KB/s in 0.04s \n",
"\n",
"2021-05-10 11:25:43 (7.36 MB/s) - ‘test.en-any.en.1’ saved [277791/277791]\n",
"\n",
"--2021-05-10 11:25:43-- https://raw.githubusercontent.com/juliakreutzer/masakhane/master/jw300_utils/test/test.en-sw.en\n",
"Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
"Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 206336 (202K) [text/plain]\n",
"Saving to: ‘test.en-sw.en’\n",
"\n",
"test.en-sw.en 100%[===================>] 201.50K --.-KB/s in 0.02s \n",
"\n",
"2021-05-10 11:25:43 (7.98 MB/s) - ‘test.en-sw.en’ saved [206336/206336]\n",
"\n",
"--2021-05-10 11:25:44-- https://raw.githubusercontent.com/juliakreutzer/masakhane/master/jw300_utils/test/test.en-sw.sw\n",
"Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
"Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 214836 (210K) [text/plain]\n",
"Saving to: ‘test.en-sw.sw’\n",
"\n",
"test.en-sw.sw 100%[===================>] 209.80K --.-KB/s in 0.01s \n",
"\n",
"2021-05-10 11:25:44 (15.4 MB/s) - ‘test.en-sw.sw’ saved [214836/214836]\n",
"\n"
]
}
],
"source": [
"# Download the global test set.\n",
"! wget https://raw.githubusercontent.com/juliakreutzer/masakhane/master/jw300_utils/test/test.en-any.en\n",
" \n",
"# And the specific test set for this language pair.\n",
"os.environ[\"trg\"] = target_language \n",
"os.environ[\"src\"] = source_language \n",
"\n",
"! wget https://raw.githubusercontent.com/juliakreutzer/masakhane/master/jw300_utils/test/test.en-$trg.en \n",
"! mv test.en-$trg.en test.en\n",
"! wget https://raw.githubusercontent.com/juliakreutzer/masakhane/master/jw300_utils/test/test.en-$trg.$trg \n",
"! mv test.en-$trg.$trg test.$trg"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"id": "NqDG-CI28y2L",
"outputId": "20dc514e-b0d4-4c53-c492-705e42fbbe7c"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loaded 3571 global test sentences to filter from the training/dev data.\n"
]
}
],
"source": [
"# Read the test data to filter from train and dev splits.\n",
"# Store english portion in set for quick filtering checks.\n",
"en_test_sents = set()\n",
"filter_test_sents = \"test.en-any.en\"\n",
"j = 0\n",
"with open(filter_test_sents) as f:\n",
" for line in f:\n",
" en_test_sents.add(line.strip())\n",
" j += 1\n",
"print('Loaded {} global test sentences to filter from the training/dev data.'.format(j))"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 161
},
"id": "3CNdwLBCfSIl",
"outputId": "fc8f80b7-2f12-4f4b-ca94-3eb0258de6ee"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loaded data and skipped 6478/979526 lines since contained in test set.\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>source_sentence</th>\n",
" <th>target_sentence</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>“ Look !</td>\n",
" <td>“ Tazama !</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>I Am Making All Things New ”</td>\n",
" <td>Mimi Ninafanya Vitu Vyote Kuwa Vipya ”</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>The above is a promise from God that has been ...</td>\n",
" <td>Iliyopo juu ni ahadi itokayo kwa Mungu ambayo ...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" source_sentence \\\n",
"0 “ Look ! \n",
"1 I Am Making All Things New ” \n",
"2 The above is a promise from God that has been ... \n",
"\n",
" target_sentence \n",
"0 “ Tazama ! \n",
"1 Mimi Ninafanya Vitu Vyote Kuwa Vipya ” \n",
"2 Iliyopo juu ni ahadi itokayo kwa Mungu ambayo ... "
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"\n",
"# TMX file to dataframe\n",
"source_file = 'jw300.' + source_language\n",
"target_file = 'jw300.' + target_language\n",
"\n",
"source = []\n",
"target = []\n",
"skip_lines = [] # Collect the line numbers of the source portion to skip the same lines for the target portion.\n",
"with open(source_file) as f:\n",
" for i, line in enumerate(f):\n",
" # Skip sentences that are contained in the test set.\n",
" if line.strip() not in en_test_sents:\n",
" source.append(line.strip())\n",
" else:\n",
" skip_lines.append(i) \n",
"with open(target_file) as f:\n",
" for j, line in enumerate(f):\n",
" # Only add to corpus if corresponding source was not skipped.\n",
" if j not in skip_lines:\n",
" target.append(line.strip())\n",
" \n",
"print('Loaded data and skipped {}/{} lines since contained in test set.'.format(len(skip_lines), i))\n",
" \n",
"df = pd.DataFrame(zip(source, target), columns=['source_sentence', 'target_sentence'])\n",
"# if you get TypeError: data argument can't be an iterator is because of your zip version run this below\n",
"#df = pd.DataFrame(list(zip(source, target)), columns=['source_sentence', 'target_sentence'])\n",
"df.head(3)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "YkuK3B4p2AkN"
},
"source": [
"## Pre-processing and export\n",
"\n",
"It is generally a good idea to remove duplicate translations and conflicting translations from the corpus. In practice, these public corpora include some number of these that need to be cleaned.\n",
"\n",
"In addition we will split our data into dev/test/train and export to the filesystem."
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 191
},
"id": "M_2ouEOH1_1q",
"outputId": "b30fcc33-5a31-46fe-a224-c7d9c4e5bcb5"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/conda/lib/python3.7/site-packages/ipykernel_launcher.py:7: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" import sys\n",
"/opt/conda/lib/python3.7/site-packages/ipykernel_launcher.py:8: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" \n"
]
}
],
"source": [
"# drop duplicate translations\n",
"df_pp = df.drop_duplicates()\n",
"\n",
"# drop conflicting translations\n",
"# (this is optional and something that you might want to comment out \n",
"# depending on the size of your corpus)\n",
"df_pp.drop_duplicates(subset='source_sentence', inplace=True)\n",
"df_pp.drop_duplicates(subset='target_sentence', inplace=True)\n",
"\n",
"# Shuffle the data to remove bias in dev set selection.\n",
"df_pp = df_pp.sample(frac=1, random_state=seed).reset_index(drop=True)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 278
},
"id": "Z_1BwAApEtMk",
"outputId": "d99a471a-6fb6-4941-950c-7c90f2a0789d"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting fuzzywuzzy\n",
" Downloading fuzzywuzzy-0.18.0-py2.py3-none-any.whl (18 kB)\n",
"Installing collected packages: fuzzywuzzy\n",
"Successfully installed fuzzywuzzy-0.18.0\n",
"Collecting python-Levenshtein\n",
" Downloading python-Levenshtein-0.12.2.tar.gz (50 kB)\n",
"\u001b[K |████████████████████████████████| 50 kB 5.3 MB/s eta 0:00:01\n",
"\u001b[?25hRequirement already satisfied: setuptools in /opt/conda/lib/python3.7/site-packages (from python-Levenshtein) (49.6.0.post20210108)\n",
"Building wheels for collected packages: python-Levenshtein\n",
" Building wheel for python-Levenshtein (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for python-Levenshtein: filename=python_Levenshtein-0.12.2-cp37-cp37m-linux_x86_64.whl size=178072 sha256=79dd8af974a3293c3d4f3e292e1e6bc3631cff89ddd823545b39199678748f61\n",
" Stored in directory: /home/freshiasackey_gmail_com/.cache/pip/wheels/05/5f/ca/7c4367734892581bb5ff896f15027a932c551080b2abd3e00d\n",
"Successfully built python-Levenshtein\n",
"Installing collected packages: python-Levenshtein\n",
"Successfully installed python-Levenshtein-0.12.2\n"
]
}
],
"source": [
"# Install fuzzy wuzzy to remove \"almost duplicate\" sentences in the\n",
"# test and training sets.\n",
"! pip install fuzzywuzzy\n",
"! pip install python-Levenshtein\n",
"import time\n",
"from fuzzywuzzy import process\n",
"import numpy as np\n",
"from os import cpu_count\n",
"from functools import partial\n",
"from multiprocessing import Pool\n",
"\n",
"\n",
"# reset the index of the training set after previous filtering\n",
"df_pp.reset_index(drop=False, inplace=True)\n",
"\n",
"# Remove samples from the training data set if they \"almost overlap\" with the\n",
"# samples in the test set.\n",
"\n",
"# Filtering function. Adjust pad to narrow down the candidate matches to\n",
"# within a certain length of characters of the given sample.\n",
"def fuzzfilter(sample, candidates, pad):\n",
" candidates = [x for x in candidates if len(x) <= len(sample)+pad and len(x) >= len(sample)-pad] \n",
" if len(candidates) > 0:\n",
" return process.extractOne(sample, candidates)[1]\n",
" else:\n",
" return np.nan"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"id": "92EsgTaY3B4H"
},
"outputs": [],
"source": [
"# start_time = time.time()\n",
"# ### iterating over pandas dataframe rows is not recomended, let use multi processing to apply the function\n",
"\n",
"# with Pool(cpu_count()-1) as pool:\n",
"# scores = pool.map(partial(fuzzfilter, candidates=list(en_test_sents), pad=5), df_pp['source_sentence'])\n",
"# hours, rem = divmod(time.time() - start_time, 3600)\n",
"# minutes, seconds = divmod(rem, 60)\n",
"# print(\"done in {}h:{}min:{}seconds\".format(hours, minutes, seconds))\n",
"\n",
"# # Filter out \"almost overlapping samples\"\n",
"# df_pp = df_pp.assign(scores=scores)\n",
"# df_pp = df_pp[df_pp['scores'] < 95]"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 836
},
"id": "hxxBOCA-xXhy",
"outputId": "e009b507-337c-4c33-e07a-172790f9755f"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"==> train.en <==\n",
"Besides , being single gives one the opportunity to do so many great things !\n",
"A Logical Conclusion\n",
"I still feel the pain of the loss , but thanking Jehovah for having had a good marriage and for the privilege of serving him with someone who deeply loved him has improved my outlook . ”\n",
"If we do his will , he blesses and supports us in this life and offers us the certain hope of an even better life to come .\n",
"We are determined to continue providing a rich supply of enlightening and appealing information — both in print and online — to benefit our many readers who respect the Bible and who want to know what it really teaches .\n",
"Well , in the past decade , the number of active Witnesses increased from slightly fewer than 3,800,000 to almost 6,000,000 .\n",
"Actually , according to the Bible , there is no spiritual part of a person that survives the death of the body .\n",
"The enemy may aim a blow by attacking Bible truths that are fundamental to your faith .\n",
"When Saul returned to Damascus , “ the Jews took counsel together to do away with him . ”\n",
"To settle the issue of Godship , Elijah now proposes a contest .\n",
"\n",
"==> train.sw <==\n",
"Isitoshe , kwa kuwa sijaanzisha urafiki kama huo nina nafasi ya kufanya mambo mengi ya pekee !\n",
"Mkataa Unaopatana na Akili\n",
"Bado nina huzuni ya kufiwa , lakini mtazamo wangu umebadilika kwa sababu ya kumshukuru Yehova kwa kuwa nilikuwa na ndoa yenye furaha na pendeleo la kumtumikia pamoja na mtu aliyempenda sana . ”\n",
"Tukifanya mapenzi yake , yeye hutubariki na hututegemeza katika uhai huu na hututolea lile tumaini hakika la uhai ulio mzuri hata zaidi utakaokuja .\n",
"Tumeazimia kuendelea kutoa habari nyingi zenye kuelimisha na zinazovutia — zinazochapishwa na pia zinazopatikana kwenye Intaneti — ili kuwafaidi wasomaji wetu wengi wanaoiheshimu Biblia na wanaotaka kujua inafundisha nini hasa .\n",
"Katika miaka kumi iliyopita , idadi ya Mashahidi watendaji iliongezeka kutoka 3,800,000 hivi hadi karibu 6,000,000 .\n",
"Kwa kweli , kulingana na Biblia , hakuna sehemu yoyote ya kiroho ya mtu ambayo huendelea kuwa hai baada ya kufa kwa mwili .\n",
"Huenda adui akaamua kushambulia kweli za Biblia ambazo ni muhimu kwa imani yako .\n",
"Sauli aliporudi Damasko , “ Wayahudi walikata shauri pamoja kumwangamiza . ”\n",
"Ili kusuluhisha hilo suala la Uungu , Eliya apendekeza shindano .\n",
"==> dev.en <==\n",
"There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"Lots of hugs and kisses .\n",
"When Harald was arrested , his wife , Elsa , was still breast - feeding their ten - month - old baby girl .\n",
"Still , from his painful experience , he learned some valuable lessons .\n",
"How did Pharaoh show haughtiness , and with what result ?\n",
"What seems to trigger such outbursts ?\n",
"In a research project , Poole heard a sound that was different from the normal elephant calls .\n",
"Misery will give way to happiness when God blesses you as he did Job .\n",
"\n",
"==> dev.sw <==\n",
"Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"Kukumbatia kwingi na busu nyingi .\n",
"Wakati Harald alipokamatwa , mke wake , Elsa , alikuwa bado anamnyonyesha binti yao mwenye umri wa miezi kumi .\n",
"Ingawa hakupata utajiri , kisa chake chenye kuhuzunisha kilimfunza mambo muhimu .\n",
"Farao alionyeshaje majivuno , na matokeo yalikuwa nini ?\n",
"Ni nini huchochea milipuko hiyo ya hasira ?\n",
"Poole alipokuwa akifanya uchunguzi fulani , alisikia mlio uliokuwa tofauti na milio ya kawaida ya tembo .\n",
"Furaha itachukua mahali pa huzuni Mungu anapokubariki kama alivyombariki Ayubu .\n"
]
}
],
"source": [
"# This section does the split between train/dev for the parallel corpora then saves them as separate files\n",
"# We use 1000 dev test and the given test set.\n",
"import csv\n",
"\n",
"# Do the split between dev/train and create parallel corpora\n",
"num_dev_patterns = 1000\n",
"\n",
"# Optional: lower case the corpora - this will make it easier to generalize, but without proper casing.\n",
"if lc: # Julia: making lowercasing optional\n",
" df_pp[\"source_sentence\"] = df_pp[\"source_sentence\"].str.lower()\n",
" df_pp[\"target_sentence\"] = df_pp[\"target_sentence\"].str.lower()\n",
"\n",
"# Julia: test sets are already generated\n",
"dev = df_pp.tail(num_dev_patterns) # Herman: Error in original\n",
"stripped = df_pp.drop(df_pp.tail(num_dev_patterns).index)\n",
"\n",
"with open(\"train.\"+source_language, \"w\") as src_file, open(\"train.\"+target_language, \"w\") as trg_file:\n",
" for index, row in stripped.iterrows():\n",
" src_file.write(row[\"source_sentence\"]+\"\\n\")\n",
" trg_file.write(row[\"target_sentence\"]+\"\\n\")\n",
" \n",
"with open(\"dev.\"+source_language, \"w\") as src_file, open(\"dev.\"+target_language, \"w\") as trg_file:\n",
" for index, row in dev.iterrows():\n",
" src_file.write(row[\"source_sentence\"]+\"\\n\")\n",
" trg_file.write(row[\"target_sentence\"]+\"\\n\")\n",
"\n",
"#stripped[[\"source_sentence\"]].to_csv(\"train.\"+source_language, header=False, index=False) # Herman: Added `header=False` everywhere\n",
"#stripped[[\"target_sentence\"]].to_csv(\"train.\"+target_language, header=False, index=False) # Julia: Problematic handling of quotation marks.\n",
"\n",
"#dev[[\"source_sentence\"]].to_csv(\"dev.\"+source_language, header=False, index=False)\n",
"#dev[[\"target_sentence\"]].to_csv(\"dev.\"+target_language, header=False, index=False)\n",
"\n",
"# Doublecheck the format below. There should be no extra quotation marks or weird characters.\n",
"! head train.*\n",
"! head dev.*"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "epeCydmCyS8X"
},
"source": [
"\n",
"\n",
"---\n",
"\n",
"\n",
