Edit model card

cs_m2m_2e-5_500_v0.2

This model is a fine-tuned version of facebook/m2m100_1.2B on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.2781
  • Bleu: 47.4947
  • Gen Len: 20.3333

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 500

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
3.5955 1.0 6 2.1700 5.2853 61.7619
2.1803 2.0 12 1.7324 45.1068 18.5238
0.884 3.0 18 1.6620 42.4488 20.0476
0.9149 4.0 24 1.6110 38.281 19.8571
0.9369 5.0 30 1.6441 37.3868 19.7143
0.1262 6.0 36 1.6365 42.0778 19.7143
0.4717 7.0 42 1.5780 44.6136 19.5238
0.2614 8.0 48 1.6052 51.6602 20.7619
0.2663 9.0 54 1.6658 53.657 20.1429
0.0851 10.0 60 1.7080 51.0034 20.4286
0.1336 11.0 66 1.7162 49.5043 19.1905
0.3736 12.0 72 1.6973 46.88 21.5238
0.0491 13.0 78 1.7101 54.4471 19.7619
0.0133 14.0 84 1.6952 46.3602 21.2857
0.0302 15.0 90 1.7021 57.2323 20.2381
0.0469 16.0 96 1.7036 50.0225 21.4762
0.0249 17.0 102 1.7247 45.7879 20.8095
0.0246 18.0 108 1.7429 53.4311 20.381
0.0832 19.0 114 1.7789 43.4352 21.4286
0.0161 20.0 120 1.8177 48.3969 19.1429
0.0035 21.0 126 1.7921 48.6517 20.2857
0.0109 22.0 132 1.8524 42.681 22.3333
0.0025 23.0 138 1.7995 50.2653 20.0476
0.003 24.0 144 1.7659 50.7496 19.4286
0.0054 25.0 150 1.8429 46.086 20.5714
0.0036 26.0 156 1.9221 39.5188 20.619
0.0023 27.0 162 1.8843 52.8052 19.7619
0.02 28.0 168 1.8557 54.4796 19.7619
0.008 29.0 174 1.8593 48.5401 21.0476
0.0088 30.0 180 1.8269 50.8012 21.1429
0.0079 31.0 186 1.7975 46.5216 19.2857
0.0552 32.0 192 1.8510 50.8412 19.2857
0.0028 33.0 198 1.9185 53.3245 19.8095
0.0011 34.0 204 1.9616 49.2009 19.9524
0.0042 35.0 210 1.9582 51.9018 19.7143
0.0009 36.0 216 1.9574 54.2746 20.0
0.0167 37.0 222 2.0107 50.2599 20.7143
0.0052 38.0 228 2.0236 51.6827 20.3333
0.0029 39.0 234 2.0169 52.7398 19.8095
0.0021 40.0 240 1.9801 51.647 19.9048
0.0009 41.0 246 1.9861 48.053 19.8571
0.0018 42.0 252 1.9881 49.8501 19.9524
0.0026 43.0 258 2.0431 51.2736 19.9048
0.0015 44.0 264 2.0913 51.1887 19.8571
0.0025 45.0 270 2.0098 49.738 19.9524
0.0041 46.0 276 1.9856 46.8015 19.8571
0.0008 47.0 282 1.9475 46.8278 19.619
0.0004 48.0 288 1.9087 49.001 19.6667
0.001 49.0 294 1.9677 45.0947 21.0
0.0019 50.0 300 1.9625 45.491 21.0476
0.002 51.0 306 1.9372 49.6757 20.5238
0.001 52.0 312 1.9319 51.4649 20.1905
0.0062 53.0 318 1.8968 51.4694 20.0
0.0013 54.0 324 1.8859 50.4794 19.9524
0.0014 55.0 330 1.9014 49.2881 20.3333
0.0008 56.0 336 1.9024 51.9622 20.2381
0.0022 57.0 342 1.9273 48.7743 20.0952
0.0013 58.0 348 1.9632 49.3723 20.2857
