Upload add_sub_sorl_v1_abs10_K1_25K/metrics.json with huggingface_hub
Browse files
add_sub_sorl_v1_abs10_K1_25K/metrics.json
CHANGED
|
@@ -1190,502 +1190,567 @@
|
|
| 1190 |
"K": null,
|
| 1191 |
"mode": "sft",
|
| 1192 |
"n_digits": 6,
|
| 1193 |
-
"n_per_split":
|
| 1194 |
},
|
| 1195 |
"splits": {
|
| 1196 |
"add_S0": {
|
| 1197 |
"full_accuracy": 1.0,
|
| 1198 |
-
"
|
|
|
|
| 1199 |
"per_subtask": {
|
| 1200 |
"SA": {
|
| 1201 |
"accuracy": 1.0,
|
| 1202 |
-
"count":
|
| 1203 |
},
|
| 1204 |
"SS": {
|
| 1205 |
"accuracy": 1.0,
|
| 1206 |
-
"count":
|
| 1207 |
}
|
| 1208 |
}
|
| 1209 |
},
|
| 1210 |
"add_S1": {
|
| 1211 |
"full_accuracy": 1.0,
|
| 1212 |
-
"
|
|
|
|
| 1213 |
"per_subtask": {
|
| 1214 |
"SA": {
|
| 1215 |
"accuracy": 1.0,
|
| 1216 |
-
"count":
|
| 1217 |
},
|
| 1218 |
"SC": {
|
| 1219 |
"accuracy": 1.0,
|
| 1220 |
-
"count":
|
| 1221 |
},
|
| 1222 |
"SS": {
|
| 1223 |
"accuracy": 1.0,
|
| 1224 |
-
"count":
|
| 1225 |
},
|
| 1226 |
"UC": {
|
| 1227 |
"accuracy": 1.0,
|
| 1228 |
-
"count":
|
| 1229 |
}
|
| 1230 |
}
|
| 1231 |
},
|
| 1232 |
"add_S2": {
|
| 1233 |
"full_accuracy": 1.0,
|
| 1234 |
-
"
|
|
|
|
| 1235 |
"per_subtask": {
|
| 1236 |
"SA": {
|
| 1237 |
"accuracy": 1.0,
|
| 1238 |
-
"count":
|
| 1239 |
},
|
| 1240 |
"SC": {
|
| 1241 |
"accuracy": 1.0,
|
| 1242 |
-
"count":
|
| 1243 |
},
|
| 1244 |
"SS": {
|
| 1245 |
"accuracy": 1.0,
|
| 1246 |
-
"count":
|
| 1247 |
},
|
| 1248 |
"UC": {
|
| 1249 |
"accuracy": 1.0,
|
| 1250 |
-
"count":
|
| 1251 |
},
|
| 1252 |
"US": {
|
| 1253 |
"accuracy": 1.0,
|
| 1254 |
-
"count":
|
| 1255 |
}
|
| 1256 |
}
|
| 1257 |
},
|
| 1258 |
"add_S3": {
|
| 1259 |
-
"full_accuracy":
|
| 1260 |
-
"
|
|
|
|
| 1261 |
"per_subtask": {
|
| 1262 |
"SA": {
|
| 1263 |
"accuracy": 1.0,
|
| 1264 |
-
"count":
|
| 1265 |
},
|
| 1266 |
"SC": {
|
| 1267 |
"accuracy": 1.0,
|
| 1268 |
-
"count":
|
| 1269 |
},
|
| 1270 |
"SS": {
|
| 1271 |
"accuracy": 1.0,
|
| 1272 |
-
"count":
|
| 1273 |
},
|
| 1274 |
"UC": {
|
| 1275 |
-
"accuracy":
|
| 1276 |
-
"count":
|
| 1277 |
},
|
| 1278 |
"US": {
|
| 1279 |
"accuracy": 1.0,
|
| 1280 |
-
"count":
|
| 1281 |
}
|
| 1282 |
}
|
| 1283 |
},
|
| 1284 |
"add_S4": {
|
| 1285 |
-
"full_accuracy": 0.
|
| 1286 |
-
"
|
|
|
|
| 1287 |
"per_subtask": {
|
| 1288 |
"SA": {
|
| 1289 |
"accuracy": 1.0,
|
| 1290 |
-
"count":
|
| 1291 |
},
|
| 1292 |
"SC": {
|
| 1293 |
"accuracy": 1.0,
|
| 1294 |
-
"count":
|
| 1295 |
},
|
| 1296 |
"SS": {
|
| 1297 |
"accuracy": 1.0,
|
| 1298 |
-
"count":
|
| 1299 |
},
|
| 1300 |
"UC": {
|
| 1301 |
-
"accuracy": 0.
|
| 1302 |
-
"count":
|
| 1303 |
},
|
| 1304 |
"US": {
|
| 1305 |
-
"accuracy": 0.
|
| 1306 |
-
"count":
|
| 1307 |
}
|
| 1308 |
}
|
| 1309 |
},
|
| 1310 |
"add_S5": {
|
| 1311 |
-
"full_accuracy": 0.
|
| 1312 |
-
"
|
|
|
|
| 1313 |
"per_subtask": {
|
| 1314 |
"SA": {
|
| 1315 |
"accuracy": 1.0,
|
| 1316 |
-
"count":
|
| 1317 |
},
|
| 1318 |
"SC": {
|
| 1319 |
"accuracy": 1.0,
|
| 1320 |
-
"count":
|
| 1321 |
},
|
| 1322 |
"UC": {
|
| 1323 |
-
"accuracy": 0.
|
| 1324 |
-
"count":
|
| 1325 |
},
|
| 1326 |
"US": {
|
| 1327 |
-
"accuracy": 0.
|
| 1328 |
-
"count":
|
| 1329 |
}
|
| 1330 |
}
|
| 1331 |
},
|
| 1332 |
"add_S6": {
|
| 1333 |
-
"full_accuracy": 0.
|
| 1334 |
-
"
|
|
|
|
| 1335 |
"per_subtask": {
|
| 1336 |
"SC": {
|
| 1337 |
"accuracy": 1.0,
|
| 1338 |
-
"count":
|
| 1339 |
},
|
| 1340 |
"UC": {
|
| 1341 |
-
"accuracy": 0.
|
| 1342 |
-
"count":
|
| 1343 |
},
|
| 1344 |
"US": {
|
| 1345 |
-
"accuracy": 0.
|
| 1346 |
-
"count":
|
| 1347 |
}
|
| 1348 |
}
|
| 1349 |
},
|
| 1350 |
"add_random": {
|
| 1351 |
-
"full_accuracy": 0.
|
|
|
|
| 1352 |
"n_examples": 200,
|
| 1353 |
"per_subtask": {
|
| 1354 |
"SA": {
|
| 1355 |
"accuracy": 1.0,
|
| 1356 |
-
"count":
|
| 1357 |
},
|
| 1358 |
"SC": {
|
| 1359 |
"accuracy": 1.0,
|
| 1360 |
-
"count":
|
| 1361 |
},
|
| 1362 |
"SS": {
|
| 1363 |
"accuracy": 1.0,
|
| 1364 |
-
"count":
|
| 1365 |
},
|
| 1366 |
"UC": {
|
| 1367 |
-
"accuracy": 0.
|
| 1368 |
-
"count":
|
| 1369 |
},
|
| 1370 |
"US": {
|
| 1371 |
"accuracy": 1.0,
|
| 1372 |
-
"count":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1373 |
}
|
| 1374 |
}
|
| 1375 |
},
|
| 1376 |
"add_C3": {
|
| 1377 |
-
"full_accuracy":
|
| 1378 |
-
"
|
|
|
|
| 1379 |
"per_subtask": {
|
| 1380 |
"SA": {
|
| 1381 |
"accuracy": 1.0,
|
| 1382 |
-
"count":
|
| 1383 |
},
|
| 1384 |
"SC": {
|
| 1385 |
"accuracy": 1.0,
|
| 1386 |
-
"count":
|
| 1387 |
},
|
| 1388 |
"UC": {
|
| 1389 |
-
"accuracy":
|
| 1390 |
-
"count":
|
| 1391 |
},
|
| 1392 |
"US": {
|
| 1393 |
"accuracy": 1.0,
|
| 1394 |
-
"count":
|
| 1395 |
}
|
| 1396 |
}
|
| 1397 |
},
|
| 1398 |
"add_C4": {
|
| 1399 |
-
"full_accuracy": 0.
|
| 1400 |
-
"
|
|
|
|
| 1401 |
"per_subtask": {
|
| 1402 |
"SA": {
|
| 1403 |
"accuracy": 1.0,
|
| 1404 |
-
"count":
|
| 1405 |
},
|
| 1406 |
"SC": {
|
| 1407 |
"accuracy": 1.0,
|
| 1408 |
-
"count":
|
| 1409 |
},
|
| 1410 |
"UC": {
|
| 1411 |
-
"accuracy": 0.
|
| 1412 |
-
"count":
|
| 1413 |
},
|
| 1414 |
"US": {
|
| 1415 |
-
"accuracy": 0.
|
| 1416 |
-
"count":
|
| 1417 |
}
|
| 1418 |
}
|
| 1419 |
},
|
| 1420 |
"add_C5": {
|
| 1421 |
-
"full_accuracy": 0.
|
| 1422 |
-
"
|
|
|
|
| 1423 |
"per_subtask": {
|
| 1424 |
"SA": {
|
| 1425 |
"accuracy": 1.0,
|
| 1426 |
-
"count":
|
| 1427 |
},
|
| 1428 |
"SC": {
|
| 1429 |
"accuracy": 1.0,
|
| 1430 |
-
"count":
|
| 1431 |
},
|
| 1432 |
"UC": {
|
| 1433 |
-
"accuracy": 0.
|
| 1434 |
-
"count":
|
| 1435 |
},
|
| 1436 |
"US": {
|
| 1437 |
-
"accuracy": 0.