"## Installation of JoeyNMT\n",
"\n",
"JoeyNMT is a simple, minimalist NMT package which is useful for learning and teaching. Check out the documentation for JoeyNMT [here](https://joeynmt.readthedocs.io) "
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "iBRMm4kMxZ8L",
"outputId": "97a36759-3f50-4498-f54e-9d36cb35c9ab"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Cloning into 'joeynmt'...\n",
"remote: Enumerating objects: 3089, done.\u001b[K\n",
"remote: Counting objects: 100% (138/138), done.\u001b[K\n",
"remote: Compressing objects: 100% (65/65), done.\u001b[K\n",
"remote: Total 3089 (delta 78), reused 118 (delta 73), pack-reused 2951\u001b[K\n",
"Receiving objects: 100% (3089/3089), 8.07 MiB | 20.07 MiB/s, done.\n",
"Resolving deltas: 100% (2107/2107), done.\n",
"Processing /home/freshiasackey_gmail_com/joeynmt\n",
"Requirement already satisfied: future in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (0.18.2)\n",
"Requirement already satisfied: pillow in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (7.2.0)\n",
"Requirement already satisfied: numpy==1.20.1 in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (1.20.1)\n",
"Requirement already satisfied: setuptools>=41.0.0 in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (49.6.0.post20210108)\n",
"Requirement already satisfied: torch==1.8.0 in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (1.8.0)\n",
"Requirement already satisfied: tensorboard>=1.15 in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (2.5.0)\n",
"Requirement already satisfied: torchtext==0.9.0 in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (0.9.0)\n",
"Requirement already satisfied: sacrebleu>=1.3.6 in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (1.5.1)\n",
"Requirement already satisfied: subword-nmt in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (0.3.7)\n",
"Requirement already satisfied: matplotlib in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (3.4.1)\n",
"Requirement already satisfied: seaborn in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (0.11.1)\n",
"Requirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (5.4.1)\n",
"Requirement already satisfied: pylint in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (2.8.2)\n",
"Requirement already satisfied: six==1.12 in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (1.12.0)\n",
"Requirement already satisfied: wrapt==1.11.1 in /opt/conda/lib/python3.7/site-packages (from joeynmt==1.3) (1.11.1)\n",
"Requirement already satisfied: typing_extensions in /opt/conda/lib/python3.7/site-packages (from torch==1.8.0->joeynmt==1.3) (3.7.4.3)\n",
"Requirement already satisfied: tqdm in /opt/conda/lib/python3.7/site-packages (from torchtext==0.9.0->joeynmt==1.3) (4.60.0)\n",
"Requirement already satisfied: requests in /opt/conda/lib/python3.7/site-packages (from torchtext==0.9.0->joeynmt==1.3) (2.25.1)\n",
"Requirement already satisfied: portalocker==2.0.0 in /opt/conda/lib/python3.7/site-packages (from sacrebleu>=1.3.6->joeynmt==1.3) (2.0.0)\n",
"Requirement already satisfied: protobuf>=3.6.0 in /opt/conda/lib/python3.7/site-packages (from tensorboard>=1.15->joeynmt==1.3) (3.15.8)\n",
"Requirement already satisfied: wheel>=0.26 in /opt/conda/lib/python3.7/site-packages (from tensorboard>=1.15->joeynmt==1.3) (0.36.2)\n",
"Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /opt/conda/lib/python3.7/site-packages (from tensorboard>=1.15->joeynmt==1.3) (0.6.0)\n",
"Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /opt/conda/lib/python3.7/site-packages (from tensorboard>=1.15->joeynmt==1.3) (0.4.3)\n",
"Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /opt/conda/lib/python3.7/site-packages (from tensorboard>=1.15->joeynmt==1.3) (1.8.0)\n",
"Requirement already satisfied: google-auth<2,>=1.6.3 in /opt/conda/lib/python3.7/site-packages (from tensorboard>=1.15->joeynmt==1.3) (1.28.0)\n",
"Requirement already satisfied: absl-py>=0.4 in /opt/conda/lib/python3.7/site-packages (from tensorboard>=1.15->joeynmt==1.3) (0.12.0)\n",
"Requirement already satisfied: markdown>=2.6.8 in /opt/conda/lib/python3.7/site-packages (from tensorboard>=1.15->joeynmt==1.3) (3.3.4)\n",
"Requirement already satisfied: werkzeug>=0.11.15 in /opt/conda/lib/python3.7/site-packages (from tensorboard>=1.15->joeynmt==1.3) (1.0.1)\n",
"Requirement already satisfied: grpcio>=1.24.3 in /opt/conda/lib/python3.7/site-packages (from tensorboard>=1.15->joeynmt==1.3) (1.37.0)\n",
"Requirement already satisfied: rsa<5,>=3.1.4 in /opt/conda/lib/python3.7/site-packages (from google-auth<2,>=1.6.3->tensorboard>=1.15->joeynmt==1.3) (4.7.2)\n",
"Requirement already satisfied: cachetools<5.0,>=2.0.0 in /opt/conda/lib/python3.7/site-packages (from google-auth<2,>=1.6.3->tensorboard>=1.15->joeynmt==1.3) (4.2.1)\n",
"Requirement already satisfied: pyasn1-modules>=0.2.1 in /opt/conda/lib/python3.7/site-packages (from google-auth<2,>=1.6.3->tensorboard>=1.15->joeynmt==1.3) (0.2.7)\n",
"Requirement already satisfied: requests-oauthlib>=0.7.0 in /opt/conda/lib/python3.7/site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard>=1.15->joeynmt==1.3) (1.3.0)\n",
"Requirement already satisfied: importlib-metadata in /opt/conda/lib/python3.7/site-packages (from markdown>=2.6.8->tensorboard>=1.15->joeynmt==1.3) (3.10.1)\n",
"Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /opt/conda/lib/python3.7/site-packages (from pyasn1-modules>=0.2.1->google-auth<2,>=1.6.3->tensorboard>=1.15->joeynmt==1.3) (0.4.8)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.7/site-packages (from requests->torchtext==0.9.0->joeynmt==1.3) (2020.12.5)\n",
"Requirement already satisfied: chardet<5,>=3.0.2 in /opt/conda/lib/python3.7/site-packages (from requests->torchtext==0.9.0->joeynmt==1.3) (4.0.0)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /opt/conda/lib/python3.7/site-packages (from requests->torchtext==0.9.0->joeynmt==1.3) (1.26.4)\n",
"Requirement already satisfied: idna<3,>=2.5 in /opt/conda/lib/python3.7/site-packages (from requests->torchtext==0.9.0->joeynmt==1.3) (2.10)\n",
"Requirement already satisfied: oauthlib>=3.0.0 in /opt/conda/lib/python3.7/site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard>=1.15->joeynmt==1.3) (3.0.1)\n",
"Requirement already satisfied: zipp>=0.5 in /opt/conda/lib/python3.7/site-packages (from importlib-metadata->markdown>=2.6.8->tensorboard>=1.15->joeynmt==1.3) (3.4.1)\n",
"Requirement already satisfied: cycler>=0.10 in /opt/conda/lib/python3.7/site-packages (from matplotlib->joeynmt==1.3) (0.10.0)\n",
"Requirement already satisfied: python-dateutil>=2.7 in /opt/conda/lib/python3.7/site-packages (from matplotlib->joeynmt==1.3) (2.8.1)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in /opt/conda/lib/python3.7/site-packages (from matplotlib->joeynmt==1.3) (1.3.1)\n",
"Requirement already satisfied: pyparsing>=2.2.1 in /opt/conda/lib/python3.7/site-packages (from matplotlib->joeynmt==1.3) (2.4.7)\n",
"Requirement already satisfied: mccabe<0.7,>=0.6 in /opt/conda/lib/python3.7/site-packages (from pylint->joeynmt==1.3) (0.6.1)\n",
"Requirement already satisfied: toml>=0.7.1 in /opt/conda/lib/python3.7/site-packages (from pylint->joeynmt==1.3) (0.10.2)\n",
"Requirement already satisfied: isort<6,>=4.2.5 in /opt/conda/lib/python3.7/site-packages (from pylint->joeynmt==1.3) (5.8.0)\n",
"Requirement already satisfied: astroid<2.7,>=2.5.6 in /opt/conda/lib/python3.7/site-packages (from pylint->joeynmt==1.3) (2.5.6)\n",
"Requirement already satisfied: lazy-object-proxy>=1.4.0 in /opt/conda/lib/python3.7/site-packages (from astroid<2.7,>=2.5.6->pylint->joeynmt==1.3) (1.6.0)\n",
"Requirement already satisfied: typed-ast<1.5,>=1.4.0 in /opt/conda/lib/python3.7/site-packages (from astroid<2.7,>=2.5.6->pylint->joeynmt==1.3) (1.4.3)\n",
"Requirement already satisfied: pandas>=0.23 in /opt/conda/lib/python3.7/site-packages (from seaborn->joeynmt==1.3) (1.2.4)\n",
"Requirement already satisfied: scipy>=1.0 in /opt/conda/lib/python3.7/site-packages (from seaborn->joeynmt==1.3) (1.6.2)\n",
"Requirement already satisfied: pytz>=2017.3 in /opt/conda/lib/python3.7/site-packages (from pandas>=0.23->seaborn->joeynmt==1.3) (2021.1)\n",
"Building wheels for collected packages: joeynmt\n",
" Building wheel for joeynmt (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for joeynmt: filename=joeynmt-1.3-py3-none-any.whl size=84842 sha256=ef07bebe91da73788bfd625d9ea9f6c2d4e41abd48a82cee881ca4aae778845b\n",
" Stored in directory: /tmp/pip-ephem-wheel-cache-i4o_on4y/wheels/c6/e5/f6/9ca9cce28ddbc86321064c68c12df09503f033db723fa4548d\n",
"Successfully built joeynmt\n",
"Installing collected packages: joeynmt\n",
" Attempting uninstall: joeynmt\n",
" Found existing installation: joeynmt 1.3\n",
" Uninstalling joeynmt-1.3:\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" Successfully uninstalled joeynmt-1.3\n",
"Successfully installed joeynmt-1.3\n",
"Looking in links: https://download.pytorch.org/whl/torch_stable.html\n",
"Collecting torch==1.8.0+cu101\n",
" Downloading https://download.pytorch.org/whl/cu101/torch-1.8.0%2Bcu101-cp37-cp37m-linux_x86_64.whl (763.5 MB)\n",
"\u001b[K |████████████████████████████████| 763.5 MB 9.8 kB/s eta 0:00:012 |██████████████████▏ | 432.3 MB 7.8 MB/s eta 0:00:43 |███████████████████▊ | 469.5 MB 2.3 MB/s eta 0:02:09\n",
"\u001b[?25hRequirement already satisfied: typing-extensions in /opt/conda/lib/python3.7/site-packages (from torch==1.8.0+cu101) (3.7.4.3)\n",
"Requirement already satisfied: numpy in /opt/conda/lib/python3.7/site-packages (from torch==1.8.0+cu101) (1.20.1)\n",
"Installing collected packages: torch\n",
" Attempting uninstall: torch\n",
" Found existing installation: torch 1.8.0\n",
" Uninstalling torch-1.8.0:\n",
" Successfully uninstalled torch-1.8.0\n",
"Successfully installed torch-1.8.0+cu101\n"
]
}
],
"source": [
"# Install JoeyNMT\n",
"! git clone https://github.com/joeynmt/joeynmt.git\n",
"! cd joeynmt; pip3 install .\n",
"# Install Pytorch with GPU support v1.8.0\n",
"! pip install torch==1.8.0+cu101 -f https://download.pytorch.org/whl/torch_stable.html"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "AaE77Tcppex9"
},
"source": [
"# Preprocessing the Data into Subword BPE Tokens\n",
"\n",
"- One of the most powerful improvements for agglutinative languages (a feature of most Bantu languages) is using BPE tokenization [ (Sennrich, 2015) ](https://arxiv.org/abs/1508.07909).\n",
"\n",
"- It was also shown that by optimizing the umber of BPE codes we significantly improve results for low-resourced languages [(Sennrich, 2019)](https://www.aclweb.org/anthology/P19-1021) [(Martinus, 2019)](https://arxiv.org/abs/1906.05685)\n",
"\n",
"- Below we have the scripts for doing BPE tokenization of our data. We use 4000 tokens as recommended by [(Sennrich, 2019)](https://www.aclweb.org/anthology/P19-1021). You do not need to change anything. Simply running the below will be suitable. "
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 416
},
"id": "H-TyjtmXB1mL",
"outputId": "9867ad89-e5ec-4007-b952-d73a158ff5cf"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"bpe.codes.4000\tdev.en\t test.bpe.sw test.en-any.en.1 train.bpe.sw\n",
"dev.bpe.en\tdev.sw\t test.en\t test.sw\t train.en\n",
"dev.bpe.sw\ttest.bpe.en test.en-any.en train.bpe.en train.sw\n",
"cp: target '' is not a directory\n",
"cp: target '' is not a directory\n",
"cp: target '' is not a directory\n",
"cp: cannot create regular file '': No such file or directory\n",
"ls: cannot access '': No such file or directory\n",
"BPE Swahili Sentences\n",
"N@@ g@@ ao kubwa ya imani ( T@@ azama f@@ ungu la 12 hadi 14 )\n",
"K@@ of@@ ia ya chu@@ ma ya wo@@ ko@@ vu ( T@@ azama f@@ ungu la 15 hadi 18 )\n",
"N@@ im@@ et@@ ambua kwamba watu hu@@ it@@ ikia vizuri wanapo@@ ona uki@@ zungum@@ zia habari za Biblia kwa sha@@ uku na unapo@@ fanya yote una@@ yo@@ weza kuwasaidia . ”\n",
"Up@@ anga wa roho ( T@@ azama f@@ ungu la 19 na 20 )\n",
"Kwa msaada wa Yehova tunaweza kus@@ im@@ ama im@@ ara na kum@@ p@@ inga !\n",
"Combined BPE Vocab\n",
"с@@\n",
"ḥ\n",
"т@@\n",
"и\n",
"х@@\n",
"м\n",
"і@@\n",
"д@@\n",
"і\n",
"➊\n"
]
}
],
"source": [
"# One of the huge boosts in NMT performance was to use a different method of tokenizing. \n",
"# Usually, NMT would tokenize by words. However, using a method called BPE gave amazing boosts to performance\n",
"\n",
"# Do subword NMT\n",
"from os import path\n",
"os.environ[\"src\"] = source_language # Sets them in bash as well, since we often use bash scripts\n",
"os.environ[\"tgt\"] = target_language\n",
"\n",
"# Learn BPEs on the training data.\n",
"os.environ[\"data_path\"] = path.join(\"joeynmt\", \"data\",target_language + source_language ) # Herman! \n",
"! subword-nmt learn-joint-bpe-and-vocab --input train.$src train.$tgt -s 4000 -o bpe.codes.4000 --write-vocabulary vocab.$src vocab.$tgt\n",
"\n",
"# Apply BPE splits to the development and test data.\n",
"! subword-nmt apply-bpe -c bpe.codes.4000 --vocabulary vocab.$src < train.$src > train.bpe.$src\n",
"! subword-nmt apply-bpe -c bpe.codes.4000 --vocabulary vocab.$tgt < train.$tgt > train.bpe.$tgt\n",
"\n",
"! subword-nmt apply-bpe -c bpe.codes.4000 --vocabulary vocab.$src < dev.$src > dev.bpe.$src\n",
"! subword-nmt apply-bpe -c bpe.codes.4000 --vocabulary vocab.$tgt < dev.$tgt > dev.bpe.$tgt\n",
"! subword-nmt apply-bpe -c bpe.codes.4000 --vocabulary vocab.$src < test.$src > test.bpe.$src\n",
"! subword-nmt apply-bpe -c bpe.codes.4000 --vocabulary vocab.$tgt < test.$tgt > test.bpe.$tgt\n",
"\n",
"# Create directory, move everyone we care about to the correct location\n",
"! mkdir -p $data_path\n",
"! cp train.* $data_path\n",
"! cp test.* $data_path\n",
"! cp dev.* $data_path\n",
"! cp bpe.codes.4000 $data_path\n",
"! ls $data_path\n",
"\n",
"# Also move everything we care about to a mounted location in google drive (relevant if running in colab) at gdrive_path\n",
"! cp train.* \"$gdrive_path\"\n",
"! cp test.* \"$gdrive_path\"\n",
"! cp dev.* \"$gdrive_path\"\n",
"! cp bpe.codes.4000 \"$gdrive_path\"\n",
"! ls \"$gdrive_path\"\n",
"\n",
"# Create that vocab using build_vocab\n",
"! sudo chmod 777 joeynmt/scripts/build_vocab.py\n",
"! joeynmt/scripts/build_vocab.py joeynmt/data/$tgt$src/train.bpe.$src joeynmt/data/$tgt$src/train.bpe.$tgt --output_path joeynmt/data/$tgt$src/vocab.txt\n",
"\n",
"# Some output\n",
"! echo \"BPE Swahili Sentences\"\n",
"! tail -n 5 test.bpe.$tgt\n",
"! echo \"Combined BPE Vocab\"\n",
"! tail -n 10 joeynmt/data/$tgt$src/vocab.txt # Herman"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 69
},
"id": "IlMitUHR8Qy-",
"outputId": "1656a274-cddb-47a2-bf71-6f64c5ef8a24"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"bpe.codes.4000\tdev.en\t test.bpe.sw test.en-any.en.1 train.bpe.sw\n",
"dev.bpe.en\tdev.sw\t test.en\t test.sw\t train.en\n",
"dev.bpe.sw\ttest.bpe.en test.en-any.en train.bpe.en train.sw\n"
]
}
],
"source": [