0.0006 59.0 354 1.9923 48.5337 20.3333
0.0011 60.0 360 1.9938 49.1061 20.4286
0.0006 61.0 366 1.9692 48.2225 20.0
0.1667 62.0 372 1.9649 47.4302 19.8095
0.0006 63.0 378 1.9827 49.0037 20.0952
0.0012 64.0 384 1.9765 48.2799 20.0476
0.0003 65.0 390 1.9955 46.735 19.9048
0.0002 66.0 396 1.9911 46.4335 19.5238
0.0007 67.0 402 1.9832 49.2708 19.6667
0.001 68.0 408 1.9897 47.6271 19.5238
0.0026 69.0 414 1.9979 47.6271 19.5238
0.0062 70.0 420 1.9920 47.5221 19.5714
0.0002 71.0 426 1.9862 50.3982 19.5714
0.0004 72.0 432 2.0065 48.4579 19.6667
0.0006 73.0 438 2.0130 49.5911 19.7143
0.0001 74.0 444 2.0056 49.9929 19.619
0.0002 75.0 450 2.0018 51.8596 19.619
0.0007 76.0 456 2.0047 50.8034 19.619
0.0005 77.0 462 2.0077 50.8034 19.619
0.0003 78.0 468 2.0133 50.8034 19.619
0.0007 79.0 474 2.0093 50.0533 19.5714
0.0002 80.0 480 2.0145 49.7182 19.4762
0.0014 81.0 486 2.0210 50.7126 19.5238
0.0003 82.0 492 2.0275 50.7126 19.5238
0.0007 83.0 498 2.0344 49.5788 19.4762
0.0004 84.0 504 2.0400 50.7126 19.5238
0.0002 85.0 510 2.0455 49.6457 19.5238
0.0003 86.0 516 2.0645 51.9483 19.619
0.0003 87.0 522 2.0836 51.9483 19.619
0.0038 88.0 528 2.1076 52.1279 19.6667
0.0005 89.0 534 2.0981 49.0257 20.0476
0.0009 90.0 540 2.0852 48.6199 20.0
0.0003 91.0 546 2.0739 50.5817 19.9524
0.0002 92.0 552 2.0602 50.1767 19.9048
0.0002 93.0 558 2.0509 48.7042 20.0
0.0008 94.0 564 2.0491 48.7042 20.0
0.0002 95.0 570 2.0517 48.7042 20.0
0.0003 96.0 576 2.0556 48.7042 20.0
0.0001 97.0 582 2.0595 52.2333 20.2857
0.0003 98.0 588 2.0621 52.2333 20.2857
0.0002 99.0 594 2.0600 54.5804 19.9048
0.0006 100.0 600 2.0611 54.6318 19.8095
0.0024 101.0 606 2.0606 54.6318 19.8095
0.0001 102.0 612 2.0643 53.1448 19.7619
0.0004 103.0 618 2.0691 55.0274 19.7143
0.0004 104.0 624 2.0697 52.665 19.4762
0.0006 105.0 630 2.0826 52.2629 19.5714
0.0016 106.0 636 2.0972 51.0973 19.6667
0.0001 107.0 642 2.0833 53.8477 19.9524
0.0034 108.0 648 2.0480 55.0274 19.8095
0.0002 109.0 654 2.0149 51.2345 19.5238
0.0008 110.0 660 1.9959 51.9978 19.5238
0.0001 111.0 666 1.9890 51.9978 19.5238
0.0003 112.0 672 1.9883 52.9513 20.0476
0.0003 113.0 678 1.9922 52.1948 20.0952
0.0007 114.0 684 1.9985 52.1948 20.0952
0.0001 115.0 690 2.0007 52.1948 20.0952
0.0001 116.0 696 2.0050 52.1948 20.1429
0.0001 117.0 702 2.0106 51.5427 20.3333
0.0001 118.0 708 2.0158 52.309 20.2381
0.0005 119.0 714 2.0206 52.309 20.2381
0.0001 120.0 720 2.0259 51.056 20.4762
0.0001 121.0 726 2.0301 51.056 20.4762
0.0005 122.0 732 2.0340 51.1742 20.2381
0.0001 123.0 738 2.0380 51.1742 20.2381