|
| 1438 |
-
"count":
|
| 1439 |
}
|
| 1440 |
}
|
| 1441 |
},
|
| 1442 |
"add_C6": {
|
| 1443 |
-
"full_accuracy": 0.
|
| 1444 |
-
"
|
|
|
|
| 1445 |
"per_subtask": {
|
| 1446 |
"SC": {
|
| 1447 |
"accuracy": 1.0,
|
| 1448 |
-
"count":
|
| 1449 |
},
|
| 1450 |
"UC": {
|
| 1451 |
-
"accuracy": 0.
|
| 1452 |
-
"count":
|
| 1453 |
},
|
| 1454 |
"US": {
|
| 1455 |
-
"accuracy":
|
| 1456 |
-
"count":
|
| 1457 |
}
|
| 1458 |
}
|
| 1459 |
},
|
| 1460 |
"sub_M0": {
|
| 1461 |
-
"full_accuracy":
|
| 1462 |
-
"
|
|
|
|
| 1463 |
"per_subtask": {
|
| 1464 |
"MD": {
|
| 1465 |
-
"accuracy":
|
| 1466 |
-
"count":
|
| 1467 |
},
|
| 1468 |
"ME": {
|
| 1469 |
"accuracy": 1.0,
|
| 1470 |
-
"count":
|
| 1471 |
}
|
| 1472 |
}
|
| 1473 |
},
|
| 1474 |
"sub_M1": {
|
| 1475 |
-
"full_accuracy":
|
| 1476 |
-
"
|
|
|
|
| 1477 |
"per_subtask": {
|
| 1478 |
"MD": {
|
| 1479 |
-
"accuracy":
|
| 1480 |
-
"count":
|
| 1481 |
},
|
| 1482 |
"MB": {
|
| 1483 |
"accuracy": 1.0,
|
| 1484 |
-
"count":
|
| 1485 |
},
|
| 1486 |
"ME": {
|
| 1487 |
"accuracy": 1.0,
|
| 1488 |
-
"count":
|
| 1489 |
},
|
| 1490 |
"UB": {
|
| 1491 |
"accuracy": 1.0,
|
| 1492 |
-
"count":
|
| 1493 |
}
|
| 1494 |
}
|
| 1495 |
},
|
| 1496 |
"sub_M2": {
|
| 1497 |
"full_accuracy": 1.0,
|
| 1498 |
-
"
|
|
|
|
| 1499 |
"per_subtask": {
|
| 1500 |
"MD": {
|
| 1501 |
"accuracy": 1.0,
|
| 1502 |
-
"count":
|
| 1503 |
},
|
| 1504 |
"MB": {
|
| 1505 |
"accuracy": 1.0,
|
| 1506 |
-
"count":
|
| 1507 |
},
|
| 1508 |
"ME": {
|
| 1509 |
"accuracy": 1.0,
|
| 1510 |
-
"count":
|
| 1511 |
},
|
| 1512 |
"UB": {
|
| 1513 |
"accuracy": 1.0,
|
| 1514 |
-
"count":
|
| 1515 |
},
|
| 1516 |
"UD": {
|
| 1517 |
"accuracy": 1.0,
|
| 1518 |
-
"count":
|
| 1519 |
}
|
| 1520 |
}
|
| 1521 |
},
|
| 1522 |
"sub_M3": {
|
| 1523 |
-
"full_accuracy":
|
| 1524 |
-
"
|
|
|
|
| 1525 |
"per_subtask": {
|
| 1526 |
"MD": {
|
| 1527 |
"accuracy": 1.0,
|
| 1528 |
-
"count":
|
| 1529 |
},
|
| 1530 |
"MB": {
|
| 1531 |
"accuracy": 1.0,
|
| 1532 |
-
"count":
|
| 1533 |
},
|
| 1534 |
"ME": {
|
| 1535 |
"accuracy": 1.0,
|
| 1536 |
-
"count":
|
| 1537 |
},
|
| 1538 |
"UB": {
|
| 1539 |
-
"accuracy":
|
| 1540 |
-
"count":
|
| 1541 |
},
|
| 1542 |
"UD": {
|
| 1543 |
"accuracy": 1.0,
|
| 1544 |
-
"count":
|
| 1545 |
}
|
| 1546 |
}
|
| 1547 |
},
|
| 1548 |
"sub_M4": {
|
| 1549 |
-
"full_accuracy": 0.
|
| 1550 |
-
"
|
|
|
|
| 1551 |
"per_subtask": {
|
| 1552 |
"MD": {
|
| 1553 |
"accuracy": 1.0,
|
| 1554 |
-
"count":
|
| 1555 |
},
|
| 1556 |
"MB": {
|
| 1557 |
"accuracy": 1.0,
|
| 1558 |
-
"count":
|
| 1559 |
},
|
| 1560 |
"UB": {
|
| 1561 |
-
"accuracy": 0.
|
| 1562 |
-
"count":
|
| 1563 |
},
|
| 1564 |
"UD": {
|
| 1565 |
-
"accuracy":
|
| 1566 |
-
"count":
|
| 1567 |
}
|
| 1568 |
}
|
| 1569 |
},
|
| 1570 |
"sub_M5": {
|
| 1571 |
-
"full_accuracy": 0.
|
| 1572 |
-
"
|
|
|
|
| 1573 |
"per_subtask": {
|
| 1574 |
"MD": {
|
| 1575 |
"accuracy": 1.0,
|
| 1576 |
-
"count":
|
| 1577 |
},
|
| 1578 |
"MB": {
|
| 1579 |
"accuracy": 1.0,
|
| 1580 |
-
"count":
|
| 1581 |
},
|
| 1582 |
"UB": {
|
| 1583 |
-
"accuracy": 0.
|
| 1584 |
-
"count":
|
| 1585 |
},
|
| 1586 |
"UD": {
|
| 1587 |
-
"accuracy": 0.
|
| 1588 |
-
"count":
|
| 1589 |
}
|
| 1590 |
}
|
| 1591 |
},
|
| 1592 |
"sub_random": {
|
| 1593 |
-
"full_accuracy":
|
|
|
|
| 1594 |
"n_examples": 200,
|
| 1595 |
"per_subtask": {
|
| 1596 |
"MD": {
|
| 1597 |
-
"accuracy":
|
| 1598 |
-
"count":
|
| 1599 |
},
|
| 1600 |
"MB": {
|
| 1601 |
"accuracy": 1.0,
|
| 1602 |
-
"count":
|
| 1603 |
},
|
| 1604 |
"ME": {
|
| 1605 |
-
"accuracy":
|
| 1606 |
"count": 53
|
| 1607 |
},
|
| 1608 |
"UB": {
|
| 1609 |
"accuracy": 1.0,
|
| 1610 |
-
"count":
|
| 1611 |
},
|
| 1612 |
"UD": {
|
| 1613 |
"accuracy": 1.0,
|
| 1614 |
-
"count":
|
| 1615 |
}
|
| 1616 |
}
|
| 1617 |
},
|
| 1618 |
"sub_B3": {
|
| 1619 |
-
"full_accuracy": 0.
|
| 1620 |
-
"
|
|
|
|
| 1621 |
"per_subtask": {
|
| 1622 |
"MD": {
|
| 1623 |
-
"accuracy":
|
| 1624 |
-
"count":
|
| 1625 |
},
|
| 1626 |
"MB": {
|
| 1627 |
"accuracy": 1.0,
|
| 1628 |
-
"count":
|
| 1629 |
},
|
| 1630 |
"UB": {
|
| 1631 |
-
"accuracy": 0.
|
| 1632 |
-
"count":
|
| 1633 |
},
|
| 1634 |
"UD": {
|
| 1635 |
"accuracy": 1.0,
|
| 1636 |
-
"count":
|
| 1637 |
}
|
| 1638 |
}
|
| 1639 |
},
|
| 1640 |
"sub_B4": {
|
| 1641 |
-
"full_accuracy":
|
| 1642 |
-
"
|
|
|
|
| 1643 |
"per_subtask": {
|
| 1644 |
"MD": {
|
| 1645 |
"accuracy": 1.0,
|
| 1646 |
-
"count":
|
| 1647 |
},
|
| 1648 |
"MB": {
|
| 1649 |
"accuracy": 1.0,
|
| 1650 |
-
"count":
|
| 1651 |
},
|
| 1652 |
"UB": {
|
| 1653 |
-
"accuracy":
|
| 1654 |
-
"count":
|
| 1655 |
},
|
| 1656 |
"UD": {
|
| 1657 |
-
"accuracy":
|
| 1658 |
-
"count":
|
| 1659 |
}
|
| 1660 |
}
|
| 1661 |
},
|
| 1662 |
"sub_B5": {
|
| 1663 |
-
"full_accuracy":
|
| 1664 |
-
"
|
|
|
|
| 1665 |
"per_subtask": {
|
| 1666 |
"MD": {
|
| 1667 |
"accuracy": 1.0,
|
| 1668 |
-
"count":
|
| 1669 |
},
|
| 1670 |
"MB": {
|
| 1671 |
"accuracy": 1.0,
|
| 1672 |
-
"count":
|
| 1673 |
},
|
| 1674 |
"UB": {
|
| 1675 |
-
"accuracy":
|
| 1676 |
-
"count":
|
| 1677 |
},
|
| 1678 |
"UD": {
|
| 1679 |
"accuracy": 1.0,
|
| 1680 |
-
"count":
|
| 1681 |
}
|
| 1682 |
}
|
| 1683 |
}
|
| 1684 |
},
|
| 1685 |
"summary": {
|
| 1686 |
-
"overall_accuracy": 0.