"# Also move everything we care about to a mounted location in google drive (relevant if running in colab) at gdrive_path\n",
"! cp train.* \"$gdrive_path\"\n",
"! cp test.* \"$gdrive_path\"\n",
"! cp dev.* \"$gdrive_path\"\n",
"! cp bpe.codes.4000 \"$gdrive_path\"\n",
"! ls \"$gdrive_path\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Ixmzi60WsUZ8"
},
"source": [
"# Creating the JoeyNMT Config\n",
"\n",
"JoeyNMT requires a yaml config. We provide a template below. We've also set a number of defaults with it, that you may play with!\n",
"\n",
"- We used Transformer architecture \n",
"- We set our dropout to reasonably high: 0.3 (recommended in [(Sennrich, 2019)](https://www.aclweb.org/anthology/P19-1021))\n",
"\n",
"Things worth playing with:\n",
"- The batch size (also recommended to change for low-resourced languages)\n",
"- The number of epochs (we've set it at 30 just so it runs in about an hour, for testing purposes)\n",
"- The decoder options (beam_size, alpha)\n",
"- Evaluation metrics (BLEU versus Crhf4)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"id": "h8TMgv1p3L1z"
},
"outputs": [],
"source": [
"# This creates the config file for our JoeyNMT system. It might seem overwhelming so we've provided a couple of useful parameters you'll need to update\n",
"# (You can of course play with all the parameters if you'd like!)\n",
"\n",
"name = '%s%s' % (target_language, source_language)\n",
"# gdrive_path = os.environ[\"gdrive_path\"]\n",
"\n",
"# Create the config\n",
"config = \"\"\"\n",
"name: \"{target_language}{source_language}_reverse_transformer\"\n",
"\n",
"data:\n",
" src: \"{target_language}\"\n",
" trg: \"{source_language}\"\n",
" train: \"data/{name}/train.bpe\"\n",
" dev: \"data/{name}/dev.bpe\"\n",
" test: \"data/{name}/test.bpe\"\n",
" level: \"bpe\"\n",
" lowercase: False\n",
" max_sent_length: 100\n",
" src_vocab: \"data/{name}/vocab.txt\"\n",
" trg_vocab: \"data/{name}/vocab.txt\"\n",
"\n",
"testing:\n",
" beam_size: 5\n",
" alpha: 1.0\n",
"\n",
"training:\n",
" #load_model: \"{gdrive_path}/models/{name}_transformer/1.ckpt\" # if uncommented, load a pre-trained model from this checkpoint\n",
" random_seed: 42\n",
" optimizer: \"adam\"\n",
" normalization: \"tokens\"\n",
" adam_betas: [0.9, 0.999] \n",
" scheduling: \"plateau\" # TODO: try switching from plateau to Noam scheduling\n",
" patience: 5 # For plateau: decrease learning rate by decrease_factor if validation score has not improved for this many validation rounds.\n",
" learning_rate_factor: 0.5 # factor for Noam scheduler (used with Transformer)\n",
" learning_rate_warmup: 1000 # warmup steps for Noam scheduler (used with Transformer)\n",
" decrease_factor: 0.7\n",
" loss: \"crossentropy\"\n",
" learning_rate: 0.0003\n",
" learning_rate_min: 0.00000001\n",
" weight_decay: 0.0\n",
" label_smoothing: 0.1\n",
" batch_size: 4096\n",
" batch_type: \"token\"\n",
" eval_batch_size: 3600\n",
" eval_batch_type: \"token\"\n",
" batch_multiplier: 1\n",
" early_stopping_metric: \"ppl\"\n",
" epochs: 35 # TODO: Decrease for when playing around and checking of working. Around 30 is sufficient to check if its working at all\n",
" validation_freq: 1000 # TODO: Set to at least once per epoch.\n",
" logging_freq: 100\n",
" eval_metric: \"bleu\"\n",
" model_dir: \"models/{name}_reverse_transformer\"\n",
" overwrite: True # TODO: Set to True if you want to overwrite possibly existing models. \n",
" shuffle: True\n",
" use_cuda: True\n",
" max_output_length: 100\n",
" print_valid_sents: [0, 1, 2, 3]\n",
" keep_last_ckpts: 3\n",
"\n",
"model:\n",
" initializer: \"xavier\"\n",
" bias_initializer: \"zeros\"\n",
" init_gain: 1.0\n",
" embed_initializer: \"xavier\"\n",
" embed_init_gain: 1.0\n",
" tied_embeddings: True\n",
" tied_softmax: True\n",
" encoder:\n",
" type: \"transformer\"\n",
" num_layers: 6\n",
" num_heads: 4 # TODO: Increase to 8 for larger data.\n",
" embeddings:\n",
" embedding_dim: 256 # TODO: Increase to 512 for larger data.\n",
" scale: True\n",
" dropout: 0.2\n",
" # typically ff_size = 4 x hidden_size\n",
" hidden_size: 256 # TODO: Increase to 512 for larger data.\n",
" ff_size: 1024 # TODO: Increase to 2048 for larger data.\n",
" dropout: 0.3\n",
" decoder:\n",
" type: \"transformer\"\n",
" num_layers: 6\n",
" num_heads: 4 # TODO: Increase to 8 for larger data.\n",
" embeddings:\n",
" embedding_dim: 256 # TODO: Increase to 512 for larger data.\n",
" scale: True\n",
" dropout: 0.2\n",
" # typically ff_size = 4 x hidden_size\n",
" hidden_size: 256 # TODO: Increase to 512 for larger data.\n",
" ff_size: 1024 # TODO: Increase to 2048 for larger data.\n",
" dropout: 0.3\n",
"\"\"\"\n",
"with open(\"joeynmt/configs/transformer_reverse_{name}.yaml\".format(name=name),'w') as f:\n",
" f.write(config)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "oEzoJtV2MIpt"
},
"source": [
"# Train the Model\n",
"\n",
"This single line of joeynmt runs the training using the config we made above"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "WzbNYNdjLgNb",
"outputId": "cc18bde5-6226-4769-de84-5e5d27a6c5a8"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 12:05:13,638 - INFO - root - Hello! This is Joey-NMT (version 1.3).\n",
"2021-05-10 12:05:13,639 - INFO - joeynmt.data - Loading training data...\n",
"2021-05-10 12:05:33,860 - INFO - joeynmt.data - Building vocabulary...\n",
"2021-05-10 12:05:34,175 - INFO - joeynmt.data - Loading dev data...\n",
"2021-05-10 12:05:34,236 - INFO - joeynmt.data - Loading test data...\n",
"2021-05-10 12:05:34,322 - INFO - joeynmt.data - Data loaded.\n",
"2021-05-10 12:05:34,322 - INFO - joeynmt.model - Building an encoder-decoder model...\n",
"2021-05-10 12:05:34,569 - INFO - joeynmt.model - Enc-dec model built.\n",
"2021-05-10 12:05:34,577 - INFO - joeynmt.training - Total params: 12219392\n",
"2021-05-10 12:05:34,580 - INFO - joeynmt.helpers - cfg.name : {target_language}{source_language}_reverse_transformer\n",
"2021-05-10 12:05:34,580 - INFO - joeynmt.helpers - cfg.data.src : sw\n",
"2021-05-10 12:05:34,580 - INFO - joeynmt.helpers - cfg.data.trg : en\n",
"2021-05-10 12:05:34,580 - INFO - joeynmt.helpers - cfg.data.train : data/swen/train.bpe\n",
"2021-05-10 12:05:34,580 - INFO - joeynmt.helpers - cfg.data.dev : data/swen/dev.bpe\n",
"2021-05-10 12:05:34,580 - INFO - joeynmt.helpers - cfg.data.test : data/swen/test.bpe\n",
"2021-05-10 12:05:34,580 - INFO - joeynmt.helpers - cfg.data.level : bpe\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.data.lowercase : False\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.data.max_sent_length : 100\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.data.src_vocab : data/swen/vocab.txt\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.data.trg_vocab : data/swen/vocab.txt\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.testing.beam_size : 5\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.testing.alpha : 1.0\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.random_seed : 42\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.optimizer : adam\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.normalization : tokens\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.adam_betas : [0.9, 0.999]\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.scheduling : plateau\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.patience : 5\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.learning_rate_factor : 0.5\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.learning_rate_warmup : 1000\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.decrease_factor : 0.7\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.loss : crossentropy\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.learning_rate : 0.0003\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.learning_rate_min : 1e-08\n",
"2021-05-10 12:05:34,581 - INFO - joeynmt.helpers - cfg.training.weight_decay : 0.0\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.label_smoothing : 0.1\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.batch_size : 4096\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.batch_type : token\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.eval_batch_size : 3600\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.eval_batch_type : token\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.batch_multiplier : 1\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.early_stopping_metric : ppl\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.epochs : 35\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.validation_freq : 1000\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.logging_freq : 100\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.eval_metric : bleu\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.model_dir : models/swen_reverse_transformer\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.overwrite : True\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.shuffle : True\n",
"2021-05-10 12:05:34,582 - INFO - joeynmt.helpers - cfg.training.use_cuda : True\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.training.max_output_length : 100\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.training.print_valid_sents : [0, 1, 2, 3]\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.training.keep_last_ckpts : 3\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.initializer : xavier\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.bias_initializer : zeros\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.init_gain : 1.0\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.embed_initializer : xavier\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.embed_init_gain : 1.0\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.tied_embeddings : True\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.tied_softmax : True\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.encoder.type : transformer\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.encoder.num_layers : 6\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.encoder.num_heads : 4\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.encoder.embeddings.embedding_dim : 256\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.encoder.embeddings.scale : True\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.encoder.embeddings.dropout : 0.2\n",
"2021-05-10 12:05:34,583 - INFO - joeynmt.helpers - cfg.model.encoder.hidden_size : 256\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - cfg.model.encoder.ff_size : 1024\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - cfg.model.encoder.dropout : 0.3\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - cfg.model.decoder.type : transformer\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - cfg.model.decoder.num_layers : 6\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - cfg.model.decoder.num_heads : 4\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - cfg.model.decoder.embeddings.embedding_dim : 256\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - cfg.model.decoder.embeddings.scale : True\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - cfg.model.decoder.embeddings.dropout : 0.2\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - cfg.model.decoder.hidden_size : 256\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - cfg.model.decoder.ff_size : 1024\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - cfg.model.decoder.dropout : 0.3\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - Data set sizes: \n",
"\ttrain 873221,\n",
"\tvalid 1000,\n",
"\ttest 2721\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - First training example:\n",
"\t[SRC] Is@@ ito@@ she , kwa kuwa si@@ j@@ a@@ anzisha ur@@ afiki kama huo n@@ ina nafasi ya kufanya mambo mengi ya pekee !\n",
"\t[TRG] B@@ es@@ id@@ es , being sing@@ le gives one the opportun@@ ity to do so many great things !\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - First 10 words (src): (0) <unk> (1) <pad> (2) <s> (3) </s> (4) , (5) . (6) the (7) na (8) ya (9) to\n",
"2021-05-10 12:05:34,584 - INFO - joeynmt.helpers - First 10 words (trg): (0) <unk> (1) <pad> (2) <s> (3) </s> (4) , (5) . (6) the (7) na (8) ya (9) to\n",
"2021-05-10 12:05:34,585 - INFO - joeynmt.helpers - Number of Src words (types): 4528\n",
"2021-05-10 12:05:34,585 - INFO - joeynmt.helpers - Number of Trg words (types): 4528\n",
"2021-05-10 12:05:34,585 - INFO - joeynmt.training - Model(\n",
"\tencoder=TransformerEncoder(num_layers=6, num_heads=4),\n",
"\tdecoder=TransformerDecoder(num_layers=6, num_heads=4),\n",
"\tsrc_embed=Embeddings(embedding_dim=256, vocab_size=4528),\n",
"\ttrg_embed=Embeddings(embedding_dim=256, vocab_size=4528))\n",
"2021-05-10 12:05:34,589 - INFO - joeynmt.training - Train stats:\n",
"\tdevice: cpu\n",
"\tn_gpu: 0\n",
"\t16-bits training: False\n",
"\tgradient accumulation: 1\n",
"\tbatch size per device: 4096\n",
"\ttotal batch size (w. parallel & accumulation): 4096\n",
"2021-05-10 12:05:34,589 - INFO - joeynmt.training - EPOCH 1\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 12:07:14,714 - INFO - joeynmt.training - Epoch 1, Step: 100, Batch Loss: 5.824012, Tokens per Sec: 2461, Lr: 0.000300\n",
"2021-05-10 12:08:53,289 - INFO - joeynmt.training - Epoch 1, Step: 200, Batch Loss: 5.505569, Tokens per Sec: 2571, Lr: 0.000300\n",
"2021-05-10 12:10:31,850 - INFO - joeynmt.training - Epoch 1, Step: 300, Batch Loss: 5.457898, Tokens per Sec: 2620, Lr: 0.000300\n",
"2021-05-10 12:12:07,941 - INFO - joeynmt.training - Epoch 1, Step: 400, Batch Loss: 5.160206, Tokens per Sec: 2542, Lr: 0.000300\n",
"2021-05-10 12:13:44,283 - INFO - joeynmt.training - Epoch 1, Step: 500, Batch Loss: 5.064879, Tokens per Sec: 2604, Lr: 0.000300\n",
"2021-05-10 12:15:19,514 - INFO - joeynmt.training - Epoch 1, Step: 600, Batch Loss: 5.153046, Tokens per Sec: 2587, Lr: 0.000300\n",
"2021-05-10 12:16:57,236 - INFO - joeynmt.training - Epoch 1, Step: 700, Batch Loss: 4.622757, Tokens per Sec: 2603, Lr: 0.000300\n",
"2021-05-10 12:18:32,836 - INFO - joeynmt.training - Epoch 1, Step: 800, Batch Loss: 4.622123, Tokens per Sec: 2537, Lr: 0.000300\n",
"2021-05-10 12:21:44,480 - INFO - joeynmt.training - Epoch 1, Step: 1000, Batch Loss: 4.562954, Tokens per Sec: 2630, Lr: 0.000300\n",
"2021-05-10 12:25:39,140 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 12:25:39,141 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 12:25:39,141 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 12:25:39,392 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 12:25:39,392 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 12:25:39,697 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 12:25:39,697 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 12:25:39,697 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 12:25:39,697 - INFO - joeynmt.training - \tHypothesis: The year of the year of the year .\n",