0.0004 124.0 744 2.0422 50.7642 20.5238
0.0002 125.0 750 2.0461 50.7642 20.5238
0.0002 126.0 756 2.0506 50.7642 20.5238
0.0001 127.0 762 2.0536 50.7642 20.5238
0.0004 128.0 768 2.0558 50.7642 20.5238
0.0001 129.0 774 2.0581 49.0869 20.4762
0.0003 130.0 780 2.0599 48.862 20.4286
0.0002 131.0 786 2.0627 48.862 20.4286
0.0003 132.0 792 2.0682 49.0869 20.4762
0.0002 133.0 798 2.0741 48.2505 20.4762
0.0002 134.0 804 2.0786 48.2505 20.4762
0.0001 135.0 810 2.0823 50.1384 20.4762
0.0001 136.0 816 2.0866 50.7642 20.381
0.0009 137.0 822 2.0906 52.2243 20.1429
0.0002 138.0 828 2.0976 50.7642 20.381
0.0001 139.0 834 2.1012 50.7642 20.381
0.0001 140.0 840 2.1034 52.2243 20.1429
0.0002 141.0 846 2.1071 50.7642 20.381
0.0006 142.0 852 2.1114 50.7642 20.381
0.0001 143.0 858 2.1146 51.1742 20.0952
0.0001 144.0 864 2.1153 50.1384 20.4762
0.0005 145.0 870 2.1157 49.3118 20.5238
0.0001 146.0 876 2.1163 51.1742 20.0952
0.0 147.0 882 2.1208 50.6075 20.0
0.0001 148.0 888 2.1241 50.6304 19.9524
0.0005 149.0 894 2.1266 50.6304 19.9524
0.0001 150.0 900 2.1281 50.5867 19.9524
0.0001 151.0 906 2.1298 50.5867 19.9524
0.0002 152.0 912 2.1316 50.5867 19.9524
0.0009 153.0 918 2.1321 49.3558 20.3333
0.0 154.0 924 2.1318 49.3558 20.3333
0.0003 155.0 930 2.1318 49.3558 20.3333
0.0 156.0 936 2.1325 49.3558 20.3333
0.0004 157.0 942 2.1341 50.479 20.381
0.0 158.0 948 2.1346 50.479 20.381
0.0003 159.0 954 2.1354 50.479 20.381
0.0 160.0 960 2.1363 50.479 20.381
0.0001 161.0 966 2.1373 50.479 20.381
0.0 162.0 972 2.1380 50.479 20.381
0.0052 163.0 978 2.1380 50.479 20.381
0.0001 164.0 984 2.1432 50.479 20.381
0.0001 165.0 990 2.1467 50.479 20.381
0.0001 166.0 996 2.1513 50.479 20.381
0.0001 167.0 1002 2.1546 50.5235 20.381
0.0005 168.0 1008 2.1553 51.6955 20.2857
0.0001 169.0 1014 2.1543 53.8019 20.0
0.0002 170.0 1020 2.1542 53.8019 20.0
0.0 171.0 1026 2.1548 53.8521 19.7143
0.0 172.0 1032 2.1555 53.8521 19.7143
0.0003 173.0 1038 2.1462 53.8521 19.7143
0.0001 174.0 1044 2.1291 52.7023 19.7143
0.0001 175.0 1050 2.1304 50.3338 19.381
0.0 176.0 1056 2.0798 50.3141 19.4286
0.0 177.0 1062 2.0432 47.7624 20.0
0.0001 178.0 1068 2.0438 47.7436 20.1429
0.0003 179.0 1074 2.0437 47.7244 20.1429
0.0001 180.0 1080 2.0524 51.3154 20.1905
0.0006 181.0 1086 2.0644 50.843 20.2381
0.0001 182.0 1092 2.1083 50.6743 20.0952
0.0 183.0 1098 2.1264 47.6199 19.8095
0.0001 184.0 1104 2.1199 45.1537 19.5238
0.0013 185.0 1110 2.1204 46.9434 19.7619
0.0001 186.0 1116 2.1338 49.9344 20.381
0.0008 187.0 1122 2.1509 51.8455 19.9524