|
| 1687 |
-
"
|
| 1688 |
-
"
|
|
|
|
| 1689 |
}
|
| 1690 |
},
|
| 1691 |
"sorl_eval": {
|
|
@@ -1694,416 +1759,477 @@
|
|
| 1694 |
"K": 1,
|
| 1695 |
"mode": "sorl",
|
| 1696 |
"n_digits": 6,
|
| 1697 |
-
"n_per_split":
|
| 1698 |
},
|
| 1699 |
"splits": {
|
| 1700 |
"add_S0": {
|
| 1701 |
"full_accuracy": 1.0,
|
| 1702 |
-
"
|
|
|
|
| 1703 |
"per_subtask": {
|
| 1704 |
"SA": {
|
| 1705 |
"accuracy": 1.0,
|
| 1706 |
-
"count":
|
| 1707 |
},
|
| 1708 |
"SS": {
|
| 1709 |
"accuracy": 1.0,
|
| 1710 |
-
"count":
|
| 1711 |
}
|
| 1712 |
}
|
| 1713 |
},
|
| 1714 |
"add_S1": {
|
| 1715 |
"full_accuracy": 1.0,
|
| 1716 |
-
"
|
|
|
|
| 1717 |
"per_subtask": {
|
| 1718 |
"SA": {
|
| 1719 |
"accuracy": 1.0,
|
| 1720 |
-
"count":
|
| 1721 |
},
|
| 1722 |
"SC": {
|
| 1723 |
"accuracy": 1.0,
|
| 1724 |
-
"count":
|
| 1725 |
},
|
| 1726 |
"SS": {
|
| 1727 |
"accuracy": 1.0,
|
| 1728 |
-
"count":
|
| 1729 |
},
|
| 1730 |
"UC": {
|
| 1731 |
"accuracy": 1.0,
|
| 1732 |
-
"count":
|
| 1733 |
}
|
| 1734 |
}
|
| 1735 |
},
|
| 1736 |
"add_S2": {
|
| 1737 |
"full_accuracy": 1.0,
|
| 1738 |
-
"
|
|
|
|
| 1739 |
"per_subtask": {
|
| 1740 |
"SA": {
|
| 1741 |
"accuracy": 1.0,
|
| 1742 |
-
"count":
|
| 1743 |
},
|
| 1744 |
"SC": {
|
| 1745 |
"accuracy": 1.0,
|
| 1746 |
-
"count":
|
| 1747 |
},
|
| 1748 |
"SS": {
|
| 1749 |
"accuracy": 1.0,
|
| 1750 |
-
"count":
|
| 1751 |
},
|
| 1752 |
"UC": {
|
| 1753 |
"accuracy": 1.0,
|
| 1754 |
-
"count":
|
| 1755 |
},
|
| 1756 |
"US": {
|
| 1757 |
"accuracy": 1.0,
|
| 1758 |
-
"count":
|
| 1759 |
}
|
| 1760 |
}
|
| 1761 |
},
|
| 1762 |
"add_S3": {
|
| 1763 |
-
"full_accuracy":
|
| 1764 |
-
"
|
|
|
|
| 1765 |
"per_subtask": {
|
| 1766 |
"SA": {
|
| 1767 |
"accuracy": 1.0,
|
| 1768 |
-
"count":
|
| 1769 |
},
|
| 1770 |
"SC": {
|
| 1771 |
"accuracy": 1.0,
|
| 1772 |
-
"count":
|
| 1773 |
},
|
| 1774 |
"SS": {
|
| 1775 |
"accuracy": 1.0,
|
| 1776 |
-
"count":
|
| 1777 |
},
|
| 1778 |
"UC": {
|
| 1779 |
-
"accuracy":
|
| 1780 |
-
"count":
|
| 1781 |
},
|
| 1782 |
"US": {
|
| 1783 |
"accuracy": 1.0,
|
| 1784 |
-
"count":
|
| 1785 |
}
|
| 1786 |
}
|
| 1787 |
},
|
| 1788 |
"add_S4": {
|
| 1789 |
"full_accuracy": 1.0,
|
| 1790 |
-
"
|
|
|
|
| 1791 |
"per_subtask": {
|
| 1792 |
"SA": {
|
| 1793 |
"accuracy": 1.0,
|
| 1794 |
-
"count":
|
| 1795 |
},
|
| 1796 |
"SC": {
|
| 1797 |
"accuracy": 1.0,
|
| 1798 |
-
"count":
|
| 1799 |
},
|
| 1800 |
"SS": {
|
| 1801 |
"accuracy": 1.0,
|
| 1802 |
-
"count":
|
| 1803 |
},
|
| 1804 |
"UC": {
|
| 1805 |
"accuracy": 1.0,
|
| 1806 |
-
"count":
|
| 1807 |
},
|
| 1808 |
"US": {
|
| 1809 |
"accuracy": 1.0,
|
| 1810 |
-
"count":
|
| 1811 |
}
|
| 1812 |
}
|
| 1813 |
},
|
| 1814 |
"add_S5": {
|
| 1815 |
"full_accuracy": 0.96,
|
| 1816 |
-
"
|
|
|
|
| 1817 |
"per_subtask": {
|
| 1818 |
"SA": {
|
| 1819 |
"accuracy": 1.0,
|
| 1820 |
-
"count":
|
| 1821 |
},
|
| 1822 |
"SC": {
|
| 1823 |
"accuracy": 1.0,
|
| 1824 |
-
"count":
|
| 1825 |
},
|
| 1826 |
"UC": {
|
| 1827 |
"accuracy": 0.96,
|
| 1828 |
-
"count":
|
| 1829 |
},
|
| 1830 |
"US": {
|
| 1831 |
"accuracy": 1.0,
|
| 1832 |
-
"count":
|
| 1833 |
}
|
| 1834 |
}
|
| 1835 |
},
|
| 1836 |
"add_S6": {
|
| 1837 |
-
"full_accuracy": 0.
|
| 1838 |
-
"
|
|
|
|
| 1839 |
"per_subtask": {
|
| 1840 |
"SC": {
|
| 1841 |
"accuracy": 1.0,
|
| 1842 |
-
"count":
|
| 1843 |
},
|
| 1844 |
"UC": {
|
| 1845 |
-
"accuracy": 0.
|
| 1846 |
-
"count":
|
| 1847 |
},
|
| 1848 |
"US": {
|
| 1849 |
-
"accuracy": 0.
|
| 1850 |
-
"count":
|
| 1851 |
}
|
| 1852 |
}
|
| 1853 |
},
|
| 1854 |
"add_random": {
|
| 1855 |
-
"full_accuracy":
|
|
|
|
| 1856 |
"n_examples": 200,
|
| 1857 |
"per_subtask": {
|
| 1858 |
"SA": {
|
| 1859 |
"accuracy": 1.0,
|
| 1860 |
-
"count":
|
| 1861 |
},
|
| 1862 |
"SC": {
|
| 1863 |
"accuracy": 1.0,
|
| 1864 |
-
"count":
|
| 1865 |
},
|
| 1866 |
"SS": {
|
| 1867 |
"accuracy": 1.0,
|
| 1868 |
-
"count":
|
| 1869 |
},
|
| 1870 |
"UC": {
|
| 1871 |
-
"accuracy":
|
| 1872 |
-
"count":
|
| 1873 |
},
|
| 1874 |
"US": {
|
| 1875 |
"accuracy": 1.0,
|
| 1876 |
-
"count":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1877 |
}
|
| 1878 |
}
|
| 1879 |
},
|
| 1880 |
"add_C3": {
|
| 1881 |
"full_accuracy": 1.0,
|
| 1882 |
-
"
|
|
|
|
| 1883 |
"per_subtask": {
|
| 1884 |
"SA": {
|
| 1885 |
"accuracy": 1.0,
|
| 1886 |
-
"count":
|
| 1887 |
},
|
| 1888 |
"SC": {
|
| 1889 |
"accuracy": 1.0,
|
| 1890 |
-
"count":
|
| 1891 |
},
|
| 1892 |
"UC": {
|
| 1893 |
"accuracy": 1.0,
|
| 1894 |
-
"count":
|
| 1895 |
},
|
| 1896 |
"US": {
|
| 1897 |
"accuracy": 1.0,
|
| 1898 |
-
"count":
|
| 1899 |
}
|
| 1900 |
}
|
| 1901 |
},
|
| 1902 |
"add_C4": {
|
| 1903 |
"full_accuracy": 1.0,
|
| 1904 |
-
"
|
|
|
|
| 1905 |
"per_subtask": {
|
| 1906 |
"SA": {
|
| 1907 |
"accuracy": 1.0,
|
| 1908 |
-
"count":
|
| 1909 |
},
|
| 1910 |
"SC": {
|
| 1911 |
"accuracy": 1.0,
|
| 1912 |
-
"count":
|
| 1913 |
},
|
| 1914 |
"UC": {
|
| 1915 |
"accuracy": 1.0,
|
| 1916 |
-
"count":
|
| 1917 |
},
|
| 1918 |
"US": {
|
| 1919 |
"accuracy": 1.0,
|
| 1920 |
-
"count":
|
| 1921 |
}
|
| 1922 |
}
|
| 1923 |
},
|
| 1924 |
"add_C5": {
|
| 1925 |
"full_accuracy": 1.0,
|
| 1926 |
-
"
|
|
|
|
| 1927 |
"per_subtask": {
|
| 1928 |
"SA": {
|
| 1929 |
"accuracy": 1.0,
|
| 1930 |
-
"count":
|
| 1931 |
},
|
| 1932 |
"SC": {
|
| 1933 |
"accuracy": 1.0,
|
| 1934 |
-
"count":
|
| 1935 |
},
|
| 1936 |
"UC": {
|
| 1937 |
"accuracy": 1.0,