"2021-05-10 12:25:39,697 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 12:25:39,697 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 12:25:39,697 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 12:25:39,697 - INFO - joeynmt.training - \tHypothesis: The Bible is the Bible of the Bible of the Bible of the Bible .\n",
"2021-05-10 12:25:39,697 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 12:25:39,697 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 12:25:39,698 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 12:25:39,698 - INFO - joeynmt.training - \tHypothesis: The Bible of the Bible , the Bible of the Bible , the Bible of the Bible , the Bible of the Bible of the Bible , the Bible of the Bible .\n",
"2021-05-10 12:25:39,698 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 12:25:39,698 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 12:25:39,698 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 12:25:39,698 - INFO - joeynmt.training - \tHypothesis: The Bible was a time of the Bible .\n",
"2021-05-10 12:25:39,698 - INFO - joeynmt.training - Validation result (greedy) at epoch 1, step 1000: bleu: 1.06, loss: 129890.1797, ppl: 92.6316, duration: 235.2171s\n",
"2021-05-10 12:27:15,979 - INFO - joeynmt.training - Epoch 1, Step: 1100, Batch Loss: 4.374075, Tokens per Sec: 2656, Lr: 0.000300\n",
"2021-05-10 12:28:52,823 - INFO - joeynmt.training - Epoch 1, Step: 1200, Batch Loss: 4.553164, Tokens per Sec: 2646, Lr: 0.000300\n",
"2021-05-10 12:30:20,386 - INFO - joeynmt.training - Epoch 1, Step: 1300, Batch Loss: 4.502044, Tokens per Sec: 2833, Lr: 0.000300\n",
"2021-05-10 12:31:48,780 - INFO - joeynmt.training - Epoch 1, Step: 1400, Batch Loss: 4.345503, Tokens per Sec: 2861, Lr: 0.000300\n",
"2021-05-10 12:33:17,365 - INFO - joeynmt.training - Epoch 1, Step: 1500, Batch Loss: 4.163601, Tokens per Sec: 2830, Lr: 0.000300\n",
"2021-05-10 12:34:44,243 - INFO - joeynmt.training - Epoch 1, Step: 1600, Batch Loss: 4.173061, Tokens per Sec: 2821, Lr: 0.000300\n",
"2021-05-10 12:36:10,735 - INFO - joeynmt.training - Epoch 1, Step: 1700, Batch Loss: 4.261605, Tokens per Sec: 2799, Lr: 0.000300\n",
"2021-05-10 12:37:38,804 - INFO - joeynmt.training - Epoch 1, Step: 1800, Batch Loss: 4.135508, Tokens per Sec: 2841, Lr: 0.000300\n",
"2021-05-10 12:39:06,062 - INFO - joeynmt.training - Epoch 1, Step: 1900, Batch Loss: 4.002204, Tokens per Sec: 2853, Lr: 0.000300\n",
"2021-05-10 12:40:33,729 - INFO - joeynmt.training - Epoch 1, Step: 2000, Batch Loss: 4.081915, Tokens per Sec: 2874, Lr: 0.000300\n",
"2021-05-10 12:44:26,202 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 12:44:26,202 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 12:44:26,202 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 12:44:26,490 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 12:44:26,491 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 12:44:26,689 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 12:44:26,689 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 12:44:26,690 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 12:44:26,690 - INFO - joeynmt.training - \tHypothesis: In 196th century of the United States .\n",
"2021-05-10 12:44:26,690 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 12:44:26,690 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 12:44:26,690 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 12:44:26,690 - INFO - joeynmt.training - \tHypothesis: The Bible will be a Bible that we have been a Bible will be a Bible and the Bible and the Bible and his name .\n",
"2021-05-10 12:44:26,690 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 12:44:26,690 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 12:44:26,690 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 12:44:26,690 - INFO - joeynmt.training - \tHypothesis: The Shal of the Shaocer , the Cran , the Cran , the Cranch of the Cranh , the Cren’s , the sleep of the world .\n",
"2021-05-10 12:44:26,690 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 12:44:26,691 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 12:44:26,691 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 12:44:26,691 - INFO - joeynmt.training - \tHypothesis: The source of the sleep and the sleep .\n",
"2021-05-10 12:44:26,691 - INFO - joeynmt.training - Validation result (greedy) at epoch 1, step 2000: bleu: 1.91, loss: 110982.6562, ppl: 47.9145, duration: 232.9610s\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 12:45:54,109 - INFO - joeynmt.training - Epoch 1, Step: 2100, Batch Loss: 4.114491, Tokens per Sec: 2871, Lr: 0.000300\n",
"2021-05-10 12:47:21,622 - INFO - joeynmt.training - Epoch 1, Step: 2200, Batch Loss: 3.484627, Tokens per Sec: 2874, Lr: 0.000300\n",
"2021-05-10 12:50:18,393 - INFO - joeynmt.training - Epoch 1, Step: 2400, Batch Loss: 3.704122, Tokens per Sec: 2867, Lr: 0.000300\n",
"2021-05-10 12:51:45,707 - INFO - joeynmt.training - Epoch 1, Step: 2500, Batch Loss: 3.647293, Tokens per Sec: 2794, Lr: 0.000300\n",
"2021-05-10 12:53:14,079 - INFO - joeynmt.training - Epoch 1, Step: 2600, Batch Loss: 3.703819, Tokens per Sec: 2880, Lr: 0.000300\n",
"2021-05-10 12:54:38,979 - INFO - joeynmt.training - Epoch 1, Step: 2700, Batch Loss: 3.674768, Tokens per Sec: 2973, Lr: 0.000300\n",
"2021-05-10 12:56:04,201 - INFO - joeynmt.training - Epoch 1, Step: 2800, Batch Loss: 3.530214, Tokens per Sec: 2920, Lr: 0.000300\n",
"2021-05-10 12:57:32,161 - INFO - joeynmt.training - Epoch 1, Step: 2900, Batch Loss: 3.656303, Tokens per Sec: 2791, Lr: 0.000300\n",
"2021-05-10 12:59:01,675 - INFO - joeynmt.training - Epoch 1, Step: 3000, Batch Loss: 3.622418, Tokens per Sec: 2793, Lr: 0.000300\n",
"2021-05-10 13:02:05,468 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 13:02:05,468 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 13:02:05,469 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 13:02:05,752 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 13:02:05,753 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 13:02:05,959 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 13:02:05,959 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 13:02:05,959 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 13:02:05,959 - INFO - joeynmt.training - \tHypothesis: In 1990 years of the year were in the United States .\n",
"2021-05-10 13:02:05,959 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - \tHypothesis: The Bible will be a person that he was a Bible and the Bible and his promises .\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - \tHypothesis: The Church in the United States , the Church is a , as a Church , the Church , the South of the Church , the most of their figergy , they were not to be a source of their own .\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - \tHypothesis: The pain of the people and the people .\n",
"2021-05-10 13:02:05,960 - INFO - joeynmt.training - Validation result (greedy) at epoch 1, step 3000: bleu: 4.24, loss: 98905.2969, ppl: 31.4482, duration: 184.2848s\n",
"2021-05-10 13:03:34,761 - INFO - joeynmt.training - Epoch 1, Step: 3100, Batch Loss: 3.201812, Tokens per Sec: 2843, Lr: 0.000300\n",
"2021-05-10 13:05:03,222 - INFO - joeynmt.training - Epoch 1, Step: 3200, Batch Loss: 3.633333, Tokens per Sec: 2815, Lr: 0.000300\n",
"2021-05-10 13:06:31,416 - INFO - joeynmt.training - Epoch 1, Step: 3300, Batch Loss: 3.959035, Tokens per Sec: 2791, Lr: 0.000300\n",
"2021-05-10 13:08:00,386 - INFO - joeynmt.training - Epoch 1, Step: 3400, Batch Loss: 3.108100, Tokens per Sec: 2865, Lr: 0.000300\n",
"2021-05-10 13:09:29,731 - INFO - joeynmt.training - Epoch 1, Step: 3500, Batch Loss: 3.613675, Tokens per Sec: 2847, Lr: 0.000300\n",
"2021-05-10 13:10:58,629 - INFO - joeynmt.training - Epoch 1, Step: 3600, Batch Loss: 3.363529, Tokens per Sec: 2867, Lr: 0.000300\n",
"2021-05-10 13:12:27,535 - INFO - joeynmt.training - Epoch 1, Step: 3700, Batch Loss: 3.335052, Tokens per Sec: 2833, Lr: 0.000300\n",
"2021-05-10 13:15:22,756 - INFO - joeynmt.training - Epoch 1, Step: 3900, Batch Loss: 3.351516, Tokens per Sec: 2842, Lr: 0.000300\n",
"2021-05-10 13:16:51,232 - INFO - joeynmt.training - Epoch 1, Step: 4000, Batch Loss: 3.097704, Tokens per Sec: 2866, Lr: 0.000300\n",
"2021-05-10 13:19:04,549 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 13:19:04,549 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 13:19:04,549 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 13:19:04,817 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 13:19:04,817 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 13:19:05,031 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tHypothesis: In 1997 the two two two two were in the city .\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tHypothesis: We will be able to know what the Bible is to be a good news and his own own .\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tHypothesis: The city of the city in the city of South , which is a city of the Europe , as the Europe of the Europe , the city of the swwwwd , and they were to take their own own .\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 13:19:05,032 - INFO - joeynmt.training - \tHypothesis: The refuge of the people and have been reached .\n",
"2021-05-10 13:19:05,033 - INFO - joeynmt.training - Validation result (greedy) at epoch 1, step 4000: bleu: 7.61, loss: 90962.1953, ppl: 23.8409, duration: 133.8001s\n",
"2021-05-10 13:20:34,939 - INFO - joeynmt.training - Epoch 1, Step: 4100, Batch Loss: 3.672779, Tokens per Sec: 2852, Lr: 0.000300\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 13:22:02,438 - INFO - joeynmt.training - Epoch 1, Step: 4200, Batch Loss: 2.996407, Tokens per Sec: 2813, Lr: 0.000300\n",
"2021-05-10 13:23:29,382 - INFO - joeynmt.training - Epoch 1, Step: 4300, Batch Loss: 3.099476, Tokens per Sec: 2794, Lr: 0.000300\n",
"2021-05-10 13:26:24,939 - INFO - joeynmt.training - Epoch 1, Step: 4500, Batch Loss: 3.238181, Tokens per Sec: 2824, Lr: 0.000300\n",
"2021-05-10 13:27:52,748 - INFO - joeynmt.training - Epoch 1, Step: 4600, Batch Loss: 3.237501, Tokens per Sec: 2835, Lr: 0.000300\n",
"2021-05-10 13:29:20,644 - INFO - joeynmt.training - Epoch 1, Step: 4700, Batch Loss: 3.250057, Tokens per Sec: 2844, Lr: 0.000300\n",
"2021-05-10 13:30:48,449 - INFO - joeynmt.training - Epoch 1, Step: 4800, Batch Loss: 3.238878, Tokens per Sec: 2818, Lr: 0.000300\n",
"2021-05-10 13:32:16,912 - INFO - joeynmt.training - Epoch 1, Step: 4900, Batch Loss: 2.947474, Tokens per Sec: 2826, Lr: 0.000300\n",
"2021-05-10 13:33:46,017 - INFO - joeynmt.training - Epoch 1, Step: 5000, Batch Loss: 3.065637, Tokens per Sec: 2805, Lr: 0.000300\n",
"2021-05-10 13:36:16,599 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 13:36:16,599 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 13:36:16,599 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 13:36:16,880 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 13:36:16,880 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 13:36:17,098 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 13:36:17,098 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 13:36:17,098 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 13:36:17,098 - INFO - joeynmt.training - \tHypothesis: In 1997 the year of the age of the 30,000 girls were found in the Britain .\n",
"2021-05-10 13:36:17,098 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 13:36:17,098 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 13:36:17,098 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 13:36:17,098 - INFO - joeynmt.training - \tHypothesis: It is not to know what the Bible is to know what the purpose of his purpose and his heart .\n",
"2021-05-10 13:36:17,098 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 13:36:17,098 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 13:36:17,098 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 13:36:17,099 - INFO - joeynmt.training - \tHypothesis: The arrital of the city of Syyran , which is the city of Europe of Europe , as the Europe of the Great , the art of the sleaves , and they were able to be reached their own .\n",
"2021-05-10 13:36:17,099 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 13:36:17,099 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 13:36:17,099 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 13:36:17,099 - INFO - joeynmt.training - \tHypothesis: The most of the most seven and many .\n",
"2021-05-10 13:36:17,099 - INFO - joeynmt.training - Validation result (greedy) at epoch 1, step 5000: bleu: 9.73, loss: 84097.4766, ppl: 18.7663, duration: 151.0815s\n",
"2021-05-10 13:37:46,166 - INFO - joeynmt.training - Epoch 1, Step: 5100, Batch Loss: 3.480074, Tokens per Sec: 2819, Lr: 0.000300\n",
"2021-05-10 13:39:13,693 - INFO - joeynmt.training - Epoch 1, Step: 5200, Batch Loss: 3.152671, Tokens per Sec: 2823, Lr: 0.000300\n",
"2021-05-10 13:40:41,526 - INFO - joeynmt.training - Epoch 1, Step: 5300, Batch Loss: 2.737840, Tokens per Sec: 2798, Lr: 0.000300\n",
"2021-05-10 13:42:10,236 - INFO - joeynmt.training - Epoch 1, Step: 5400, Batch Loss: 3.052401, Tokens per Sec: 2857, Lr: 0.000300\n",
"2021-05-10 13:43:39,203 - INFO - joeynmt.training - Epoch 1, Step: 5500, Batch Loss: 2.959814, Tokens per Sec: 2858, Lr: 0.000300\n",
"2021-05-10 13:45:07,252 - INFO - joeynmt.training - Epoch 1, Step: 5600, Batch Loss: 3.237727, Tokens per Sec: 2867, Lr: 0.000300\n",
"2021-05-10 13:46:35,422 - INFO - joeynmt.training - Epoch 1, Step: 5700, Batch Loss: 2.970789, Tokens per Sec: 2898, Lr: 0.000300\n",
"2021-05-10 13:48:02,824 - INFO - joeynmt.training - Epoch 1, Step: 5800, Batch Loss: 3.036379, Tokens per Sec: 2788, Lr: 0.000300\n",
"2021-05-10 13:49:32,111 - INFO - joeynmt.training - Epoch 1, Step: 5900, Batch Loss: 3.152328, Tokens per Sec: 2867, Lr: 0.000300\n",
"2021-05-10 13:51:00,682 - INFO - joeynmt.training - Epoch 1, Step: 6000, Batch Loss: 2.889906, Tokens per Sec: 2837, Lr: 0.000300\n",
"2021-05-10 13:54:30,791 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 13:54:30,791 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 13:54:30,791 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 13:54:31,068 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 13:54:31,068 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 13:54:31,280 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tHypothesis: In 1997 a year - year girls were returned in Britain .\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tHypothesis: It is not to know what the Bible does not give the purpose of his own and his own .\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tHypothesis: The city of Sydddddddddddddddy , which is the Europe of Europe of the Europe of the Messiah , the rejected to their own putes .\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 13:54:31,281 - INFO - joeynmt.training - \tHypothesis: The most of the seven and often .\n",
"2021-05-10 13:54:31,282 - INFO - joeynmt.training - Validation result (greedy) at epoch 1, step 6000: bleu: 11.24, loss: 79250.9609, ppl: 15.8487, duration: 210.5988s\n",