0.0001 188.0 1128 2.1949 51.3978 19.8095
0.0001 189.0 1134 2.2056 53.87 19.6667
0.0002 190.0 1140 2.1266 49.0503 20.9524
0.0005 191.0 1146 2.1215 50.0876 20.9048
0.0002 192.0 1152 2.0713 50.0199 20.0476
0.0006 193.0 1158 2.0728 49.5668 19.8095
0.0001 194.0 1164 2.1020 48.7331 20.4286
0.0001 195.0 1170 2.1143 50.1215 20.2857
0.0002 196.0 1176 2.0750 49.983 20.9524
0.0003 197.0 1182 1.9591 52.5796 19.8571
0.0003 198.0 1188 1.9419 49.5994 19.8571
0.0003 199.0 1194 1.9659 47.6525 20.7619
0.0013 200.0 1200 1.9903 47.7076 20.4286
0.0003 201.0 1206 2.0053 46.0621 20.0952
0.0003 202.0 1212 2.0320 47.1943 20.1429
0.0006 203.0 1218 2.0508 45.6812 20.0952
0.0014 204.0 1224 2.0534 45.8767 20.1905
0.0002 205.0 1230 2.0415 46.633 20.1429
0.0035 206.0 1236 2.0424 44.5798 19.9524
0.0005 207.0 1242 2.0165 45.2633 19.8571
0.0001 208.0 1248 2.0307 47.6459 20.0
0.0016 209.0 1254 2.0661 48.8307 20.7619
0.0006 210.0 1260 2.0939 48.992 20.5714
0.0001 211.0 1266 2.1039 49.2669 20.5714
0.0001 212.0 1272 2.1057 49.4961 20.7619
0.0001 213.0 1278 2.1076 49.4813 20.4286
0.0001 214.0 1284 2.1059 49.973 20.3333
0.0004 215.0 1290 2.1045 49.7227 20.2857
0.0014 216.0 1296 2.1148 48.4398 20.381
0.0001 217.0 1302 2.1612 49.2202 20.5714
0.0005 218.0 1308 2.1941 46.6581 21.0476
0.0006 219.0 1314 2.2119 46.6703 20.9048
0.0002 220.0 1320 2.1986 45.8806 21.0476
0.0001 221.0 1326 2.1711 46.8083 20.7619
0.0006 222.0 1332 2.1572 46.8083 20.7619
0.0102 223.0 1338 2.1339 48.1926 20.4286
0.0003 224.0 1344 2.0926 48.7288 20.3333
0.2973 225.0 1350 2.1248 49.4645 20.5238
0.0 226.0 1356 2.1955 46.7165 20.7619
0.0001 227.0 1362 2.1353 50.381 20.5714
0.0001 228.0 1368 2.0547 50.8303 20.0476
0.0001 229.0 1374 1.9967 47.8055 19.7619
0.0001 230.0 1380 1.9714 48.2664 19.9048
0.0003 231.0 1386 1.9728 47.4206 20.0
0.0002 232.0 1392 1.9759 48.2275 19.9048
0.0025 233.0 1398 1.9796 47.7789 20.0476
0.0001 234.0 1404 1.9915 46.5661 20.2857
0.0001 235.0 1410 2.0214 45.9259 20.0476
0.0001 236.0 1416 2.0512 45.9259 20.0476
0.0001 237.0 1422 2.0702 45.9259 20.0476
0.0006 238.0 1428 2.0808 46.7359 19.9524
0.0001 239.0 1434 2.0863 45.5803 19.5714
0.0001 240.0 1440 2.0899 45.5803 19.5714
0.0003 241.0 1446 2.0954 45.574 20.0952
0.0 242.0 1452 2.1013 47.0915 20.2857
0.0003 243.0 1458 2.1052 47.0723 20.1429
0.0003 244.0 1464 2.1076 47.0281 20.0952
0.0002 245.0 1470 2.1108 45.4934 20.0476
0.0001 246.0 1476 2.1124 45.4934 20.0476
0.0003 247.0 1482 2.1137 45.8284 20.3333
0.0001 248.0 1488 2.1158 45.8284 20.3333
0.0001 249.0 1494 2.1176 45.8284 20.3333