|
| 1938 |
-
"count":
|
| 1939 |
},
|
| 1940 |
"US": {
|
| 1941 |
"accuracy": 1.0,
|
| 1942 |
-
"count":
|
| 1943 |
}
|
| 1944 |
}
|
| 1945 |
},
|
| 1946 |
"add_C6": {
|
| 1947 |
-
"full_accuracy":
|
| 1948 |
-
"
|
|
|
|
| 1949 |
"per_subtask": {
|
| 1950 |
"SC": {
|
| 1951 |
"accuracy": 1.0,
|
| 1952 |
-
"count":
|
| 1953 |
},
|
| 1954 |
"UC": {
|
| 1955 |
-
"accuracy":
|
| 1956 |
-
"count":
|
| 1957 |
},
|
| 1958 |
"US": {
|
| 1959 |
"accuracy": 1.0,
|
| 1960 |
-
"count":
|
| 1961 |
}
|
| 1962 |
}
|
| 1963 |
},
|
| 1964 |
"sub_M0": {
|
| 1965 |
"full_accuracy": 1.0,
|
| 1966 |
-
"
|
|
|
|
| 1967 |
"per_subtask": {
|
| 1968 |
"MD": {
|
| 1969 |
"accuracy": 1.0,
|
| 1970 |
-
"count":
|
| 1971 |
},
|
| 1972 |
"ME": {
|
| 1973 |
"accuracy": 1.0,
|
| 1974 |
-
"count":
|
| 1975 |
}
|
| 1976 |
}
|
| 1977 |
},
|
| 1978 |
"sub_M1": {
|
| 1979 |
"full_accuracy": 1.0,
|
| 1980 |
-
"
|
|
|
|
| 1981 |
"per_subtask": {
|
| 1982 |
"MD": {
|
| 1983 |
"accuracy": 1.0,
|
| 1984 |
-
"count":
|
| 1985 |
},
|
| 1986 |
"MB": {
|
| 1987 |
"accuracy": 1.0,
|
| 1988 |
-
"count":
|
| 1989 |
},
|
| 1990 |
"ME": {
|
| 1991 |
"accuracy": 1.0,
|
| 1992 |
-
"count":
|
| 1993 |
},
|
| 1994 |
"UB": {
|
| 1995 |
"accuracy": 1.0,
|
| 1996 |
-
"count":
|
| 1997 |
}
|
| 1998 |
}
|
| 1999 |
},
|
| 2000 |
"sub_M2": {
|
| 2001 |
"full_accuracy": 1.0,
|
| 2002 |
-
"
|
|
|
|
| 2003 |
"per_subtask": {
|
| 2004 |
"MD": {
|
| 2005 |
"accuracy": 1.0,
|
| 2006 |
-
"count":
|
| 2007 |
},
|
| 2008 |
"MB": {
|
| 2009 |
"accuracy": 1.0,
|
| 2010 |
-
"count":
|
| 2011 |
},
|
| 2012 |
"ME": {
|
| 2013 |
"accuracy": 1.0,
|
| 2014 |
-
"count":
|
| 2015 |
},
|
| 2016 |
"UB": {
|
| 2017 |
"accuracy": 1.0,
|
| 2018 |
-
"count":
|
| 2019 |
},
|
| 2020 |
"UD": {
|
| 2021 |
"accuracy": 1.0,
|
| 2022 |
-
"count":
|
| 2023 |
}
|
| 2024 |
}
|
| 2025 |
},
|
| 2026 |
"sub_M3": {
|
| 2027 |
"full_accuracy": 1.0,
|
| 2028 |
-
"
|
|
|
|
| 2029 |
"per_subtask": {
|
| 2030 |
"MD": {
|
| 2031 |
"accuracy": 1.0,
|
| 2032 |
-
"count":
|
| 2033 |
},
|
| 2034 |
"MB": {
|
| 2035 |
"accuracy": 1.0,
|
| 2036 |
-
"count":
|
| 2037 |
},
|
| 2038 |
"ME": {
|
| 2039 |
"accuracy": 1.0,
|
| 2040 |
-
"count":
|
| 2041 |
},
|
| 2042 |
"UB": {
|
| 2043 |
"accuracy": 1.0,
|
| 2044 |
-
"count":
|
| 2045 |
},
|
| 2046 |
"UD": {
|
| 2047 |
"accuracy": 1.0,
|
| 2048 |
-
"count":
|
| 2049 |
}
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"sub_M4": {
|
| 2053 |
"full_accuracy": 1.0,
|
| 2054 |
-
"
|
|
|
|
| 2055 |
"per_subtask": {
|
| 2056 |
"MD": {
|
| 2057 |
"accuracy": 1.0,
|
| 2058 |
-
"count":
|
| 2059 |
},
|
| 2060 |
"MB": {
|
| 2061 |
"accuracy": 1.0,
|
| 2062 |
-
"count":
|
| 2063 |
},
|
| 2064 |
"UB": {
|
| 2065 |
"accuracy": 1.0,
|
| 2066 |
-
"count":
|
| 2067 |
},
|
| 2068 |
"UD": {
|
| 2069 |
"accuracy": 1.0,
|
| 2070 |
-
"count":
|
| 2071 |
}
|
| 2072 |
}
|
| 2073 |
},
|
| 2074 |
"sub_M5": {
|
| 2075 |
-
"full_accuracy": 0.
|
| 2076 |
-
"
|
|
|
|
| 2077 |
"per_subtask": {
|
| 2078 |
"MD": {
|
| 2079 |
"accuracy": 1.0,
|
| 2080 |
-
"count":
|
| 2081 |
},
|
| 2082 |
"MB": {
|
| 2083 |
"accuracy": 1.0,
|
| 2084 |
-
"count":
|
| 2085 |
},
|
| 2086 |
"UB": {
|
| 2087 |
-
"accuracy": 0.
|
| 2088 |
-
"count":
|
| 2089 |
},
|
| 2090 |
"UD": {
|
| 2091 |
-
"accuracy":
|
| 2092 |
-
"count":
|
| 2093 |
}
|
| 2094 |
}
|
| 2095 |
},
|
| 2096 |
"sub_random": {
|
| 2097 |
-
"full_accuracy":
|
|
|
|
| 2098 |
"n_examples": 200,
|
| 2099 |
"per_subtask": {
|
| 2100 |
"MD": {
|
| 2101 |
-
"accuracy":
|
| 2102 |
-
"count":
|
| 2103 |
},
|
| 2104 |
"MB": {
|
| 2105 |
"accuracy": 1.0,
|
| 2106 |
-
"count":
|
| 2107 |
},
|
| 2108 |
"ME": {
|
| 2109 |
"accuracy": 1.0,
|
|
@@ -2111,85 +2237,89 @@
|
|
| 2111 |
},
|
| 2112 |
"UB": {
|
| 2113 |
"accuracy": 1.0,
|
| 2114 |
-
"count":
|
| 2115 |
},
|
| 2116 |
"UD": {
|
| 2117 |
"accuracy": 1.0,
|
| 2118 |
-
"count":
|
| 2119 |
}
|
| 2120 |
}
|
| 2121 |
},
|
| 2122 |
"sub_B3": {
|
| 2123 |
"full_accuracy": 1.0,
|
| 2124 |
-
"
|
|
|
|
| 2125 |
"per_subtask": {
|
| 2126 |
"MD": {
|
| 2127 |
"accuracy": 1.0,
|
| 2128 |
-
"count":
|
| 2129 |
},
|
| 2130 |
"MB": {
|
| 2131 |
"accuracy": 1.0,
|
| 2132 |
-
"count":
|
| 2133 |
},
|
| 2134 |
"UB": {
|
| 2135 |
"accuracy": 1.0,
|
| 2136 |
-
"count":
|
| 2137 |
},
|
| 2138 |
"UD": {
|
| 2139 |
"accuracy": 1.0,
|
| 2140 |
-
"count":
|
| 2141 |
}
|
| 2142 |
}
|
| 2143 |
},
|
| 2144 |
"sub_B4": {
|
| 2145 |
"full_accuracy": 1.0,
|
| 2146 |
-
"
|
|
|
|
| 2147 |
"per_subtask": {
|
| 2148 |
"MD": {
|
| 2149 |
"accuracy": 1.0,
|
| 2150 |
-
"count":
|
| 2151 |
},
|
| 2152 |
"MB": {
|
| 2153 |
"accuracy": 1.0,
|
| 2154 |
-
"count":
|
| 2155 |
},
|
| 2156 |
"UB": {
|
| 2157 |
"accuracy": 1.0,
|
| 2158 |
-
"count":
|
| 2159 |
},
|
| 2160 |
"UD": {
|
| 2161 |
"accuracy": 1.0,
|
| 2162 |
-
"count":
|
| 2163 |
}
|
| 2164 |
}
|
| 2165 |
},
|
| 2166 |
"sub_B5": {
|
| 2167 |
-
"full_accuracy": 0.
|
| 2168 |
-
"
|
|
|
|
| 2169 |
"per_subtask": {
|
| 2170 |
"MD": {
|
| 2171 |
"accuracy": 1.0,
|
| 2172 |
-
"count":
|
| 2173 |
},
|
| 2174 |
"MB": {
|
| 2175 |
"accuracy": 1.0,
|
| 2176 |
-
"count":
|
| 2177 |
},
|
| 2178 |
"UB": {
|
| 2179 |
-
"accuracy": 0.
|
| 2180 |
-
"count":
|
| 2181 |
},
|
| 2182 |
"UD": {
|
| 2183 |
"accuracy": 1.0,
|
| 2184 |
-
"count":
|
| 2185 |
}
|
| 2186 |
}
|
| 2187 |
}
|
| 2188 |
},
|
| 2189 |
"summary": {
|
| 2190 |
-
"overall_accuracy": 0.