"2021-05-10 13:55:59,226 - INFO - joeynmt.training - Epoch 1, Step: 6100, Batch Loss: 2.726814, Tokens per Sec: 2877, Lr: 0.000300\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 13:57:27,905 - INFO - joeynmt.training - Epoch 1, Step: 6200, Batch Loss: 2.735085, Tokens per Sec: 2882, Lr: 0.000300\n",
"2021-05-10 13:58:55,655 - INFO - joeynmt.training - Epoch 1, Step: 6300, Batch Loss: 2.721830, Tokens per Sec: 2781, Lr: 0.000300\n",
"2021-05-10 14:00:25,340 - INFO - joeynmt.training - Epoch 1, Step: 6400, Batch Loss: 2.639565, Tokens per Sec: 2802, Lr: 0.000300\n",
"2021-05-10 14:01:53,724 - INFO - joeynmt.training - Epoch 1, Step: 6500, Batch Loss: 3.123513, Tokens per Sec: 2798, Lr: 0.000300\n",
"2021-05-10 14:03:22,714 - INFO - joeynmt.training - Epoch 1, Step: 6600, Batch Loss: 2.939059, Tokens per Sec: 2823, Lr: 0.000300\n",
"2021-05-10 14:04:51,919 - INFO - joeynmt.training - Epoch 1, Step: 6700, Batch Loss: 2.742112, Tokens per Sec: 2842, Lr: 0.000300\n",
"2021-05-10 14:06:21,332 - INFO - joeynmt.training - Epoch 1, Step: 6800, Batch Loss: 3.273561, Tokens per Sec: 2886, Lr: 0.000300\n",
"2021-05-10 14:07:50,202 - INFO - joeynmt.training - Epoch 1, Step: 6900, Batch Loss: 2.880594, Tokens per Sec: 2897, Lr: 0.000300\n",
"2021-05-10 14:09:18,899 - INFO - joeynmt.training - Epoch 1, Step: 7000, Batch Loss: 3.233414, Tokens per Sec: 2860, Lr: 0.000300\n",
"2021-05-10 14:11:39,966 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 14:11:39,966 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 14:11:39,966 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 14:11:40,241 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 14:11:40,241 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 14:11:40,455 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 14:11:40,455 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 14:11:40,455 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 14:11:40,455 - INFO - joeynmt.training - \tHypothesis: In 1997 a 90,000 girls were in Britain .\n",
"2021-05-10 14:11:40,455 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - \tHypothesis: It is not to know what the Bible says the right of his own purpose and his heart .\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - \tHypothesis: The city of Syllerg , which is a part of Europe of Europe , as the Europe of the Europe of the Europe , who returned to the sleep of their paper .\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - \tHypothesis: The most of the most and many of the seven .\n",
"2021-05-10 14:11:40,456 - INFO - joeynmt.training - Validation result (greedy) at epoch 1, step 7000: bleu: 14.56, loss: 75467.2188, ppl: 13.8900, duration: 141.5573s\n",
"2021-05-10 14:13:08,847 - INFO - joeynmt.training - Epoch 1, Step: 7100, Batch Loss: 2.824364, Tokens per Sec: 2834, Lr: 0.000300\n",
"2021-05-10 14:14:38,142 - INFO - joeynmt.training - Epoch 1, Step: 7200, Batch Loss: 2.770475, Tokens per Sec: 2837, Lr: 0.000300\n",
"2021-05-10 14:16:03,753 - INFO - joeynmt.training - Epoch 1, Step: 7300, Batch Loss: 2.589112, Tokens per Sec: 2922, Lr: 0.000300\n",
"2021-05-10 14:17:28,026 - INFO - joeynmt.training - Epoch 1, Step: 7400, Batch Loss: 3.010032, Tokens per Sec: 3030, Lr: 0.000300\n",
"2021-05-10 14:18:52,780 - INFO - joeynmt.training - Epoch 1, Step: 7500, Batch Loss: 2.712847, Tokens per Sec: 2955, Lr: 0.000300\n",
"2021-05-10 14:20:21,534 - INFO - joeynmt.training - Epoch 1, Step: 7600, Batch Loss: 2.793720, Tokens per Sec: 2886, Lr: 0.000300\n",
"2021-05-10 14:21:49,718 - INFO - joeynmt.training - Epoch 1, Step: 7700, Batch Loss: 2.680154, Tokens per Sec: 2874, Lr: 0.000300\n",
"2021-05-10 14:23:16,269 - INFO - joeynmt.training - Epoch 1, Step: 7800, Batch Loss: 2.449150, Tokens per Sec: 2816, Lr: 0.000300\n",
"2021-05-10 14:24:46,025 - INFO - joeynmt.training - Epoch 1, Step: 7900, Batch Loss: 2.619170, Tokens per Sec: 2859, Lr: 0.000300\n",
"2021-05-10 14:26:13,974 - INFO - joeynmt.training - Epoch 1, Step: 8000, Batch Loss: 2.975786, Tokens per Sec: 2801, Lr: 0.000300\n",
"2021-05-10 14:28:39,473 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 14:28:39,473 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 14:28:39,474 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 14:28:39,745 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 14:28:39,745 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 14:28:39,960 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 14:28:39,960 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 14:28:39,960 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 14:28:39,960 - INFO - joeynmt.training - \tHypothesis: In 1997 the girls were found in Britain .\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - \tHypothesis: It is not to know what he did not know the Bible to do the purpose of him and to support his heart .\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - \tHypothesis: The main of the city in Sang , which is the Japanese African African , as the Europe of the Without of the human Hiberia , the process of the bank of their head .\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - \tHypothesis: Explain and many deeds .\n",
"2021-05-10 14:28:39,961 - INFO - joeynmt.training - Validation result (greedy) at epoch 1, step 8000: bleu: 16.10, loss: 72340.8125, ppl: 12.4556, duration: 145.9870s\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 14:30:08,639 - INFO - joeynmt.training - Epoch 1, Step: 8100, Batch Loss: 2.968779, Tokens per Sec: 2873, Lr: 0.000300\n",
"2021-05-10 14:31:37,651 - INFO - joeynmt.training - Epoch 1, Step: 8200, Batch Loss: 2.754746, Tokens per Sec: 2891, Lr: 0.000300\n",
"2021-05-10 14:33:06,065 - INFO - joeynmt.training - Epoch 1, Step: 8300, Batch Loss: 2.761967, Tokens per Sec: 2803, Lr: 0.000300\n",
"2021-05-10 14:34:32,892 - INFO - joeynmt.training - Epoch 1, Step: 8400, Batch Loss: 2.588269, Tokens per Sec: 2832, Lr: 0.000300\n",
"2021-05-10 14:35:59,909 - INFO - joeynmt.training - Epoch 1, Step: 8500, Batch Loss: 2.817042, Tokens per Sec: 2794, Lr: 0.000300\n",
"2021-05-10 14:37:27,611 - INFO - joeynmt.training - Epoch 1, Step: 8600, Batch Loss: 2.819373, Tokens per Sec: 2837, Lr: 0.000300\n",
"2021-05-10 14:38:55,587 - INFO - joeynmt.training - Epoch 1, Step: 8700, Batch Loss: 2.464084, Tokens per Sec: 2885, Lr: 0.000300\n",
"2021-05-10 14:40:22,589 - INFO - joeynmt.training - Epoch 1, Step: 8800, Batch Loss: 2.556808, Tokens per Sec: 2890, Lr: 0.000300\n",
"2021-05-10 14:41:51,488 - INFO - joeynmt.training - Epoch 1, Step: 8900, Batch Loss: 2.726137, Tokens per Sec: 2857, Lr: 0.000300\n",
"2021-05-10 14:43:18,468 - INFO - joeynmt.training - Epoch 1, Step: 9000, Batch Loss: 2.456280, Tokens per Sec: 2796, Lr: 0.000300\n",
"2021-05-10 14:46:08,948 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 14:46:08,948 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 14:46:08,948 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 14:46:09,219 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 14:46:09,220 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 14:46:09,434 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 14:46:09,434 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 14:46:09,434 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 14:46:09,434 - INFO - joeynmt.training - \tHypothesis: In 1997 a 90,000 girls found in England .\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - \tHypothesis: It is not necessary to know what the Bible does not give him a purpose and support his own .\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - \tHypothesis: The major of the city in Sweddg , which is the African African of the European African , the rejected the sleep to find their cope .\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - \tHypothesis: Regarding the most sight and many stims .\n",
"2021-05-10 14:46:09,435 - INFO - joeynmt.training - Validation result (greedy) at epoch 1, step 9000: bleu: 17.35, loss: 69847.0703, ppl: 11.4184, duration: 170.9666s\n",
"2021-05-10 14:47:37,866 - INFO - joeynmt.training - Epoch 1, Step: 9100, Batch Loss: 2.603883, Tokens per Sec: 2818, Lr: 0.000300\n",
"2021-05-10 14:49:05,107 - INFO - joeynmt.training - Epoch 1, Step: 9200, Batch Loss: 2.455597, Tokens per Sec: 2793, Lr: 0.000300\n",
"2021-05-10 14:50:31,955 - INFO - joeynmt.training - Epoch 1, Step: 9300, Batch Loss: 2.480252, Tokens per Sec: 2832, Lr: 0.000300\n",
"2021-05-10 14:52:00,087 - INFO - joeynmt.training - Epoch 1, Step: 9400, Batch Loss: 3.095553, Tokens per Sec: 2828, Lr: 0.000300\n",
"2021-05-10 14:53:27,841 - INFO - joeynmt.training - Epoch 1, Step: 9500, Batch Loss: 2.538290, Tokens per Sec: 2862, Lr: 0.000300\n",
"2021-05-10 14:54:56,418 - INFO - joeynmt.training - Epoch 1, Step: 9600, Batch Loss: 2.212147, Tokens per Sec: 2854, Lr: 0.000300\n",
"2021-05-10 14:56:24,308 - INFO - joeynmt.training - Epoch 1, Step: 9700, Batch Loss: 2.546114, Tokens per Sec: 2843, Lr: 0.000300\n",
"2021-05-10 14:57:52,008 - INFO - joeynmt.training - Epoch 1, Step: 9800, Batch Loss: 2.591657, Tokens per Sec: 2845, Lr: 0.000300\n",
"2021-05-10 14:57:58,465 - INFO - joeynmt.training - Epoch 1: total training loss 33437.65\n",
"2021-05-10 14:57:58,465 - INFO - joeynmt.training - EPOCH 2\n",
"2021-05-10 14:59:21,986 - INFO - joeynmt.training - Epoch 2, Step: 9900, Batch Loss: 2.833395, Tokens per Sec: 2753, Lr: 0.000300\n",
"2021-05-10 15:00:49,888 - INFO - joeynmt.training - Epoch 2, Step: 10000, Batch Loss: 3.190526, Tokens per Sec: 2788, Lr: 0.000300\n",
"2021-05-10 15:03:36,352 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 15:03:36,352 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 15:03:36,352 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 15:03:36,627 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 15:03:36,627 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 15:03:36,909 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - \tHypothesis: In 1997 the girls found in England .\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - \tHypothesis: It is wise to tell him what the Bible does not give him to be a personal purpose and support to him .\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - \tHypothesis: The chief in Strtrang , which is the headquarters of the European European African Empire , they returned to the philosophy to their copies .\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 15:03:36,910 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 15:03:36,911 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 15:03:36,911 - INFO - joeynmt.training - \tHypothesis: Remember , it is many susputes and many .\n",
"2021-05-10 15:03:36,911 - INFO - joeynmt.training - Validation result (greedy) at epoch 2, step 10000: bleu: 18.33, loss: 67433.7500, ppl: 10.4969, duration: 167.0217s\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 15:05:06,882 - INFO - joeynmt.training - Epoch 2, Step: 10100, Batch Loss: 2.488953, Tokens per Sec: 2826, Lr: 0.000300\n",
"2021-05-10 15:06:34,363 - INFO - joeynmt.training - Epoch 2, Step: 10200, Batch Loss: 2.318348, Tokens per Sec: 2865, Lr: 0.000300\n",
"2021-05-10 15:08:02,181 - INFO - joeynmt.training - Epoch 2, Step: 10300, Batch Loss: 2.836575, Tokens per Sec: 2819, Lr: 0.000300\n",
"2021-05-10 15:09:30,532 - INFO - joeynmt.training - Epoch 2, Step: 10400, Batch Loss: 2.896009, Tokens per Sec: 2831, Lr: 0.000300\n",
"2021-05-10 15:10:59,365 - INFO - joeynmt.training - Epoch 2, Step: 10500, Batch Loss: 2.383335, Tokens per Sec: 2843, Lr: 0.000300\n",
"2021-05-10 15:12:27,112 - INFO - joeynmt.training - Epoch 2, Step: 10600, Batch Loss: 2.260209, Tokens per Sec: 2839, Lr: 0.000300\n",
"2021-05-10 15:13:55,346 - INFO - joeynmt.training - Epoch 2, Step: 10700, Batch Loss: 2.334218, Tokens per Sec: 2861, Lr: 0.000300\n",
"2021-05-10 15:15:24,312 - INFO - joeynmt.training - Epoch 2, Step: 10800, Batch Loss: 2.322378, Tokens per Sec: 2834, Lr: 0.000300\n",
"2021-05-10 15:16:52,043 - INFO - joeynmt.training - Epoch 2, Step: 10900, Batch Loss: 2.467571, Tokens per Sec: 2859, Lr: 0.000300\n",
"2021-05-10 15:18:19,948 - INFO - joeynmt.training - Epoch 2, Step: 11000, Batch Loss: 2.245156, Tokens per Sec: 2850, Lr: 0.000300\n",
"2021-05-10 15:20:43,292 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 15:20:43,292 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 15:20:43,293 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 15:20:43,562 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 15:20:43,562 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 15:20:43,775 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 15:20:43,775 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 15:20:43,775 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 15:20:43,775 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found in Britain .\n",
"2021-05-10 15:20:43,775 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - \tHypothesis: It is to know what the Bible does not be able to be satisfied by his suffering .\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - \tHypothesis: The main statement in the city of Straskg , which is the headquarters of Europe as the Europe of Human Hiberia , the traveling the car to find their copy .\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - \tHypothesis: Remember the most and many snakes .\n",
"2021-05-10 15:20:43,776 - INFO - joeynmt.training - Validation result (greedy) at epoch 2, step 11000: bleu: 20.09, loss: 65427.5938, ppl: 9.7878, duration: 143.8283s\n",
"2021-05-10 15:22:12,435 - INFO - joeynmt.training - Epoch 2, Step: 11100, Batch Loss: 2.718374, Tokens per Sec: 2868, Lr: 0.000300\n",
"2021-05-10 15:23:41,694 - INFO - joeynmt.training - Epoch 2, Step: 11200, Batch Loss: 2.804248, Tokens per Sec: 2851, Lr: 0.000300\n",
"2021-05-10 15:25:10,117 - INFO - joeynmt.training - Epoch 2, Step: 11300, Batch Loss: 2.421386, Tokens per Sec: 2777, Lr: 0.000300\n",
"2021-05-10 15:26:38,795 - INFO - joeynmt.training - Epoch 2, Step: 11400, Batch Loss: 2.607991, Tokens per Sec: 2847, Lr: 0.000300\n",
"2021-05-10 15:28:07,104 - INFO - joeynmt.training - Epoch 2, Step: 11500, Batch Loss: 2.418192, Tokens per Sec: 2840, Lr: 0.000300\n",
"2021-05-10 15:29:34,190 - INFO - joeynmt.training - Epoch 2, Step: 11600, Batch Loss: 2.103862, Tokens per Sec: 2794, Lr: 0.000300\n",
"2021-05-10 15:31:04,670 - INFO - joeynmt.training - Epoch 2, Step: 11700, Batch Loss: 2.689956, Tokens per Sec: 2789, Lr: 0.000300\n",
"2021-05-10 15:32:35,154 - INFO - joeynmt.training - Epoch 2, Step: 11800, Batch Loss: 2.534465, Tokens per Sec: 2737, Lr: 0.000300\n",
"2021-05-10 15:34:04,194 - INFO - joeynmt.training - Epoch 2, Step: 11900, Batch Loss: 2.762211, Tokens per Sec: 2842, Lr: 0.000300\n",
"2021-05-10 15:35:32,880 - INFO - joeynmt.training - Epoch 2, Step: 12000, Batch Loss: 2.664960, Tokens per Sec: 2834, Lr: 0.000300\n",