0.0 250.0 1500 2.1193 45.4934 20.0476
0.0015 251.0 1506 2.1208 45.4934 20.0476
0.0001 252.0 1512 2.1222 45.512 20.0952
0.0001 253.0 1518 2.1234 45.512 20.0952
0.0001 254.0 1524 2.1253 45.512 20.0952
0.0004 255.0 1530 2.1266 45.512 20.0952
0.0008 256.0 1536 2.1280 45.512 20.0952
0.0001 257.0 1542 2.1326 45.512 20.0952
0.0001 258.0 1548 2.1868 45.3968 20.2381
0.0001 259.0 1554 2.2196 45.7643 20.5714
0.0 260.0 1560 2.2238 47.9478 19.8095
0.0001 261.0 1566 2.1992 46.66 20.4286
0.0002 262.0 1572 2.1599 46.4694 20.1429
0.0002 263.0 1578 2.1418 49.4284 20.3333
0.0002 264.0 1584 2.1377 46.8936 20.1905
0.0006 265.0 1590 2.1559 46.4694 20.2857
0.0005 266.0 1596 2.1897 48.0993 20.381
0.0002 267.0 1602 2.2092 47.1607 20.4762
0.0003 268.0 1608 2.2165 47.1685 20.5238
0.0001 269.0 1614 2.2186 48.1068 20.4286
0.0001 270.0 1620 2.2182 48.0643 20.381
0.0002 271.0 1626 2.2189 48.8767 20.4762
0.0009 272.0 1632 2.2200 48.8767 20.4762
0.0002 273.0 1638 2.2225 47.257 20.381
0.0002 274.0 1644 2.2289 47.257 20.381
0.0001 275.0 1650 2.2403 47.257 20.381
0.0001 276.0 1656 2.2460 47.2914 20.381
0.0003 277.0 1662 2.2549 48.9183 20.5238
0.0001 278.0 1668 2.2598 48.9183 20.5238
0.0001 279.0 1674 2.2622 48.9183 20.5238
0.0005 280.0 1680 2.2651 48.9183 20.5238
0.0 281.0 1686 2.2663 48.9183 20.5238
0.0 282.0 1692 2.2666 48.9183 20.5238
0.0 283.0 1698 2.2660 47.2988 20.4286
0.0 284.0 1704 2.2620 47.2988 20.4286
0.0001 285.0 1710 2.2595 47.2988 20.2857
0.0 286.0 1716 2.2580 47.2988 20.2857
0.0001 287.0 1722 2.2564 47.2988 20.2857
0.0 288.0 1728 2.2553 46.9445 20.0476
0.0001 289.0 1734 2.2553 46.9445 20.0476
0.0001 290.0 1740 2.2562 46.4768 20.1429
0.0001 291.0 1746 2.2567 48.9183 20.5238
0.0001 292.0 1752 2.2563 48.9183 20.5238
0.0001 293.0 1758 2.2562 48.9183 20.5238
0.0 294.0 1764 2.2566 46.4768 20.2857
0.0 295.0 1770 2.2568 46.4768 20.2857
0.0 296.0 1776 2.2570 46.6807 20.5238
0.0002 297.0 1782 2.2577 46.6807 20.5238
0.0 298.0 1788 2.2586 46.6807 20.5238
0.0 299.0 1794 2.2587 46.6807 20.5238
0.0002 300.0 1800 2.2590 47.1779 20.4286
0.0 301.0 1806 2.2599 46.7979 20.4286
0.0 302.0 1812 2.2607 46.7979 20.4286
0.0 303.0 1818 2.2612 46.7979 20.4286
0.0001 304.0 1824 2.2636 47.4812 20.5238
0.0 305.0 1830 2.2967 46.6592 20.5714
0.0001 306.0 1836 2.3152 45.6495 20.1905
0.0 307.0 1842 2.3223 45.6495 20.1905
0.0041 308.0 1848 2.3132 46.3486 20.1905
0.0001 309.0 1854 2.2839 46.6149 20.5714
0.0001 310.0 1860 2.2739 46.7461 20.9524
0.0001 311.0 1866 2.2741 48.816 21.0
0.0001 312.0 1872 2.2815 48.816 21.0
0.0008 313.0 1878 2.2861 49.7977 20.8095