|
| 2191 |
-
"
|
| 2192 |
-
"
|
|
|
|
| 2193 |
}
|
| 2194 |
},
|
| 2195 |
"sorl_overall_accuracy": 0.985,
|
|
|
|
| 1190 |
"K": null,
|
| 1191 |
"mode": "sft",
|
| 1192 |
"n_digits": 6,
|
| 1193 |
+
"n_per_split": 50
|
| 1194 |
},
|
| 1195 |
"splits": {
|
| 1196 |
"add_S0": {
|
| 1197 |
"full_accuracy": 1.0,
|
| 1198 |
+
"digit_accuracy": 1.0,
|
| 1199 |
+
"n_examples": 50,
|
| 1200 |
"per_subtask": {
|
| 1201 |
"SA": {
|
| 1202 |
"accuracy": 1.0,
|
| 1203 |
+
"count": 295
|
| 1204 |
},
|
| 1205 |
"SS": {
|
| 1206 |
"accuracy": 1.0,
|
| 1207 |
+
"count": 55
|
| 1208 |
}
|
| 1209 |
}
|
| 1210 |
},
|
| 1211 |
"add_S1": {
|
| 1212 |
"full_accuracy": 1.0,
|
| 1213 |
+
"digit_accuracy": 1.0,
|
| 1214 |
+
"n_examples": 50,
|
| 1215 |
"per_subtask": {
|
| 1216 |
"SA": {
|
| 1217 |
"accuracy": 1.0,
|
| 1218 |
+
"count": 126
|
| 1219 |
},
|
| 1220 |
"SC": {
|
| 1221 |
"accuracy": 1.0,
|
| 1222 |
+
"count": 79
|
| 1223 |
},
|
| 1224 |
"SS": {
|
| 1225 |
"accuracy": 1.0,
|
| 1226 |
+
"count": 21
|
| 1227 |
},
|
| 1228 |
"UC": {
|
| 1229 |
"accuracy": 1.0,
|
| 1230 |
+
"count": 124
|
| 1231 |
}
|
| 1232 |
}
|
| 1233 |
},
|
| 1234 |
"add_S2": {
|
| 1235 |
"full_accuracy": 1.0,
|
| 1236 |
+
"digit_accuracy": 1.0,
|
| 1237 |
+
"n_examples": 50,
|
| 1238 |
"per_subtask": {
|
| 1239 |
"SA": {
|
| 1240 |
"accuracy": 1.0,
|
| 1241 |
+
"count": 75
|
| 1242 |
},
|
| 1243 |
"SC": {
|
| 1244 |
"accuracy": 1.0,
|
| 1245 |
+
"count": 62
|
| 1246 |
},
|
| 1247 |
"SS": {
|
| 1248 |
"accuracy": 1.0,
|
| 1249 |
+
"count": 39
|
| 1250 |
},
|
| 1251 |
"UC": {
|
| 1252 |
"accuracy": 1.0,
|
| 1253 |
+
"count": 111
|
| 1254 |
},
|
| 1255 |
"US": {
|
| 1256 |
"accuracy": 1.0,
|
| 1257 |
+
"count": 63
|
| 1258 |
}
|
| 1259 |
}
|
| 1260 |
},
|
| 1261 |
"add_S3": {
|
| 1262 |
+
"full_accuracy": 1.0,
|
| 1263 |
+
"digit_accuracy": 1.0,
|
| 1264 |
+
"n_examples": 50,
|
| 1265 |
"per_subtask": {
|
| 1266 |
"SA": {
|
| 1267 |
"accuracy": 1.0,
|
| 1268 |
+
"count": 60
|
| 1269 |
},
|
| 1270 |
"SC": {
|
| 1271 |
"accuracy": 1.0,
|
| 1272 |
+
"count": 57
|
| 1273 |
},
|
| 1274 |
"SS": {
|
| 1275 |
"accuracy": 1.0,
|
| 1276 |
+
"count": 19
|
| 1277 |
},
|
| 1278 |
"UC": {
|
| 1279 |
+
"accuracy": 1.0,
|
| 1280 |
+
"count": 104
|
| 1281 |
},
|
| 1282 |
"US": {
|
| 1283 |
"accuracy": 1.0,
|
| 1284 |
+
"count": 110
|
| 1285 |
}
|
| 1286 |
}
|
| 1287 |
},
|
| 1288 |
"add_S4": {
|
| 1289 |
+
"full_accuracy": 0.72,
|
| 1290 |
+
"digit_accuracy": 0.9485714285714286,
|
| 1291 |
+
"n_examples": 50,
|
| 1292 |
"per_subtask": {
|
| 1293 |
"SA": {
|
| 1294 |
"accuracy": 1.0,
|
| 1295 |
+
"count": 48
|
| 1296 |
},
|
| 1297 |
"SC": {
|
| 1298 |
"accuracy": 1.0,
|
| 1299 |
+
"count": 52
|
| 1300 |
},
|
| 1301 |
"SS": {
|
| 1302 |
"accuracy": 1.0,
|
| 1303 |
+
"count": 7
|
| 1304 |
},
|
| 1305 |
"UC": {
|
| 1306 |
+
"accuracy": 0.8426966292134831,
|
| 1307 |
+
"count": 89
|
| 1308 |
},
|
| 1309 |
"US": {
|
| 1310 |
+
"accuracy": 0.974025974025974,
|
| 1311 |
+
"count": 154
|
| 1312 |
}
|
| 1313 |
}
|
| 1314 |
},
|
| 1315 |
"add_S5": {
|
| 1316 |
+
"full_accuracy": 0.4,
|
| 1317 |
+
"digit_accuracy": 0.8285714285714286,
|
| 1318 |
+
"n_examples": 50,
|
| 1319 |
"per_subtask": {
|
| 1320 |
"SA": {
|
| 1321 |
"accuracy": 1.0,
|
| 1322 |
+
"count": 50
|
| 1323 |
},
|
| 1324 |
"SC": {
|
| 1325 |
"accuracy": 1.0,
|
| 1326 |
+
"count": 50
|
| 1327 |
},
|
| 1328 |
"UC": {
|
| 1329 |
+
"accuracy": 0.48,
|
| 1330 |
+
"count": 50
|
| 1331 |
},
|
| 1332 |
"US": {
|
| 1333 |
+
"accuracy": 0.83,
|
| 1334 |
+
"count": 200
|
| 1335 |
}
|
| 1336 |
}
|
| 1337 |
},
|
| 1338 |
"add_S6": {
|
| 1339 |
+
"full_accuracy": 0.52,
|
| 1340 |
+
"digit_accuracy": 0.8314285714285714,
|
| 1341 |
+
"n_examples": 50,
|
| 1342 |
"per_subtask": {
|
| 1343 |
"SC": {
|
| 1344 |
"accuracy": 1.0,
|
| 1345 |
+
"count": 50
|
| 1346 |
},
|
| 1347 |
"UC": {
|
| 1348 |
+
"accuracy": 0.66,
|
| 1349 |
+
"count": 50
|
| 1350 |
},
|
| 1351 |
"US": {
|
| 1352 |
+
"accuracy": 0.832,
|
| 1353 |
+
"count": 250
|
| 1354 |
}
|
| 1355 |
}
|
| 1356 |
},
|
| 1357 |
"add_random": {
|
| 1358 |
+
"full_accuracy": 0.995,
|
| 1359 |
+
"digit_accuracy": 0.9992857142857143,
|
| 1360 |
"n_examples": 200,
|
| 1361 |
"per_subtask": {
|
| 1362 |
"SA": {
|
| 1363 |
"accuracy": 1.0,
|
| 1364 |
+
"count": 431
|
| 1365 |
},
|
| 1366 |
"SC": {
|
| 1367 |
"accuracy": 1.0,
|
| 1368 |
+
"count": 316
|
| 1369 |
},
|
| 1370 |
"SS": {
|
| 1371 |
"accuracy": 1.0,
|
| 1372 |
+
"count": 39
|
| 1373 |
},
|
| 1374 |
"UC": {
|
| 1375 |
+
"accuracy": 0.9982142857142857,
|
| 1376 |
+
"count": 560
|
| 1377 |
},
|
| 1378 |
"US": {
|
| 1379 |
"accuracy": 1.0,
|
| 1380 |
+
"count": 54
|
| 1381 |
+
}
|
| 1382 |
+
}
|
| 1383 |
+
},
|
| 1384 |
+
"add_C1": {
|
| 1385 |
+
"full_accuracy": 1.0,
|
| 1386 |
+
"digit_accuracy": 1.0,
|
| 1387 |
+
"n_examples": 50,
|
| 1388 |
+
"per_subtask": {
|
| 1389 |
+
"SA": {
|
| 1390 |
+
"accuracy": 1.0,
|
| 1391 |
+
"count": 250
|
| 1392 |
+
},
|
| 1393 |
+
"SC": {
|
| 1394 |
+
"accuracy": 1.0,
|
| 1395 |
+
"count": 50
|
| 1396 |
+
},
|
| 1397 |
+
"UC": {
|
| 1398 |
+
"accuracy": 1.0,
|
| 1399 |
+
"count": 50
|
| 1400 |
+
}
|
| 1401 |
+
}
|
| 1402 |
+
},
|
| 1403 |
+
"add_C2": {
|
| 1404 |
+
"full_accuracy": 0.96,
|
| 1405 |
+
"digit_accuracy": 0.9885714285714285,
|
| 1406 |
+
"n_examples": 50,
|
| 1407 |
+
"per_subtask": {
|
| 1408 |
+
"SA": {
|
| 1409 |
+
"accuracy": 1.0,
|
| 1410 |
+
"count": 200
|
| 1411 |
+
},
|
| 1412 |
+
"SC": {
|
| 1413 |
+
"accuracy": 1.0,
|
| 1414 |
+
"count": 50
|
| 1415 |
+
},
|
| 1416 |
+
"UC": {
|
| 1417 |
+
"accuracy": 0.9759036144578314,
|
| 1418 |
+
"count": 83
|
| 1419 |
+
},
|
| 1420 |
+
"US": {
|
| 1421 |
+
"accuracy": 0.8823529411764706,
|
| 1422 |
+
"count": 17