"2021-05-10 15:38:04,341 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 15:38:04,341 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 15:38:04,341 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 15:38:04,611 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 15:38:04,611 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 15:38:04,827 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 15:38:04,827 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 15:38:04,827 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 15:38:04,827 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found in England .\n",
"2021-05-10 15:38:04,827 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 15:38:04,827 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 15:38:04,827 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 15:38:04,827 - INFO - joeynmt.training - \tHypothesis: It is not to tell him what the Bible does not understand what the purpose is to be satisfied by his suffering .\n",
"2021-05-10 15:38:04,827 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 15:38:04,828 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 15:38:04,828 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 15:38:04,828 - INFO - joeynmt.training - \tHypothesis: The main provision in the city of Straskourg , which is the home of the European European European Egyptian , traveling the branch office to find their copies .\n",
"2021-05-10 15:38:04,828 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 15:38:04,828 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 15:38:04,828 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 15:38:04,828 - INFO - joeynmt.training - \tHypothesis: Remember and many global .\n",
"2021-05-10 15:38:04,828 - INFO - joeynmt.training - Validation result (greedy) at epoch 2, step 12000: bleu: 20.97, loss: 63807.8203, ppl: 9.2504, duration: 151.9473s\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 15:39:33,410 - INFO - joeynmt.training - Epoch 2, Step: 12100, Batch Loss: 2.577723, Tokens per Sec: 2830, Lr: 0.000300\n",
"2021-05-10 15:41:01,376 - INFO - joeynmt.training - Epoch 2, Step: 12200, Batch Loss: 2.754146, Tokens per Sec: 2821, Lr: 0.000300\n",
"2021-05-10 15:42:30,303 - INFO - joeynmt.training - Epoch 2, Step: 12300, Batch Loss: 2.252576, Tokens per Sec: 2756, Lr: 0.000300\n",
"2021-05-10 15:45:30,749 - INFO - joeynmt.training - Epoch 2, Step: 12500, Batch Loss: 2.649587, Tokens per Sec: 2761, Lr: 0.000300\n",
"2021-05-10 15:46:58,825 - INFO - joeynmt.training - Epoch 2, Step: 12600, Batch Loss: 2.472306, Tokens per Sec: 2825, Lr: 0.000300\n",
"2021-05-10 15:48:27,559 - INFO - joeynmt.training - Epoch 2, Step: 12700, Batch Loss: 2.329885, Tokens per Sec: 2807, Lr: 0.000300\n",
"2021-05-10 15:49:54,806 - INFO - joeynmt.training - Epoch 2, Step: 12800, Batch Loss: 2.543615, Tokens per Sec: 2880, Lr: 0.000300\n",
"2021-05-10 15:51:22,837 - INFO - joeynmt.training - Epoch 2, Step: 12900, Batch Loss: 2.080272, Tokens per Sec: 2884, Lr: 0.000300\n",
"2021-05-10 15:52:50,526 - INFO - joeynmt.training - Epoch 2, Step: 13000, Batch Loss: 2.337162, Tokens per Sec: 2832, Lr: 0.000300\n",
"2021-05-10 15:54:59,833 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 15:54:59,833 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 15:54:59,833 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 15:55:00,103 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 15:55:00,103 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 15:55:00,323 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found in England .\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - \tHypothesis: The wisdom must have to know what the Bible does not be able to be supported by his support .\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - \tHypothesis: The main source in the city of Strasbourg , which is the home of the European Empire , traveling the room to find their copy .\n",
"2021-05-10 15:55:00,324 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 15:55:00,325 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 15:55:00,325 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 15:55:00,325 - INFO - joeynmt.training - \tHypothesis: Remember the most and the global .\n",
"2021-05-10 15:55:00,325 - INFO - joeynmt.training - Validation result (greedy) at epoch 2, step 13000: bleu: 21.96, loss: 62265.4727, ppl: 8.7661, duration: 129.7984s\n",
"2021-05-10 15:56:28,716 - INFO - joeynmt.training - Epoch 2, Step: 13100, Batch Loss: 2.274951, Tokens per Sec: 2856, Lr: 0.000300\n",
"2021-05-10 15:57:55,581 - INFO - joeynmt.training - Epoch 2, Step: 13200, Batch Loss: 2.450541, Tokens per Sec: 2881, Lr: 0.000300\n",
"2021-05-10 15:59:22,906 - INFO - joeynmt.training - Epoch 2, Step: 13300, Batch Loss: 2.340995, Tokens per Sec: 2854, Lr: 0.000300\n",
"2021-05-10 16:00:49,584 - INFO - joeynmt.training - Epoch 2, Step: 13400, Batch Loss: 2.622322, Tokens per Sec: 2860, Lr: 0.000300\n",
"2021-05-10 16:02:17,038 - INFO - joeynmt.training - Epoch 2, Step: 13500, Batch Loss: 2.419177, Tokens per Sec: 2798, Lr: 0.000300\n",
"2021-05-10 16:03:44,857 - INFO - joeynmt.training - Epoch 2, Step: 13600, Batch Loss: 2.278650, Tokens per Sec: 2827, Lr: 0.000300\n",
"2021-05-10 16:06:40,473 - INFO - joeynmt.training - Epoch 2, Step: 13800, Batch Loss: 2.539600, Tokens per Sec: 2853, Lr: 0.000300\n",
"2021-05-10 16:08:07,836 - INFO - joeynmt.training - Epoch 2, Step: 13900, Batch Loss: 2.500989, Tokens per Sec: 2913, Lr: 0.000300\n",
"2021-05-10 16:09:35,796 - INFO - joeynmt.training - Epoch 2, Step: 14000, Batch Loss: 2.492006, Tokens per Sec: 2889, Lr: 0.000300\n",
"2021-05-10 16:11:46,710 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 16:11:46,711 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 16:11:46,711 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 16:11:46,978 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 16:11:46,978 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 16:11:47,193 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 16:11:47,193 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 16:11:47,193 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 16:11:47,193 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found the village in Britain .\n",
"2021-05-10 16:11:47,193 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 16:11:47,193 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 16:11:47,193 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 16:11:47,193 - INFO - joeynmt.training - \tHypothesis: He must have to know what the Bible does not be able to be supported by his support .\n",
"2021-05-10 16:11:47,193 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 16:11:47,193 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 16:11:47,193 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 16:11:47,194 - INFO - joeynmt.training - \tHypothesis: The main process in the city of Strasbourg , which is the North of Human Earth , traveling the cities to prevent their copy .\n",
"2021-05-10 16:11:47,194 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 16:11:47,194 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 16:11:47,194 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 16:11:47,194 - INFO - joeynmt.training - \tHypothesis: Remember the most and many disasters .\n",
"2021-05-10 16:11:47,194 - INFO - joeynmt.training - Validation result (greedy) at epoch 2, step 14000: bleu: 22.92, loss: 60852.6367, ppl: 8.3447, duration: 131.3972s\n",
"2021-05-10 16:13:14,425 - INFO - joeynmt.training - Epoch 2, Step: 14100, Batch Loss: 2.560148, Tokens per Sec: 2873, Lr: 0.000300\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 16:14:42,256 - INFO - joeynmt.training - Epoch 2, Step: 14200, Batch Loss: 2.448101, Tokens per Sec: 2893, Lr: 0.000300\n",
"2021-05-10 16:16:09,749 - INFO - joeynmt.training - Epoch 2, Step: 14300, Batch Loss: 2.667431, Tokens per Sec: 2778, Lr: 0.000300\n",
"2021-05-10 16:17:37,716 - INFO - joeynmt.training - Epoch 2, Step: 14400, Batch Loss: 2.711628, Tokens per Sec: 2855, Lr: 0.000300\n",
"2021-05-10 16:19:05,637 - INFO - joeynmt.training - Epoch 2, Step: 14500, Batch Loss: 2.636516, Tokens per Sec: 2828, Lr: 0.000300\n",
"2021-05-10 16:20:32,133 - INFO - joeynmt.training - Epoch 2, Step: 14600, Batch Loss: 2.328991, Tokens per Sec: 2846, Lr: 0.000300\n",
"2021-05-10 16:23:28,431 - INFO - joeynmt.training - Epoch 2, Step: 14800, Batch Loss: 2.399189, Tokens per Sec: 2859, Lr: 0.000300\n",
"2021-05-10 16:24:57,288 - INFO - joeynmt.training - Epoch 2, Step: 14900, Batch Loss: 2.430764, Tokens per Sec: 2848, Lr: 0.000300\n",
"2021-05-10 16:26:25,022 - INFO - joeynmt.training - Epoch 2, Step: 15000, Batch Loss: 2.095859, Tokens per Sec: 2831, Lr: 0.000300\n",
"2021-05-10 16:28:39,402 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 16:28:39,403 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 16:28:39,403 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 16:28:39,671 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 16:28:39,672 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 16:28:39,887 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found in England .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tHypothesis: He must have to know what the Bible does not be satisfied by his support .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tHypothesis: The chief in Strasbourg , which is the Attttalian Empire of Human Everyal European Empire , traveling to the cost of their copies .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - \tHypothesis: Remember the most and many diseases .\n",
"2021-05-10 16:28:39,888 - INFO - joeynmt.training - Validation result (greedy) at epoch 2, step 15000: bleu: 23.56, loss: 59718.6797, ppl: 8.0213, duration: 134.8659s\n",
"2021-05-10 16:30:05,941 - INFO - joeynmt.training - Epoch 2, Step: 15100, Batch Loss: 2.266094, Tokens per Sec: 2854, Lr: 0.000300\n",
"2021-05-10 16:31:34,194 - INFO - joeynmt.training - Epoch 2, Step: 15200, Batch Loss: 2.239600, Tokens per Sec: 2892, Lr: 0.000300\n",
"2021-05-10 16:33:02,664 - INFO - joeynmt.training - Epoch 2, Step: 15300, Batch Loss: 2.434514, Tokens per Sec: 2833, Lr: 0.000300\n",
"2021-05-10 16:34:30,637 - INFO - joeynmt.training - Epoch 2, Step: 15400, Batch Loss: 2.177247, Tokens per Sec: 2840, Lr: 0.000300\n",
"2021-05-10 16:35:59,152 - INFO - joeynmt.training - Epoch 2, Step: 15500, Batch Loss: 2.103582, Tokens per Sec: 2836, Lr: 0.000300\n",
"2021-05-10 16:37:29,214 - INFO - joeynmt.training - Epoch 2, Step: 15600, Batch Loss: 2.441991, Tokens per Sec: 2850, Lr: 0.000300\n",
"2021-05-10 16:38:56,462 - INFO - joeynmt.training - Epoch 2, Step: 15700, Batch Loss: 2.284941, Tokens per Sec: 2816, Lr: 0.000300\n",
"2021-05-10 16:40:22,745 - INFO - joeynmt.training - Epoch 2, Step: 15800, Batch Loss: 2.363835, Tokens per Sec: 2843, Lr: 0.000300\n",
"2021-05-10 16:41:49,011 - INFO - joeynmt.training - Epoch 2, Step: 15900, Batch Loss: 2.183062, Tokens per Sec: 2849, Lr: 0.000300\n",
"2021-05-10 16:45:28,244 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 16:45:28,244 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 16:45:28,244 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 16:45:28,518 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 16:45:28,518 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 16:45:28,733 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 16:45:28,733 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 16:45:28,733 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 16:45:28,733 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found a room in England .\n",
"2021-05-10 16:45:28,733 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 16:45:28,733 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 16:45:28,733 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 16:45:28,733 - INFO - joeynmt.training - \tHypothesis: You must have to know what the Bible does not be removed by his support .\n",
"2021-05-10 16:45:28,733 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 16:45:28,733 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 16:45:28,733 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 16:45:28,734 - INFO - joeynmt.training - \tHypothesis: The main stories in the Strasbourg , which is the headquarters of Human Empire , traveling the philosophy to find their copy .\n",
"2021-05-10 16:45:28,734 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 16:45:28,734 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 16:45:28,734 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 16:45:28,734 - INFO - joeynmt.training - \tHypothesis: Remember the many gardens and many garden .\n",
"2021-05-10 16:45:28,734 - INFO - joeynmt.training - Validation result (greedy) at epoch 2, step 16000: bleu: 23.75, loss: 58571.9453, ppl: 7.7069, duration: 131.5635s\n",
"2021-05-10 16:46:56,038 - INFO - joeynmt.training - Epoch 2, Step: 16100, Batch Loss: 2.302176, Tokens per Sec: 2874, Lr: 0.000300\n",
"2021-05-10 16:48:24,825 - INFO - joeynmt.training - Epoch 2, Step: 16200, Batch Loss: 2.276431, Tokens per Sec: 2817, Lr: 0.000300\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 16:49:51,930 - INFO - joeynmt.training - Epoch 2, Step: 16300, Batch Loss: 2.335480, Tokens per Sec: 2950, Lr: 0.000300\n",
"2021-05-10 16:51:19,529 - INFO - joeynmt.training - Epoch 2, Step: 16400, Batch Loss: 2.371825, Tokens per Sec: 2872, Lr: 0.000300\n",
"2021-05-10 16:52:47,261 - INFO - joeynmt.training - Epoch 2, Step: 16500, Batch Loss: 2.606483, Tokens per Sec: 2936, Lr: 0.000300\n",
"2021-05-10 16:54:14,152 - INFO - joeynmt.training - Epoch 2, Step: 16600, Batch Loss: 2.476956, Tokens per Sec: 2838, Lr: 0.000300\n",
"2021-05-10 16:55:42,195 - INFO - joeynmt.training - Epoch 2, Step: 16700, Batch Loss: 2.273109, Tokens per Sec: 2872, Lr: 0.000300\n",
"2021-05-10 16:57:09,085 - INFO - joeynmt.training - Epoch 2, Step: 16800, Batch Loss: 2.470606, Tokens per Sec: 2869, Lr: 0.000300\n",
"2021-05-10 16:58:35,336 - INFO - joeynmt.training - Epoch 2, Step: 16900, Batch Loss: 2.239506, Tokens per Sec: 2818, Lr: 0.000300\n",
"2021-05-10 17:00:03,333 - INFO - joeynmt.training - Epoch 2, Step: 17000, Batch Loss: 2.247704, Tokens per Sec: 2860, Lr: 0.000300\n",
"2021-05-10 17:02:11,842 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 17:02:11,842 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 17:02:11,842 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 17:02:12,110 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 17:02:12,110 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 17:02:12,325 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found a room in Britain .\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - \tHypothesis: He must have to know what the Bible says is not to be intensed by his support .\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - \tHypothesis: The main statement in the Strasbourg , which is the Strasbourg of the European Empire , traveling the philosophy to prevent their copy .\n",