0.0001 314.0 1884 2.2888 49.7977 20.8095
0.0005 315.0 1890 2.2884 49.7977 20.8095
0.0002 316.0 1896 2.2930 49.5982 20.8571
0.0001 317.0 1902 2.2943 49.5982 20.8571
0.0 318.0 1908 2.2929 49.4561 20.8571
0.0001 319.0 1914 2.2910 49.4561 20.8571
0.0002 320.0 1920 2.2895 49.4561 20.7619
0.0 321.0 1926 2.2867 49.4561 20.7619
0.0002 322.0 1932 2.2848 49.6545 20.7143
0.0001 323.0 1938 2.2833 49.6545 20.7143
0.0001 324.0 1944 2.2808 49.6545 20.8095
0.0002 325.0 1950 2.2789 49.6545 20.8095
0.0 326.0 1956 2.2777 49.6545 20.8095
0.0002 327.0 1962 2.2769 49.6545 20.8095
0.0003 328.0 1968 2.2766 49.6545 20.8095
0.0001 329.0 1974 2.2767 47.3641 20.7143
0.0 330.0 1980 2.2768 47.3641 20.7143
0.0001 331.0 1986 2.2768 47.5556 20.6667
0.0007 332.0 1992 2.2768 47.5556 20.6667
0.0001 333.0 1998 2.2775 47.5556 20.6667
0.0001 334.0 2004 2.2780 47.5556 20.6667
0.0 335.0 2010 2.2779 47.5556 20.6667
0.0001 336.0 2016 2.2775 47.5556 20.6667
0.0001 337.0 2022 2.2774 47.5556 20.6667
0.0002 338.0 2028 2.2773 47.5556 20.6667
0.0001 339.0 2034 2.2774 47.5556 20.6667
0.0 340.0 2040 2.2774 47.5556 20.6667
0.0001 341.0 2046 2.2777 47.5556 20.6667
0.0 342.0 2052 2.2785 47.5556 20.6667
0.0 343.0 2058 2.2789 47.5556 20.6667
0.0 344.0 2064 2.2792 47.5556 20.6667
0.0001 345.0 2070 2.2792 47.5556 20.6667
0.0001 346.0 2076 2.2788 47.5556 20.6667
0.0001 347.0 2082 2.2777 47.5556 20.6667
0.0 348.0 2088 2.2765 47.5556 20.5714
0.0001 349.0 2094 2.2759 47.6855 20.5238
0.0 350.0 2100 2.2759 47.6855 20.5238
0.0 351.0 2106 2.2765 47.6855 20.5238
0.0001 352.0 2112 2.2770 47.7313 20.4286
0.0001 353.0 2118 2.2771 47.7313 20.4286
0.0001 354.0 2124 2.2781 47.7313 20.4286
0.0003 355.0 2130 2.2793 47.7313 20.4286
0.0 356.0 2136 2.2799 47.7313 20.4286
0.0 357.0 2142 2.2795 47.7313 20.5238
0.0 358.0 2148 2.2785 47.7313 20.5238
0.0 359.0 2154 2.2731 47.7313 20.5238
0.0001 360.0 2160 2.2700 49.0445 20.5238
0.0001 361.0 2166 2.2729 47.4186 20.5238
0.0001 362.0 2172 2.2738 47.6535 20.619
0.0003 363.0 2178 2.2749 47.6535 20.619
0.0 364.0 2184 2.2764 49.934 20.7619
0.0 365.0 2190 2.2767 49.934 20.7619
0.0 366.0 2196 2.2777 47.6535 20.619
0.0001 367.0 2202 2.2781 47.6535 20.619
0.0 368.0 2208 2.2782 47.6535 20.619
0.0001 369.0 2214 2.2793 47.6535 20.619
0.0001 370.0 2220 2.2813 47.6535 20.619
0.0 371.0 2226 2.2825 47.6535 20.619
0.0 372.0 2232 2.2829 47.6535 20.619
0.0 373.0 2238 2.2829 47.6535 20.619
0.0 374.0 2244 2.2835 47.6535 20.619
0.0001 375.0 2250 2.2839 47.6535 20.5238
0.0 376.0 2256 2.2813 47.7313 20.4286