|
| 1423 |
}
|
| 1424 |
}
|
| 1425 |
},
|
| 1426 |
"add_C3": {
|
| 1427 |
+
"full_accuracy": 1.0,
|
| 1428 |
+
"digit_accuracy": 1.0,
|
| 1429 |
+
"n_examples": 50,
|
| 1430 |
"per_subtask": {
|
| 1431 |
"SA": {
|
| 1432 |
"accuracy": 1.0,
|
| 1433 |
+
"count": 150
|
| 1434 |
},
|
| 1435 |
"SC": {
|
| 1436 |
"accuracy": 1.0,
|
| 1437 |
+
"count": 50
|
| 1438 |
},
|
| 1439 |
"UC": {
|
| 1440 |
+
"accuracy": 1.0,
|
| 1441 |
+
"count": 100
|
| 1442 |
},
|
| 1443 |
"US": {
|
| 1444 |
"accuracy": 1.0,
|
| 1445 |
+
"count": 50
|
| 1446 |
}
|
| 1447 |
}
|
| 1448 |
},
|
| 1449 |
"add_C4": {
|
| 1450 |
+
"full_accuracy": 0.9,
|
| 1451 |
+
"digit_accuracy": 0.98,
|
| 1452 |
+
"n_examples": 50,
|
| 1453 |
"per_subtask": {
|
| 1454 |
"SA": {
|
| 1455 |
"accuracy": 1.0,
|
| 1456 |
+
"count": 100
|
| 1457 |
},
|
| 1458 |
"SC": {
|
| 1459 |
"accuracy": 1.0,
|
| 1460 |
+
"count": 50
|
| 1461 |
},
|
| 1462 |
"UC": {
|
| 1463 |
+
"accuracy": 0.9621212121212122,
|
| 1464 |
+
"count": 132
|
| 1465 |
},
|
| 1466 |
"US": {
|
| 1467 |
+
"accuracy": 0.9705882352941176,
|
| 1468 |
+
"count": 68
|
| 1469 |
}
|
| 1470 |
}
|
| 1471 |
},
|
| 1472 |
"add_C5": {
|
| 1473 |
+
"full_accuracy": 0.86,
|
| 1474 |
+
"digit_accuracy": 0.9742857142857143,
|
| 1475 |
+
"n_examples": 50,
|
| 1476 |
"per_subtask": {
|
| 1477 |
"SA": {
|
| 1478 |
"accuracy": 1.0,
|
| 1479 |
+
"count": 50
|
| 1480 |
},
|
| 1481 |
"SC": {
|
| 1482 |
"accuracy": 1.0,
|
| 1483 |
+
"count": 50
|
| 1484 |
},
|
| 1485 |
"UC": {
|
| 1486 |
+
"accuracy": 0.9726027397260274,
|
| 1487 |
+
"count": 146
|
| 1488 |
},
|
| 1489 |
"US": {
|
| 1490 |
+
"accuracy": 0.9519230769230769,
|
| 1491 |
+
"count": 104
|
| 1492 |
}
|
| 1493 |
}
|
| 1494 |
},
|
| 1495 |
"add_C6": {
|
| 1496 |
+
"full_accuracy": 0.98,
|
| 1497 |
+
"digit_accuracy": 0.9914285714285714,
|
| 1498 |
+
"n_examples": 50,
|
| 1499 |
"per_subtask": {
|
| 1500 |
"SC": {
|
| 1501 |
"accuracy": 1.0,
|
| 1502 |
+
"count": 50
|
| 1503 |
},
|
| 1504 |
"UC": {
|
| 1505 |
+
"accuracy": 0.9947089947089947,
|
| 1506 |
+
"count": 189
|
| 1507 |
},
|
| 1508 |
"US": {
|
| 1509 |
+
"accuracy": 0.9819819819819819,
|
| 1510 |
+
"count": 111
|
| 1511 |
}
|
| 1512 |
}
|
| 1513 |
},
|
| 1514 |
"sub_M0": {
|
| 1515 |
+
"full_accuracy": 1.0,
|
| 1516 |
+
"digit_accuracy": 1.0,
|
| 1517 |
+
"n_examples": 50,
|
| 1518 |
"per_subtask": {
|
| 1519 |
"MD": {
|
| 1520 |
+
"accuracy": 1.0,
|
| 1521 |
+
"count": 303
|
| 1522 |
},
|
| 1523 |
"ME": {
|
| 1524 |
"accuracy": 1.0,
|
| 1525 |
+
"count": 47
|
| 1526 |
}
|
| 1527 |
}
|
| 1528 |
},
|
| 1529 |
"sub_M1": {
|
| 1530 |
+
"full_accuracy": 0.98,
|
| 1531 |
+
"digit_accuracy": 0.9971428571428571,
|
| 1532 |
+
"n_examples": 50,
|
| 1533 |
"per_subtask": {
|
| 1534 |
"MD": {
|
| 1535 |
+
"accuracy": 0.9929078014184397,
|
| 1536 |
+
"count": 141
|
| 1537 |
},
|
| 1538 |
"MB": {
|
| 1539 |
"accuracy": 1.0,
|
| 1540 |
+
"count": 72
|
| 1541 |
},
|
| 1542 |
"ME": {
|
| 1543 |
"accuracy": 1.0,
|
| 1544 |
+
"count": 18
|
| 1545 |
},
|
| 1546 |
"UB": {
|
| 1547 |
"accuracy": 1.0,
|
| 1548 |
+
"count": 119
|
| 1549 |
}
|
| 1550 |
}
|
| 1551 |
},
|
| 1552 |
"sub_M2": {
|
| 1553 |
"full_accuracy": 1.0,
|
| 1554 |
+
"digit_accuracy": 1.0,
|
| 1555 |
+
"n_examples": 50,
|
| 1556 |
"per_subtask": {
|
| 1557 |
"MD": {
|
| 1558 |
"accuracy": 1.0,
|
| 1559 |
+
"count": 112
|
| 1560 |
},
|
| 1561 |
"MB": {
|
| 1562 |
"accuracy": 1.0,
|
| 1563 |
+
"count": 53
|
| 1564 |
},
|
| 1565 |
"ME": {
|
| 1566 |
"accuracy": 1.0,
|
| 1567 |
+
"count": 47
|
| 1568 |
},
|
| 1569 |
"UB": {
|
| 1570 |
"accuracy": 1.0,
|
| 1571 |
+
"count": 85
|
| 1572 |
},
|
| 1573 |
"UD": {
|
| 1574 |
"accuracy": 1.0,
|
| 1575 |
+
"count": 53
|
| 1576 |
}
|
| 1577 |
}
|
| 1578 |
},
|
| 1579 |
"sub_M3": {
|
| 1580 |
+
"full_accuracy": 1.0,
|
| 1581 |
+
"digit_accuracy": 1.0,
|
| 1582 |
+
"n_examples": 50,
|
| 1583 |
"per_subtask": {
|
| 1584 |
"MD": {
|
| 1585 |
"accuracy": 1.0,
|
| 1586 |
+
"count": 97
|
| 1587 |
},
|
| 1588 |
"MB": {
|
| 1589 |
"accuracy": 1.0,
|
| 1590 |
+
"count": 51
|
| 1591 |
},
|
| 1592 |
"ME": {
|
| 1593 |
"accuracy": 1.0,
|
| 1594 |
+
"count": 27
|
| 1595 |
},
|
| 1596 |
"UB": {
|
| 1597 |
+
"accuracy": 1.0,
|
| 1598 |
+
"count": 74
|
| 1599 |
},
|
| 1600 |
"UD": {
|
| 1601 |
"accuracy": 1.0,
|
| 1602 |
+
"count": 101
|
| 1603 |
}
|
| 1604 |
}
|
| 1605 |
},
|
| 1606 |
"sub_M4": {
|
| 1607 |
+
"full_accuracy": 0.76,
|
| 1608 |
+
"digit_accuracy": 0.9657142857142857,
|
| 1609 |
+
"n_examples": 50,
|
| 1610 |
"per_subtask": {
|
| 1611 |
"MD": {
|
| 1612 |
"accuracy": 1.0,
|
| 1613 |
+
"count": 100
|
| 1614 |
},
|
| 1615 |
"MB": {
|
| 1616 |
"accuracy": 1.0,
|
| 1617 |
+
"count": 50
|
| 1618 |
},
|
| 1619 |
"UB": {
|
| 1620 |
+
"accuracy": 0.78,
|
| 1621 |
+
"count": 50
|
| 1622 |
},
|
| 1623 |
"UD": {
|
| 1624 |
+
"accuracy": 0.9933333333333333,
|
| 1625 |
+
"count": 150
|
| 1626 |
}
|
| 1627 |
}
|
| 1628 |
},
|
| 1629 |
"sub_M5": {
|
| 1630 |
+
"full_accuracy": 0.8,
|
| 1631 |
+
"digit_accuracy": 0.9685714285714285,
|
| 1632 |
+
"n_examples": 50,
|
| 1633 |
"per_subtask": {
|
| 1634 |
"MD": {
|
| 1635 |
"accuracy": 1.0,
|
| 1636 |
+
"count": 50
|
| 1637 |
},
|
| 1638 |
"MB": {
|
| 1639 |
"accuracy": 1.0,
|
| 1640 |
+
"count": 50
|
| 1641 |
},
|
| 1642 |
"UB": {
|
| 1643 |
+
"accuracy": 0.98,
|
| 1644 |
+
"count": 50
|
| 1645 |
},
|
| 1646 |
"UD": {
|
| 1647 |
+
"accuracy": 0.95,
|
| 1648 |
+
"count": 200
|
| 1649 |
}
|
| 1650 |
}
|
| 1651 |
},
|
| 1652 |
"sub_random": {
|
| 1653 |
+
"full_accuracy": 1.0,
|
| 1654 |
+
"digit_accuracy": 1.0,
|
| 1655 |
"n_examples": 200,
|
| 1656 |
"per_subtask": {
|
| 1657 |
"MD": {
|
| 1658 |
+
"accuracy": 1.0,
|
| 1659 |
+
"count": 570
|
| 1660 |
},
|