"2021-05-10 17:02:12,326 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 17:02:12,327 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 17:02:12,327 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 17:02:12,327 - INFO - joeynmt.training - \tHypothesis: Remember the most and the garden .\n",
"2021-05-10 17:02:12,327 - INFO - joeynmt.training - Validation result (greedy) at epoch 2, step 17000: bleu: 24.84, loss: 57695.2266, ppl: 7.4749, duration: 128.9931s\n",
"2021-05-10 17:03:39,036 - INFO - joeynmt.training - Epoch 2, Step: 17100, Batch Loss: 1.949176, Tokens per Sec: 2899, Lr: 0.000300\n",
"2021-05-10 17:05:05,646 - INFO - joeynmt.training - Epoch 2, Step: 17200, Batch Loss: 2.030777, Tokens per Sec: 2879, Lr: 0.000300\n",
"2021-05-10 17:06:32,176 - INFO - joeynmt.training - Epoch 2, Step: 17300, Batch Loss: 2.125240, Tokens per Sec: 2926, Lr: 0.000300\n",
"2021-05-10 17:07:58,502 - INFO - joeynmt.training - Epoch 2, Step: 17400, Batch Loss: 2.137732, Tokens per Sec: 2883, Lr: 0.000300\n",
"2021-05-10 17:09:26,339 - INFO - joeynmt.training - Epoch 2, Step: 17500, Batch Loss: 2.221572, Tokens per Sec: 2884, Lr: 0.000300\n",
"2021-05-10 17:10:53,583 - INFO - joeynmt.training - Epoch 2, Step: 17600, Batch Loss: 2.523746, Tokens per Sec: 2848, Lr: 0.000300\n",
"2021-05-10 17:15:17,676 - INFO - joeynmt.training - Epoch 2, Step: 17900, Batch Loss: 2.180850, Tokens per Sec: 2890, Lr: 0.000300\n",
"2021-05-10 17:16:44,157 - INFO - joeynmt.training - Epoch 2, Step: 18000, Batch Loss: 2.076793, Tokens per Sec: 2882, Lr: 0.000300\n",
"2021-05-10 17:18:57,613 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 17:18:57,613 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 17:18:57,614 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 17:18:57,880 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 17:18:57,881 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 17:18:58,094 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 17:18:58,094 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 17:18:58,094 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 17:18:58,094 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found room in England .\n",
"2021-05-10 17:18:58,094 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 17:18:58,094 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 17:18:58,094 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 17:18:58,094 - INFO - joeynmt.training - \tHypothesis: You must have to know what the Bible does not be removed by his support .\n",
"2021-05-10 17:18:58,094 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 17:18:58,094 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 17:18:58,094 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 17:18:58,095 - INFO - joeynmt.training - \tHypothesis: The main center in the city of Strasbourg , which is the Atttecular European Earth , traveling the traveling of the catch to prevent their copies .\n",
"2021-05-10 17:18:58,095 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 17:18:58,095 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 17:18:58,095 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 17:18:58,095 - INFO - joeynmt.training - \tHypothesis: Remember the most and discreet .\n",
"2021-05-10 17:18:58,095 - INFO - joeynmt.training - Validation result (greedy) at epoch 2, step 18000: bleu: 25.14, loss: 56873.7656, ppl: 7.2638, duration: 133.9372s\n",
"2021-05-10 17:20:24,511 - INFO - joeynmt.training - Epoch 2, Step: 18100, Batch Loss: 2.152098, Tokens per Sec: 2841, Lr: 0.000300\n",
"2021-05-10 17:21:50,812 - INFO - joeynmt.training - Epoch 2, Step: 18200, Batch Loss: 2.139853, Tokens per Sec: 2891, Lr: 0.000300\n",
"2021-05-10 17:23:19,087 - INFO - joeynmt.training - Epoch 2, Step: 18300, Batch Loss: 2.258672, Tokens per Sec: 2930, Lr: 0.000300\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 17:24:47,373 - INFO - joeynmt.training - Epoch 2, Step: 18400, Batch Loss: 2.140292, Tokens per Sec: 2894, Lr: 0.000300\n",
"2021-05-10 17:26:15,494 - INFO - joeynmt.training - Epoch 2, Step: 18500, Batch Loss: 2.206281, Tokens per Sec: 2896, Lr: 0.000300\n",
"2021-05-10 17:27:40,942 - INFO - joeynmt.training - Epoch 2, Step: 18600, Batch Loss: 2.277930, Tokens per Sec: 2827, Lr: 0.000300\n",
"2021-05-10 17:29:06,849 - INFO - joeynmt.training - Epoch 2, Step: 18700, Batch Loss: 2.116841, Tokens per Sec: 2892, Lr: 0.000300\n",
"2021-05-10 17:30:35,663 - INFO - joeynmt.training - Epoch 2, Step: 18800, Batch Loss: 2.076362, Tokens per Sec: 2846, Lr: 0.000300\n",
"2021-05-10 17:32:03,173 - INFO - joeynmt.training - Epoch 2, Step: 18900, Batch Loss: 2.053634, Tokens per Sec: 2866, Lr: 0.000300\n",
"2021-05-10 17:33:30,952 - INFO - joeynmt.training - Epoch 2, Step: 19000, Batch Loss: 2.275691, Tokens per Sec: 2897, Lr: 0.000300\n",
"2021-05-10 17:35:38,865 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 17:35:38,866 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 17:35:38,866 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 17:35:39,133 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 17:35:39,134 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 17:35:39,348 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found a room in England .\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tHypothesis: You must have to know what the Bible says to the purpose of his support .\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tHypothesis: At the main center in the city of Strasbourg , which is the home of the European Earth , the travelers arranged to prevent their copies .\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 17:35:39,349 - INFO - joeynmt.training - \tHypothesis: Remember the most and disaster .\n",
"2021-05-10 17:35:39,350 - INFO - joeynmt.training - Validation result (greedy) at epoch 2, step 19000: bleu: 25.92, loss: 55897.6758, ppl: 7.0208, duration: 128.3968s\n",
"2021-05-10 17:37:06,138 - INFO - joeynmt.training - Epoch 2, Step: 19100, Batch Loss: 2.810566, Tokens per Sec: 2927, Lr: 0.000300\n",
"2021-05-10 17:38:33,979 - INFO - joeynmt.training - Epoch 2, Step: 19200, Batch Loss: 2.189923, Tokens per Sec: 2885, Lr: 0.000300\n",
"2021-05-10 17:40:00,161 - INFO - joeynmt.training - Epoch 2, Step: 19300, Batch Loss: 2.141145, Tokens per Sec: 2877, Lr: 0.000300\n",
"2021-05-10 17:41:27,555 - INFO - joeynmt.training - Epoch 2, Step: 19400, Batch Loss: 2.023566, Tokens per Sec: 2906, Lr: 0.000300\n",
"2021-05-10 17:42:54,143 - INFO - joeynmt.training - Epoch 2, Step: 19500, Batch Loss: 2.116561, Tokens per Sec: 2875, Lr: 0.000300\n",
"2021-05-10 17:44:20,606 - INFO - joeynmt.training - Epoch 2, Step: 19600, Batch Loss: 2.195735, Tokens per Sec: 2904, Lr: 0.000300\n",
"2021-05-10 17:44:29,698 - INFO - joeynmt.training - Epoch 2: total training loss 23096.25\n",
"2021-05-10 17:44:29,698 - INFO - joeynmt.training - EPOCH 3\n",
"2021-05-10 17:45:49,613 - INFO - joeynmt.training - Epoch 3, Step: 19700, Batch Loss: 2.022207, Tokens per Sec: 2840, Lr: 0.000300\n",
"2021-05-10 17:47:19,247 - INFO - joeynmt.training - Epoch 3, Step: 19800, Batch Loss: 2.395367, Tokens per Sec: 2829, Lr: 0.000300\n",
"2021-05-10 17:48:48,192 - INFO - joeynmt.training - Epoch 3, Step: 19900, Batch Loss: 2.234133, Tokens per Sec: 2889, Lr: 0.000300\n",
"2021-05-10 17:50:14,263 - INFO - joeynmt.training - Epoch 3, Step: 20000, Batch Loss: 2.041868, Tokens per Sec: 2825, Lr: 0.000300\n",
"2021-05-10 17:52:25,177 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 17:52:25,178 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 17:52:25,178 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 17:52:25,443 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 17:52:25,443 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 17:52:25,656 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found a room in England .\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - \tHypothesis: You must have to know what the Bible says to be convinced and support to him .\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - \tHypothesis: At the main center in the city of Strasbourg , which is the Art of Human Earth , the travelers arranged to prevent their copy .\n",
"2021-05-10 17:52:25,657 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 17:52:25,658 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 17:52:25,658 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 17:52:25,658 - INFO - joeynmt.training - \tHypothesis: Remember the most and discreet .\n",
"2021-05-10 17:52:25,658 - INFO - joeynmt.training - Validation result (greedy) at epoch 3, step 20000: bleu: 26.10, loss: 55378.2656, ppl: 6.8948, duration: 131.3945s\n",
"2021-05-10 17:53:52,081 - INFO - joeynmt.training - Epoch 3, Step: 20100, Batch Loss: 2.382305, Tokens per Sec: 2905, Lr: 0.000300\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 17:55:19,466 - INFO - joeynmt.training - Epoch 3, Step: 20200, Batch Loss: 2.271461, Tokens per Sec: 2915, Lr: 0.000300\n",
"2021-05-10 17:56:47,625 - INFO - joeynmt.training - Epoch 3, Step: 20300, Batch Loss: 2.046909, Tokens per Sec: 2876, Lr: 0.000300\n",
"2021-05-10 17:58:14,182 - INFO - joeynmt.training - Epoch 3, Step: 20400, Batch Loss: 2.206532, Tokens per Sec: 2864, Lr: 0.000300\n",
"2021-05-10 17:59:41,190 - INFO - joeynmt.training - Epoch 3, Step: 20500, Batch Loss: 2.080265, Tokens per Sec: 2907, Lr: 0.000300\n",
"2021-05-10 18:01:09,133 - INFO - joeynmt.training - Epoch 3, Step: 20600, Batch Loss: 2.179455, Tokens per Sec: 2891, Lr: 0.000300\n",
"2021-05-10 18:02:36,323 - INFO - joeynmt.training - Epoch 3, Step: 20700, Batch Loss: 2.198697, Tokens per Sec: 2881, Lr: 0.000300\n",
"2021-05-10 18:04:04,127 - INFO - joeynmt.training - Epoch 3, Step: 20800, Batch Loss: 2.115926, Tokens per Sec: 2858, Lr: 0.000300\n",
"2021-05-10 18:05:30,260 - INFO - joeynmt.training - Epoch 3, Step: 20900, Batch Loss: 2.086459, Tokens per Sec: 2882, Lr: 0.000300\n",
"2021-05-10 18:07:00,744 - INFO - joeynmt.training - Epoch 3, Step: 21000, Batch Loss: 2.107676, Tokens per Sec: 2659, Lr: 0.000300\n",
"2021-05-10 18:09:41,202 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 18:09:41,203 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 18:09:41,203 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 18:09:41,470 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 18:09:41,471 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 18:09:41,682 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found the room in England .\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - \tHypothesis: You must have to know what the Bible says to be removed by his support .\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - \tHypothesis: At the main center in the city of Strasbourg , which is the European Court of Human Rights , the travelers arranged to produce their copy .\n",
"2021-05-10 18:09:41,683 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 18:09:41,684 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 18:09:41,684 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 18:09:41,684 - INFO - joeynmt.training - \tHypothesis: Remember the most and discreet .\n",
"2021-05-10 18:09:41,684 - INFO - joeynmt.training - Validation result (greedy) at epoch 3, step 21000: bleu: 26.24, loss: 55252.9492, ppl: 6.8647, duration: 160.9396s\n",
"2021-05-10 18:11:09,026 - INFO - joeynmt.training - Epoch 3, Step: 21100, Batch Loss: 1.908183, Tokens per Sec: 2904, Lr: 0.000300\n",
"2021-05-10 18:12:36,192 - INFO - joeynmt.training - Epoch 3, Step: 21200, Batch Loss: 2.253291, Tokens per Sec: 2901, Lr: 0.000300\n",
"2021-05-10 18:14:03,734 - INFO - joeynmt.training - Epoch 3, Step: 21300, Batch Loss: 2.119918, Tokens per Sec: 2896, Lr: 0.000300\n",
"2021-05-10 18:15:30,836 - INFO - joeynmt.training - Epoch 3, Step: 21400, Batch Loss: 1.739385, Tokens per Sec: 2875, Lr: 0.000300\n",
"2021-05-10 18:16:59,084 - INFO - joeynmt.training - Epoch 3, Step: 21500, Batch Loss: 2.232154, Tokens per Sec: 2892, Lr: 0.000300\n",
"2021-05-10 18:18:25,922 - INFO - joeynmt.training - Epoch 3, Step: 21600, Batch Loss: 2.261061, Tokens per Sec: 2901, Lr: 0.000300\n",
"2021-05-10 18:19:53,332 - INFO - joeynmt.training - Epoch 3, Step: 21700, Batch Loss: 2.158993, Tokens per Sec: 2851, Lr: 0.000300\n",
"2021-05-10 18:21:24,054 - INFO - joeynmt.training - Epoch 3, Step: 21800, Batch Loss: 2.268159, Tokens per Sec: 2785, Lr: 0.000300\n",
"2021-05-10 18:22:51,171 - INFO - joeynmt.training - Epoch 3, Step: 21900, Batch Loss: 2.183103, Tokens per Sec: 2904, Lr: 0.000300\n",
"2021-05-10 18:24:16,550 - INFO - joeynmt.training - Epoch 3, Step: 22000, Batch Loss: 2.112784, Tokens per Sec: 2837, Lr: 0.000300\n",
"2021-05-10 18:26:15,849 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 18:26:15,849 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 18:26:15,849 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 18:26:16,113 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 18:26:16,113 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 18:26:16,328 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 18:26:16,328 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 18:26:16,328 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 18:26:16,328 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found in England .\n",
"2021-05-10 18:26:16,328 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 18:26:16,328 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 18:26:16,328 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 18:26:16,328 - INFO - joeynmt.training - \tHypothesis: You must have to know what the Bible does not be convinced and support of him .\n",
"2021-05-10 18:26:16,328 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 18:26:16,329 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 18:26:16,329 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 18:26:16,329 - INFO - joeynmt.training - \tHypothesis: At the main center in the city of Strasbourg , which is the European homes of Human High , travelers arranged to predict their copy .\n",
"2021-05-10 18:26:16,329 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 18:26:16,329 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 18:26:16,329 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 18:26:16,329 - INFO - joeynmt.training - \tHypothesis: Remember the most and discreet .\n",
"2021-05-10 18:26:16,329 - INFO - joeynmt.training - Validation result (greedy) at epoch 3, step 22000: bleu: 26.95, loss: 54241.4805, ppl: 6.6269, duration: 119.7793s\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 18:27:42,816 - INFO - joeynmt.training - Epoch 3, Step: 22100, Batch Loss: 2.179298, Tokens per Sec: 2884, Lr: 0.000300\n",