0.0 377.0 2262 2.2799 47.7313 20.4286
0.0 378.0 2268 2.2905 49.934 20.6667
0.0003 379.0 2274 2.2987 49.4003 20.8571
0.0 380.0 2280 2.3031 49.4003 20.8571
0.0 381.0 2286 2.2846 49.9567 20.4762
0.0 382.0 2292 2.2619 50.5242 20.4286
0.0001 383.0 2298 2.2513 48.6789 20.1905
0.0001 384.0 2304 2.2479 48.7115 20.1905
0.0 385.0 2310 2.2467 50.4157 20.1905
0.0 386.0 2316 2.2465 50.4157 20.1905
0.0001 387.0 2322 2.2470 50.4157 20.1905
0.0001 388.0 2328 2.2464 48.7115 20.1905
0.0 389.0 2334 2.2461 48.7115 20.1905
0.0 390.0 2340 2.2467 48.6789 20.1905
0.0 391.0 2346 2.2471 48.7431 20.2381
0.0001 392.0 2352 2.2475 48.7431 20.2381
0.0 393.0 2358 2.2481 48.7431 20.2381
0.0 394.0 2364 2.2485 48.7431 20.2381
0.0001 395.0 2370 2.2492 48.7431 20.2381
0.0 396.0 2376 2.2494 48.7431 20.2381
0.0001 397.0 2382 2.2496 48.7431 20.2381
0.0002 398.0 2388 2.2498 48.7018 20.1905
0.0 399.0 2394 2.2499 48.7351 20.1905
0.0 400.0 2400 2.2502 48.7351 20.1905
0.0001 401.0 2406 2.2506 48.7351 20.1905
0.0001 402.0 2412 2.2511 48.7351 20.1905
0.0 403.0 2418 2.2514 48.7351 20.1905
0.0 404.0 2424 2.2518 48.7351 20.0952
0.0003 405.0 2430 2.2524 48.7351 20.0952
0.0001 406.0 2436 2.2537 48.7351 20.0952
0.0 407.0 2442 2.2551 48.7351 20.0952
0.0 408.0 2448 2.2561 48.7018 20.0952
0.0 409.0 2454 2.2570 48.7351 20.0952
0.0001 410.0 2460 2.2578 48.7351 20.0952
0.0002 411.0 2466 2.2585 48.7351 20.0952
0.0001 412.0 2472 2.2593 48.7351 20.0952
0.0 413.0 2478 2.2597 48.7351 20.0952
0.0002 414.0 2484 2.2600 48.7351 20.0952
0.0 415.0 2490 2.2604 48.7351 20.0952
0.0 416.0 2496 2.2609 48.7351 20.0952
0.0002 417.0 2502 2.2613 48.7351 20.0952
0.0004 418.0 2508 2.2620 48.7351 20.0952
0.0001 419.0 2514 2.2630 48.7351 20.0952
0.0001 420.0 2520 2.2636 48.7351 20.0952
0.0 421.0 2526 2.2641 48.7351 20.0952
0.0 422.0 2532 2.2645 48.7351 20.0952
0.0 423.0 2538 2.2648 48.7351 20.0952
0.0 424.0 2544 2.2651 48.7351 20.0952
0.0002 425.0 2550 2.2644 48.7351 20.0952
0.0001 426.0 2556 2.2629 48.7351 20.0952
0.0 427.0 2562 2.2622 48.7351 20.0952
0.0 428.0 2568 2.2613 48.7351 20.0952
0.0 429.0 2574 2.2700 47.7358 20.2381
0.0001 430.0 2580 2.2775 47.4947 20.3333
0.0001 431.0 2586 2.2809 49.9567 20.4762
0.0001 432.0 2592 2.2739 47.4947 20.3333
0.0 433.0 2598 2.2711 47.4728 20.381
0.0002 434.0 2604 2.2701 47.4728 20.381
0.0 435.0 2610 2.2703 47.4728 20.381
0.0001 436.0 2616 2.2705 49.9328 20.5238
0.0 437.0 2622 2.2710 49.8173 20.381
0.0001 438.0 2628 2.2712 49.8173 20.381
0.0 439.0 2634 2.2712 49.8173 20.381
0.0 440.0 2640 2.2713 49.8173 20.381
0.0 441.0 2646 2.2717 47.7358 20.2381