| 1661 |
"MB": {
|
| 1662 |
"accuracy": 1.0,
|
| 1663 |
+
"count": 277
|
| 1664 |
},
|
| 1665 |
"ME": {
|
| 1666 |
+
"accuracy": 1.0,
|
| 1667 |
"count": 53
|
| 1668 |
},
|
| 1669 |
"UB": {
|
| 1670 |
"accuracy": 1.0,
|
| 1671 |
+
"count": 471
|
| 1672 |
},
|
| 1673 |
"UD": {
|
| 1674 |
"accuracy": 1.0,
|
| 1675 |
+
"count": 29
|
| 1676 |
}
|
| 1677 |
}
|
| 1678 |
},
|
| 1679 |
"sub_B3": {
|
| 1680 |
+
"full_accuracy": 0.98,
|
| 1681 |
+
"digit_accuracy": 0.9971428571428571,
|
| 1682 |
+
"n_examples": 50,
|
| 1683 |
"per_subtask": {
|
| 1684 |
"MD": {
|
| 1685 |
+
"accuracy": 1.0,
|
| 1686 |
+
"count": 150
|
| 1687 |
},
|
| 1688 |
"MB": {
|
| 1689 |
"accuracy": 1.0,
|
| 1690 |
+
"count": 50
|
| 1691 |
},
|
| 1692 |
"UB": {
|
| 1693 |
+
"accuracy": 0.9900990099009901,
|
| 1694 |
+
"count": 101
|
| 1695 |
},
|
| 1696 |
"UD": {
|
| 1697 |
"accuracy": 1.0,
|
| 1698 |
+
"count": 49
|
| 1699 |
}
|
| 1700 |
}
|
| 1701 |
},
|
| 1702 |
"sub_B4": {
|
| 1703 |
+
"full_accuracy": 1.0,
|
| 1704 |
+
"digit_accuracy": 1.0,
|
| 1705 |
+
"n_examples": 50,
|
| 1706 |
"per_subtask": {
|
| 1707 |
"MD": {
|
| 1708 |
"accuracy": 1.0,
|
| 1709 |
+
"count": 100
|
| 1710 |
},
|
| 1711 |
"MB": {
|
| 1712 |
"accuracy": 1.0,
|
| 1713 |
+
"count": 50
|
| 1714 |
},
|
| 1715 |
"UB": {
|
| 1716 |
+
"accuracy": 1.0,
|
| 1717 |
+
"count": 121
|
| 1718 |
},
|
| 1719 |
"UD": {
|
| 1720 |
+
"accuracy": 1.0,
|
| 1721 |
+
"count": 79
|
| 1722 |
}
|
| 1723 |
}
|
| 1724 |
},
|
| 1725 |
"sub_B5": {
|
| 1726 |
+
"full_accuracy": 0.98,
|
| 1727 |
+
"digit_accuracy": 0.9971428571428571,
|
| 1728 |
+
"n_examples": 50,
|
| 1729 |
"per_subtask": {
|
| 1730 |
"MD": {
|
| 1731 |
"accuracy": 1.0,
|
| 1732 |
+
"count": 50
|
| 1733 |
},
|
| 1734 |
"MB": {
|
| 1735 |
"accuracy": 1.0,
|
| 1736 |
+
"count": 50
|
| 1737 |
},
|
| 1738 |
"UB": {
|
| 1739 |
+
"accuracy": 0.993421052631579,
|
| 1740 |
+
"count": 152
|
| 1741 |
},
|
| 1742 |
"UD": {
|
| 1743 |
"accuracy": 1.0,
|
| 1744 |
+
"count": 98
|
| 1745 |
}
|
| 1746 |
}
|
| 1747 |
}
|
| 1748 |
},
|
| 1749 |
"summary": {
|
| 1750 |
+
"overall_accuracy": 0.9273333333333333,
|
| 1751 |
+
"digit_accuracy": 0.9820952380952381,
|
| 1752 |
+
"total_examples": 1500,
|
| 1753 |
+
"n_splits": 24
|
| 1754 |
}
|
| 1755 |
},
|
| 1756 |
"sorl_eval": {
|
|
|
|
| 1759 |
"K": 1,
|
| 1760 |
"mode": "sorl",
|
| 1761 |
"n_digits": 6,
|
| 1762 |
+
"n_per_split": 50
|
| 1763 |
},
|
| 1764 |
"splits": {
|
| 1765 |
"add_S0": {
|
| 1766 |
"full_accuracy": 1.0,
|
| 1767 |
+
"digit_accuracy": 1.0,
|
| 1768 |
+
"n_examples": 50,
|
| 1769 |
"per_subtask": {
|
| 1770 |
"SA": {
|
| 1771 |
"accuracy": 1.0,
|
| 1772 |
+
"count": 295
|
| 1773 |
},
|
| 1774 |
"SS": {
|
| 1775 |
"accuracy": 1.0,
|
| 1776 |
+
"count": 55
|
| 1777 |
}
|
| 1778 |
}
|
| 1779 |
},
|
| 1780 |
"add_S1": {
|
| 1781 |
"full_accuracy": 1.0,
|
| 1782 |
+
"digit_accuracy": 1.0,
|
| 1783 |
+
"n_examples": 50,
|
| 1784 |
"per_subtask": {
|
| 1785 |
"SA": {
|
| 1786 |
"accuracy": 1.0,
|
| 1787 |
+
"count": 126
|
| 1788 |
},
|
| 1789 |
"SC": {
|
| 1790 |
"accuracy": 1.0,
|
| 1791 |
+
"count": 79
|
| 1792 |
},
|
| 1793 |
"SS": {
|
| 1794 |
"accuracy": 1.0,
|
| 1795 |
+
"count": 21
|
| 1796 |
},
|
| 1797 |
"UC": {
|
| 1798 |
"accuracy": 1.0,
|
| 1799 |
+
"count": 124
|
| 1800 |
}
|
| 1801 |
}
|
| 1802 |
},
|
| 1803 |
"add_S2": {
|
| 1804 |
"full_accuracy": 1.0,
|
| 1805 |
+
"digit_accuracy": 1.0,
|
| 1806 |
+
"n_examples": 50,
|
| 1807 |
"per_subtask": {
|
| 1808 |
"SA": {
|
| 1809 |
"accuracy": 1.0,
|
| 1810 |
+
"count": 75
|
| 1811 |
},
|
| 1812 |
"SC": {
|
| 1813 |
"accuracy": 1.0,
|
| 1814 |
+
"count": 62
|
| 1815 |
},
|
| 1816 |
"SS": {
|
| 1817 |
"accuracy": 1.0,
|
| 1818 |
+
"count": 39
|
| 1819 |
},
|
| 1820 |
"UC": {
|
| 1821 |
"accuracy": 1.0,
|
| 1822 |
+
"count": 111
|
| 1823 |
},
|
| 1824 |
"US": {
|
| 1825 |
"accuracy": 1.0,
|
| 1826 |
+
"count": 63
|
| 1827 |
}
|
| 1828 |
}
|
| 1829 |
},
|
| 1830 |
"add_S3": {
|
| 1831 |
+
"full_accuracy": 0.98,
|
| 1832 |
+
"digit_accuracy": 0.9971428571428571,
|
| 1833 |
+
"n_examples": 50,
|
| 1834 |
"per_subtask": {
|
| 1835 |
"SA": {
|
| 1836 |
"accuracy": 1.0,
|
| 1837 |
+
"count": 60
|
| 1838 |
},
|
| 1839 |
"SC": {
|
| 1840 |
"accuracy": 1.0,
|
| 1841 |
+
"count": 57
|
| 1842 |
},
|
| 1843 |
"SS": {
|
| 1844 |
"accuracy": 1.0,
|
| 1845 |
+
"count": 19
|
| 1846 |
},
|
| 1847 |
"UC": {
|
| 1848 |
+
"accuracy": 0.9903846153846154,
|
| 1849 |
+
"count": 104
|
| 1850 |
},
|
| 1851 |
"US": {
|
| 1852 |
"accuracy": 1.0,
|
| 1853 |
+
"count": 110
|
| 1854 |
}
|
| 1855 |
}
|
| 1856 |
},
|
| 1857 |
"add_S4": {
|
| 1858 |
"full_accuracy": 1.0,
|
| 1859 |
+
"digit_accuracy": 1.0,
|
| 1860 |
+
"n_examples": 50,
|
| 1861 |
"per_subtask": {
|
| 1862 |
"SA": {
|
| 1863 |
"accuracy": 1.0,
|
| 1864 |
+
"count": 48
|
| 1865 |
},
|
| 1866 |
"SC": {
|
| 1867 |
"accuracy": 1.0,
|
| 1868 |
+
"count": 52
|
| 1869 |
},
|
| 1870 |
"SS": {
|
| 1871 |
"accuracy": 1.0,
|
| 1872 |
+
"count": 7
|
| 1873 |
},
|
| 1874 |
"UC": {
|
| 1875 |
"accuracy": 1.0,
|
| 1876 |
+
"count": 89
|
| 1877 |
},
|
| 1878 |
"US": {
|
| 1879 |
"accuracy": 1.0,
|
| 1880 |
+
"count": 154
|
| 1881 |
}
|
| 1882 |
}
|
| 1883 |
},
|
| 1884 |
"add_S5": {
|
| 1885 |
"full_accuracy": 0.96,
|
| 1886 |
+
"digit_accuracy": 0.9942857142857143,
|
| 1887 |
+
"n_examples": 50,
|
| 1888 |
"per_subtask": {
|
| 1889 |
"SA": {
|
| 1890 |
"accuracy": 1.0,
|
| 1891 |
+
"count": 50
|
| 1892 |
},
|
| 1893 |
"SC": {
|
| 1894 |
"accuracy": 1.0,
|
| 1895 |
+
"count": 50
|
| 1896 |
},
|
| 1897 |
"UC": {
|
| 1898 |
"accuracy": 0.96,
|
| 1899 |
+
"count": 50
|
| 1900 |
},
|
| 1901 |
"US": {
|
| 1902 |
"accuracy": 1.0,
|
| 1903 |
+
"count": 200
|
| 1904 |
}
|
| 1905 |
}
|