"2021-05-10 18:29:09,642 - INFO - joeynmt.training - Epoch 3, Step: 22200, Batch Loss: 1.911644, Tokens per Sec: 2919, Lr: 0.000300\n",
"2021-05-10 18:30:36,544 - INFO - joeynmt.training - Epoch 3, Step: 22300, Batch Loss: 2.098760, Tokens per Sec: 2874, Lr: 0.000300\n",
"2021-05-10 18:32:02,872 - INFO - joeynmt.training - Epoch 3, Step: 22400, Batch Loss: 2.001364, Tokens per Sec: 2844, Lr: 0.000300\n",
"2021-05-10 18:33:29,896 - INFO - joeynmt.training - Epoch 3, Step: 22500, Batch Loss: 1.917742, Tokens per Sec: 2880, Lr: 0.000300\n",
"2021-05-10 18:34:56,473 - INFO - joeynmt.training - Epoch 3, Step: 22600, Batch Loss: 1.971986, Tokens per Sec: 2844, Lr: 0.000300\n",
"2021-05-10 18:36:24,135 - INFO - joeynmt.training - Epoch 3, Step: 22700, Batch Loss: 2.091261, Tokens per Sec: 2924, Lr: 0.000300\n",
"2021-05-10 18:37:51,747 - INFO - joeynmt.training - Epoch 3, Step: 22800, Batch Loss: 2.165265, Tokens per Sec: 2887, Lr: 0.000300\n",
"2021-05-10 18:39:17,249 - INFO - joeynmt.training - Epoch 3, Step: 22900, Batch Loss: 1.974013, Tokens per Sec: 2896, Lr: 0.000300\n",
"2021-05-10 18:40:44,745 - INFO - joeynmt.training - Epoch 3, Step: 23000, Batch Loss: 2.112074, Tokens per Sec: 2881, Lr: 0.000300\n",
"2021-05-10 18:42:45,172 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 18:42:45,172 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 18:42:45,172 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 18:42:45,436 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 18:42:45,436 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 18:42:45,648 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 18:42:45,648 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 18:42:45,648 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 18:42:45,648 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found a room in Britain .\n",
"2021-05-10 18:42:45,648 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 18:42:45,648 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 18:42:45,648 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 18:42:45,648 - INFO - joeynmt.training - \tHypothesis: You must have to know what the Bible says to be convinced and support to him .\n",
"2021-05-10 18:42:45,649 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 18:42:45,649 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 18:42:45,649 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 18:42:45,649 - INFO - joeynmt.training - \tHypothesis: At the main station in the city of Strasbourg , which is the Earth of Human Earth , the travelers arranged to prevent their copy .\n",
"2021-05-10 18:42:45,649 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 18:42:45,649 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 18:42:45,649 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 18:42:45,649 - INFO - joeynmt.training - \tHypothesis: Remember the most and discreet .\n",
"2021-05-10 18:42:45,649 - INFO - joeynmt.training - Validation result (greedy) at epoch 3, step 23000: bleu: 27.01, loss: 53518.8750, ppl: 6.4620, duration: 120.9040s\n",
"2021-05-10 18:44:12,188 - INFO - joeynmt.training - Epoch 3, Step: 23100, Batch Loss: 1.892363, Tokens per Sec: 2925, Lr: 0.000300\n",
"2021-05-10 18:45:39,005 - INFO - joeynmt.training - Epoch 3, Step: 23200, Batch Loss: 2.022973, Tokens per Sec: 2962, Lr: 0.000300\n",
"2021-05-10 18:47:05,902 - INFO - joeynmt.training - Epoch 3, Step: 23300, Batch Loss: 1.946127, Tokens per Sec: 2913, Lr: 0.000300\n",
"2021-05-10 18:48:31,741 - INFO - joeynmt.training - Epoch 3, Step: 23400, Batch Loss: 2.462944, Tokens per Sec: 2797, Lr: 0.000300\n",
"2021-05-10 18:49:58,563 - INFO - joeynmt.training - Epoch 3, Step: 23500, Batch Loss: 2.276049, Tokens per Sec: 2930, Lr: 0.000300\n",
"2021-05-10 18:51:25,520 - INFO - joeynmt.training - Epoch 3, Step: 23600, Batch Loss: 1.861068, Tokens per Sec: 2884, Lr: 0.000300\n",
"2021-05-10 18:52:52,909 - INFO - joeynmt.training - Epoch 3, Step: 23700, Batch Loss: 1.905351, Tokens per Sec: 2894, Lr: 0.000300\n",
"2021-05-10 18:54:20,114 - INFO - joeynmt.training - Epoch 3, Step: 23800, Batch Loss: 2.171257, Tokens per Sec: 2803, Lr: 0.000300\n",
"2021-05-10 18:55:47,172 - INFO - joeynmt.training - Epoch 3, Step: 23900, Batch Loss: 1.932601, Tokens per Sec: 2931, Lr: 0.000300\n",
"2021-05-10 18:57:13,394 - INFO - joeynmt.training - Epoch 3, Step: 24000, Batch Loss: 2.071873, Tokens per Sec: 2837, Lr: 0.000300\n",
"2021-05-10 18:59:14,344 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 18:59:14,344 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 18:59:14,344 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 18:59:14,606 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 18:59:14,607 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 18:59:14,822 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 18:59:14,822 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 18:59:14,822 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 18:59:14,822 - INFO - joeynmt.training - \tHypothesis: In 1997 90,000 girls found room in England .\n",
"2021-05-10 18:59:14,822 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - \tHypothesis: You must have to know what the Bible does not be convinced and support to him .\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - \tHypothesis: At the main center in the city of Strasbourg , which is the Pharisees of Human Empire , travelers arranged to predict their copy .\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - \tHypothesis: Remember the abundance and discreet .\n",
"2021-05-10 18:59:14,823 - INFO - joeynmt.training - Validation result (greedy) at epoch 3, step 24000: bleu: 27.07, loss: 53311.3945, ppl: 6.4154, duration: 121.4290s\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2021-05-10 19:00:40,537 - INFO - joeynmt.training - Epoch 3, Step: 24100, Batch Loss: 1.761699, Tokens per Sec: 2854, Lr: 0.000300\n",
"2021-05-10 19:02:06,905 - INFO - joeynmt.training - Epoch 3, Step: 24200, Batch Loss: 1.903977, Tokens per Sec: 2923, Lr: 0.000300\n",
"2021-05-10 19:03:32,696 - INFO - joeynmt.training - Epoch 3, Step: 24300, Batch Loss: 1.905390, Tokens per Sec: 2903, Lr: 0.000300\n",
"2021-05-10 19:04:59,193 - INFO - joeynmt.training - Epoch 3, Step: 24400, Batch Loss: 2.093480, Tokens per Sec: 2926, Lr: 0.000300\n",
"2021-05-10 19:06:25,690 - INFO - joeynmt.training - Epoch 3, Step: 24500, Batch Loss: 2.135311, Tokens per Sec: 2954, Lr: 0.000300\n",
"2021-05-10 19:07:51,921 - INFO - joeynmt.training - Epoch 3, Step: 24600, Batch Loss: 2.122672, Tokens per Sec: 2913, Lr: 0.000300\n",
"2021-05-10 19:09:18,775 - INFO - joeynmt.training - Epoch 3, Step: 24700, Batch Loss: 2.238747, Tokens per Sec: 2899, Lr: 0.000300\n",
"2021-05-10 19:10:45,515 - INFO - joeynmt.training - Epoch 3, Step: 24800, Batch Loss: 1.964722, Tokens per Sec: 2877, Lr: 0.000300\n",
"2021-05-10 19:12:11,358 - INFO - joeynmt.training - Epoch 3, Step: 24900, Batch Loss: 1.914498, Tokens per Sec: 2828, Lr: 0.000300\n",
"2021-05-10 19:13:36,237 - INFO - joeynmt.training - Epoch 3, Step: 25000, Batch Loss: 1.887765, Tokens per Sec: 2859, Lr: 0.000300\n",
"2021-05-10 19:15:43,509 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 19:15:43,509 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 19:15:43,509 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 19:15:43,771 - INFO - joeynmt.training - Hooray! New best validation result [ppl]!\n",
"2021-05-10 19:15:43,771 - INFO - joeynmt.training - Saving new checkpoint.\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found in England .\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - \tHypothesis: You must have learned what the Bible says to be convinced and reliable to him .\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - \tHypothesis: At the capital of Strasbourg , which is a Roman European Rights of Human Rights , travelers arranged to predict their copy .\n",
"2021-05-10 19:15:43,985 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 19:15:43,986 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 19:15:43,986 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 19:15:43,986 - INFO - joeynmt.training - \tHypothesis: Remember many and discreet .\n",
"2021-05-10 19:15:43,986 - INFO - joeynmt.training - Validation result (greedy) at epoch 3, step 25000: bleu: 27.79, loss: 52673.2461, ppl: 6.2743, duration: 127.7482s\n",
"2021-05-10 19:17:12,858 - INFO - joeynmt.training - Epoch 3, Step: 25100, Batch Loss: 1.952466, Tokens per Sec: 2839, Lr: 0.000300\n",
"2021-05-10 19:18:39,812 - INFO - joeynmt.training - Epoch 3, Step: 25200, Batch Loss: 2.080122, Tokens per Sec: 2931, Lr: 0.000300\n",
"2021-05-10 19:20:05,524 - INFO - joeynmt.training - Epoch 3, Step: 25300, Batch Loss: 2.109455, Tokens per Sec: 2961, Lr: 0.000300\n",
"2021-05-10 19:21:31,503 - INFO - joeynmt.training - Epoch 3, Step: 25400, Batch Loss: 1.890165, Tokens per Sec: 2905, Lr: 0.000300\n",
"2021-05-10 19:22:58,327 - INFO - joeynmt.training - Epoch 3, Step: 25500, Batch Loss: 1.891301, Tokens per Sec: 2929, Lr: 0.000300\n",
"2021-05-10 19:24:23,619 - INFO - joeynmt.training - Epoch 3, Step: 25600, Batch Loss: 2.036573, Tokens per Sec: 2899, Lr: 0.000300\n",
"2021-05-10 19:25:49,673 - INFO - joeynmt.training - Epoch 3, Step: 25700, Batch Loss: 1.813404, Tokens per Sec: 2892, Lr: 0.000300\n",
"2021-05-10 19:27:15,983 - INFO - joeynmt.training - Epoch 3, Step: 25800, Batch Loss: 1.910212, Tokens per Sec: 2904, Lr: 0.000300\n",
"2021-05-10 19:28:41,847 - INFO - joeynmt.training - Epoch 3, Step: 25900, Batch Loss: 2.352136, Tokens per Sec: 2895, Lr: 0.000300\n",
"2021-05-10 19:30:07,490 - INFO - joeynmt.training - Epoch 3, Step: 26000, Batch Loss: 1.867678, Tokens per Sec: 2912, Lr: 0.000300\n",
"2021-05-10 19:33:38,167 - INFO - joeynmt.training - Epoch 3, Step: 26100, Batch Loss: 2.038053, Tokens per Sec: 2964, Lr: 0.000300\n",
"2021-05-10 19:35:03,751 - INFO - joeynmt.training - Epoch 3, Step: 26200, Batch Loss: 1.955604, Tokens per Sec: 2889, Lr: 0.000300\n",
"2021-05-10 19:36:31,590 - INFO - joeynmt.training - Epoch 3, Step: 26300, Batch Loss: 1.804468, Tokens per Sec: 2940, Lr: 0.000300\n",
"2021-05-10 19:37:56,751 - INFO - joeynmt.training - Epoch 3, Step: 26400, Batch Loss: 1.958242, Tokens per Sec: 2898, Lr: 0.000300\n",
"2021-05-10 19:39:22,943 - INFO - joeynmt.training - Epoch 3, Step: 26500, Batch Loss: 2.022110, Tokens per Sec: 2905, Lr: 0.000300\n",
"2021-05-10 19:40:49,341 - INFO - joeynmt.training - Epoch 3, Step: 26600, Batch Loss: 2.556990, Tokens per Sec: 2925, Lr: 0.000300\n",
"2021-05-10 19:42:14,828 - INFO - joeynmt.training - Epoch 3, Step: 26700, Batch Loss: 2.087514, Tokens per Sec: 2881, Lr: 0.000300\n",
"2021-05-10 19:43:41,227 - INFO - joeynmt.training - Epoch 3, Step: 26800, Batch Loss: 1.980137, Tokens per Sec: 2917, Lr: 0.000300\n",
"2021-05-10 19:45:05,907 - INFO - joeynmt.training - Epoch 3, Step: 26900, Batch Loss: 1.983151, Tokens per Sec: 2885, Lr: 0.000300\n",
"2021-05-10 19:46:31,410 - INFO - joeynmt.training - Epoch 3, Step: 27000, Batch Loss: 1.855923, Tokens per Sec: 2928, Lr: 0.000300\n",
"2021-05-10 19:48:29,500 - WARNING - sacrebleu - That's 100 lines that end in a tokenized period ('.')\n",
"2021-05-10 19:48:29,501 - WARNING - sacrebleu - It looks like you forgot to detokenize your test data, which may hurt your score.\n",
"2021-05-10 19:48:29,501 - WARNING - sacrebleu - If you insist your data is detokenized, or don't care, you can suppress this message with '--force'.\n",
"2021-05-10 19:48:29,960 - INFO - joeynmt.training - Example #0\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - \tSource: Katika mwaka wa 1997 wasichana 90,000 walipata mimba huko Uingereza .\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - \tReference: There were almost 90,000 conceptions to teenagers in England in 1997 .\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - \tHypothesis: In 1997 the 90,000 girls found in Britain .\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - Example #1\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - \tSource: Lazima ujikakamue kujua kile isemacho Biblia kusudi usadikishwe na kutegemeka kwake .\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - \tReference: You must exert yourself to find out what the Bible says so as to be convinced of its reliability .\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - \tHypothesis: You must have to know what the Bible says not to be convinced and reliable .\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - Example #2\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - \tSource: Kwenye kituo kikuu katika jiji la Strasbourg , ambalo ni makao ya Mahakama ya Ulaya ya Haki za Kibinadamu , wasafiri walipanga foleni wakisubiri kupata nakala yao .\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - \tReference: In Strasbourg , home of the European Court of Human Rights , travelers at the central station line up patiently to receive their copy .\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - \tHypothesis: At the main center in the city of Strasbourg , which is the European Rights , travelers sought to find their copy .\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - Example #3\n",
"2021-05-10 19:48:29,961 - INFO - joeynmt.training - \tSource: Kukumbatia kwingi na busu nyingi .\n",
"2021-05-10 19:48:29,962 - INFO - joeynmt.training - \tReference: Lots of hugs and kisses .\n",
"2021-05-10 19:48:29,962 - INFO - joeynmt.training - \tHypothesis: Remember , and many discreet .\n",
"2021-05-10 19:48:29,962 - INFO - joeynmt.training - Validation result (greedy) at epoch 3, step 27000: bleu: 26.92, loss: 53394.1797, ppl: 6.4340, duration: 118.5513s\n"
]
}
],
"source": [
"# Train the model\n",
"# You can press Ctrl-C to stop. And then run the next cell to save your checkpoints! \n",
"!cd joeynmt; python3 -m joeynmt train configs/transformer_reverse_$tgt$src.yaml"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "MBoDS09JM807"
},
"outputs": [],
"source": [
"# Copy the created models from the notebook storage to google drive for persistant storage \n",
"!cp -r joeynmt/models/${tgt}${src}_reverse_transformer/* \"$gdrive_path/models/${src}${tgt}_reverse_transformer/\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "n94wlrCjVc17"
},
"outputs": [],
"source": [
"# Output our validation accuracy\n",
"! cat \"$gdrive_path/models/${tgt}${src}_reverse_transformer/validations.txt\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "66WhRE9lIhoD"
},
"outputs": [],
"source": [
"# Test our model\n",
"! cd joeynmt; python3 -m joeynmt test \"$gdrive_path/models/${tgt}${src}_reverse_transformer/config.yaml\""
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"collapsed_sections": [],
"name": "starter_notebook_reverse_training.ipynb",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.10"
}
},
"nbformat": 4,
"nbformat_minor": 1
}
|