0.0 442.0 2652 2.2721 47.7358 20.2381
0.0001 443.0 2658 2.2724 47.7358 20.2381
0.0 444.0 2664 2.2727 47.7358 20.2381
0.0001 445.0 2670 2.2730 47.7358 20.2381
0.0001 446.0 2676 2.2732 47.7358 20.2381
0.0 447.0 2682 2.2734 47.7358 20.2381
0.0002 448.0 2688 2.2735 47.7358 20.2381
0.0 449.0 2694 2.2736 47.7358 20.2381
0.0 450.0 2700 2.2739 47.7358 20.2381
0.0 451.0 2706 2.2741 47.7358 20.2381
0.0 452.0 2712 2.2743 47.7358 20.2381
0.0 453.0 2718 2.2747 47.7358 20.2381
0.0001 454.0 2724 2.2747 47.7358 20.2381
0.0002 455.0 2730 2.2745 47.7358 20.2381
0.0 456.0 2736 2.2744 47.7358 20.2381
0.0 457.0 2742 2.2744 47.7358 20.2381
0.0 458.0 2748 2.2744 47.7358 20.2381
0.0 459.0 2754 2.2745 47.7358 20.2381
0.0 460.0 2760 2.2746 47.7358 20.2381
0.0003 461.0 2766 2.2748 47.7358 20.2381
0.0 462.0 2772 2.2750 47.7358 20.2381
0.0001 463.0 2778 2.2751 47.7358 20.2381
0.0001 464.0 2784 2.2752 47.7358 20.2381
0.0 465.0 2790 2.2754 47.7358 20.2381
0.0 466.0 2796 2.2755 47.7358 20.2381
0.0 467.0 2802 2.2755 47.7358 20.2381
0.0 468.0 2808 2.2756 47.7358 20.2381
0.0 469.0 2814 2.2758 47.7358 20.2381
0.0 470.0 2820 2.2758 47.7358 20.2381
0.0 471.0 2826 2.2758 47.7358 20.2381
0.0001 472.0 2832 2.2757 47.4947 20.3333
0.0001 473.0 2838 2.2757 47.4947 20.3333
0.0001 474.0 2844 2.2757 47.4947 20.3333
0.0 475.0 2850 2.2758 47.4947 20.3333
0.0001 476.0 2856 2.2758 47.4947 20.3333
0.0 477.0 2862 2.2759 47.4947 20.3333
0.0 478.0 2868 2.2760 47.4947 20.3333
0.0001 479.0 2874 2.2761 47.4947 20.3333
0.0001 480.0 2880 2.2762 47.4947 20.3333
0.0002 481.0 2886 2.2766 47.4947 20.3333
0.0002 482.0 2892 2.2768 47.4947 20.3333
0.0003 483.0 2898 2.2770 47.4947 20.3333
0.0 484.0 2904 2.2772 47.4947 20.3333
0.0 485.0 2910 2.2773 47.4947 20.3333
0.0 486.0 2916 2.2776 47.4947 20.3333
0.0001 487.0 2922 2.2777 47.4947 20.3333
0.0 488.0 2928 2.2779 47.4947 20.3333
0.0 489.0 2934 2.2779 47.4947 20.3333
0.0 490.0 2940 2.2780 47.4947 20.3333
0.0 491.0 2946 2.2781 47.4947 20.3333
0.0 492.0 2952 2.2781 47.4947 20.3333
0.0 493.0 2958 2.2781 47.4947 20.3333
0.0 494.0 2964 2.2781 47.4947 20.3333
0.0 495.0 2970 2.2781 47.4947 20.3333
0.0001 496.0 2976 2.2781 47.4947 20.3333
0.0 497.0 2982 2.2781 47.4947 20.3333
0.0004 498.0 2988 2.2781 47.4947 20.3333
0.0001 499.0 2994 2.2781 47.4947 20.3333
0.0001 500.0 3000 2.2781 47.4947 20.3333

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
7
Safetensors
Model size
1.24B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for kmok1/cs_m2m_2e-5_500_v0.2

Finetuned
(13)
this model