| 1906 |
},
|
| 1907 |
"add_S6": {
|
| 1908 |
+
"full_accuracy": 0.9,
|
| 1909 |
+
"digit_accuracy": 0.9771428571428571,
|
| 1910 |
+
"n_examples": 50,
|
| 1911 |
"per_subtask": {
|
| 1912 |
"SC": {
|
| 1913 |
"accuracy": 1.0,
|
| 1914 |
+
"count": 50
|
| 1915 |
},
|
| 1916 |
"UC": {
|
| 1917 |
+
"accuracy": 0.9,
|
| 1918 |
+
"count": 50
|
| 1919 |
},
|
| 1920 |
"US": {
|
| 1921 |
+
"accuracy": 0.988,
|
| 1922 |
+
"count": 250
|
| 1923 |
}
|
| 1924 |
}
|
| 1925 |
},
|
| 1926 |
"add_random": {
|
| 1927 |
+
"full_accuracy": 0.995,
|
| 1928 |
+
"digit_accuracy": 0.9992857142857143,
|
| 1929 |
"n_examples": 200,
|
| 1930 |
"per_subtask": {
|
| 1931 |
"SA": {
|
| 1932 |
"accuracy": 1.0,
|
| 1933 |
+
"count": 431
|
| 1934 |
},
|
| 1935 |
"SC": {
|
| 1936 |
"accuracy": 1.0,
|
| 1937 |
+
"count": 316
|
| 1938 |
},
|
| 1939 |
"SS": {
|
| 1940 |
"accuracy": 1.0,
|
| 1941 |
+
"count": 39
|
| 1942 |
},
|
| 1943 |
"UC": {
|
| 1944 |
+
"accuracy": 0.9982142857142857,
|
| 1945 |
+
"count": 560
|
| 1946 |
},
|
| 1947 |
"US": {
|
| 1948 |
"accuracy": 1.0,
|
| 1949 |
+
"count": 54
|
| 1950 |
+
}
|
| 1951 |
+
}
|
| 1952 |
+
},
|
| 1953 |
+
"add_C1": {
|
| 1954 |
+
"full_accuracy": 1.0,
|
| 1955 |
+
"digit_accuracy": 1.0,
|
| 1956 |
+
"n_examples": 50,
|
| 1957 |
+
"per_subtask": {
|
| 1958 |
+
"SA": {
|
| 1959 |
+
"accuracy": 1.0,
|
| 1960 |
+
"count": 250
|
| 1961 |
+
},
|
| 1962 |
+
"SC": {
|
| 1963 |
+
"accuracy": 1.0,
|
| 1964 |
+
"count": 50
|
| 1965 |
+
},
|
| 1966 |
+
"UC": {
|
| 1967 |
+
"accuracy": 1.0,
|
| 1968 |
+
"count": 50
|
| 1969 |
+
}
|
| 1970 |
+
}
|
| 1971 |
+
},
|
| 1972 |
+
"add_C2": {
|
| 1973 |
+
"full_accuracy": 0.98,
|
| 1974 |
+
"digit_accuracy": 0.9942857142857143,
|
| 1975 |
+
"n_examples": 50,
|
| 1976 |
+
"per_subtask": {
|
| 1977 |
+
"SA": {
|
| 1978 |
+
"accuracy": 1.0,
|
| 1979 |
+
"count": 200
|
| 1980 |
+
},
|
| 1981 |
+
"SC": {
|
| 1982 |
+
"accuracy": 1.0,
|
| 1983 |
+
"count": 50
|
| 1984 |
+
},
|
| 1985 |
+
"UC": {
|
| 1986 |
+
"accuracy": 0.9879518072289156,
|
| 1987 |
+
"count": 83
|
| 1988 |
+
},
|
| 1989 |
+
"US": {
|
| 1990 |
+
"accuracy": 0.9411764705882353,
|
| 1991 |
+
"count": 17
|
| 1992 |
}
|
| 1993 |
}
|
| 1994 |
},
|
| 1995 |
"add_C3": {
|
| 1996 |
"full_accuracy": 1.0,
|
| 1997 |
+
"digit_accuracy": 1.0,
|
| 1998 |
+
"n_examples": 50,
|
| 1999 |
"per_subtask": {
|
| 2000 |
"SA": {
|
| 2001 |
"accuracy": 1.0,
|
| 2002 |
+
"count": 150
|
| 2003 |
},
|
| 2004 |
"SC": {
|
| 2005 |
"accuracy": 1.0,
|
| 2006 |
+
"count": 50
|
| 2007 |
},
|
| 2008 |
"UC": {
|
| 2009 |
"accuracy": 1.0,
|
| 2010 |
+
"count": 100
|
| 2011 |
},
|
| 2012 |
"US": {
|
| 2013 |
"accuracy": 1.0,
|
| 2014 |
+
"count": 50
|
| 2015 |
}
|
| 2016 |
}
|
| 2017 |
},
|
| 2018 |
"add_C4": {
|
| 2019 |
"full_accuracy": 1.0,
|
| 2020 |
+
"digit_accuracy": 1.0,
|
| 2021 |
+
"n_examples": 50,
|
| 2022 |
"per_subtask": {
|
| 2023 |
"SA": {
|
| 2024 |
"accuracy": 1.0,
|
| 2025 |
+
"count": 100
|
| 2026 |
},
|
| 2027 |
"SC": {
|
| 2028 |
"accuracy": 1.0,
|
| 2029 |
+
"count": 50
|
| 2030 |
},
|
| 2031 |
"UC": {
|
| 2032 |
"accuracy": 1.0,
|
| 2033 |
+
"count": 132
|
| 2034 |
},
|
| 2035 |
"US": {
|
| 2036 |
"accuracy": 1.0,
|
| 2037 |
+
"count": 68
|
| 2038 |
}
|
| 2039 |
}
|
| 2040 |
},
|
| 2041 |
"add_C5": {
|
| 2042 |
"full_accuracy": 1.0,
|
| 2043 |
+
"digit_accuracy": 1.0,
|
| 2044 |
+
"n_examples": 50,
|
| 2045 |
"per_subtask": {
|
| 2046 |
"SA": {
|
| 2047 |
"accuracy": 1.0,
|
| 2048 |
+
"count": 50
|
| 2049 |
},
|
| 2050 |
"SC": {
|
| 2051 |
"accuracy": 1.0,
|
| 2052 |
+
"count": 50
|
| 2053 |
},
|
| 2054 |
"UC": {
|
| 2055 |
"accuracy": 1.0,
|
| 2056 |
+
"count": 146
|
| 2057 |
},
|
| 2058 |
"US": {
|
| 2059 |
"accuracy": 1.0,
|
| 2060 |
+
"count": 104
|
| 2061 |
}
|
| 2062 |
}
|
| 2063 |
},
|
| 2064 |
"add_C6": {
|
| 2065 |
+
"full_accuracy": 1.0,
|
| 2066 |
+
"digit_accuracy": 1.0,
|
| 2067 |
+
"n_examples": 50,
|
| 2068 |
"per_subtask": {
|
| 2069 |
"SC": {
|
| 2070 |
"accuracy": 1.0,
|
| 2071 |
+
"count": 50
|
| 2072 |
},
|
| 2073 |
"UC": {
|
| 2074 |
+
"accuracy": 1.0,
|
| 2075 |
+
"count": 189
|
| 2076 |
},
|
| 2077 |
"US": {
|
| 2078 |
"accuracy": 1.0,
|
| 2079 |
+
"count": 111
|
| 2080 |
}
|
| 2081 |
}
|
| 2082 |
},
|
| 2083 |
"sub_M0": {
|
| 2084 |
"full_accuracy": 1.0,
|
| 2085 |
+
"digit_accuracy": 1.0,
|
| 2086 |
+
"n_examples": 50,
|
| 2087 |
"per_subtask": {
|
| 2088 |
"MD": {
|
| 2089 |
"accuracy": 1.0,
|
| 2090 |
+
"count": 303
|
| 2091 |
},
|
| 2092 |
"ME": {
|
| 2093 |
"accuracy": 1.0,
|
| 2094 |
+
"count": 47
|
| 2095 |
}
|
| 2096 |
}
|
| 2097 |
},
|
| 2098 |
"sub_M1": {
|
| 2099 |
"full_accuracy": 1.0,
|
| 2100 |
+
"digit_accuracy": 1.0,
|
| 2101 |
+
"n_examples": 50,
|
| 2102 |
"per_subtask": {
|
| 2103 |
"MD": {
|
| 2104 |
"accuracy": 1.0,
|
| 2105 |
+
"count": 141
|
| 2106 |
},
|
| 2107 |
"MB": {
|
| 2108 |
"accuracy": 1.0,
|
| 2109 |
+
"count": 72
|
| 2110 |
},
|
| 2111 |
"ME": {
|
| 2112 |
"accuracy": 1.0,
|
| 2113 |
+
"count": 18
|
| 2114 |
},
|
| 2115 |
"UB": {
|
| 2116 |
"accuracy": 1.0,
|
| 2117 |
+
"count": 119
|
| 2118 |
}
|
| 2119 |
}
|
| 2120 |
},
|
| 2121 |
"sub_M2": {
|
| 2122 |
"full_accuracy": 1.0,
|
| 2123 |
+
"digit_accuracy": 1.0,
|
| 2124 |
+
"n_examples": 50,
|
| 2125 |
"per_subtask": {
|
| 2126 |
"MD": {
|
| 2127 |
"accuracy": 1.0,
|
| 2128 |
+
"count": 112
|
| 2129 |
},
|
| 2130 |
"MB": {
|
| 2131 |
"accuracy": 1.0,
|
| 2132 |
+
"count": 53
|
| 2133 |
},
|
| 2134 |
"ME": {
|
| 2135 |
"accuracy": 1.0,
|
| 2136 |
+
"count": 47
|
| 2137 |
},
|
| 2138 |
"UB": {
|
| 2139 |
"accuracy": 1.0,
|
| 2140 |
+
"count": 85
|
| 2141 |
},
|
| 2142 |
"UD": {
|
| 2143 |
"accuracy": 1.0,
|
| 2144 |
+
"count": 53
|
| 2145 |
}
|
| 2146 |
}
|
| 2147 |
},
|
| 2148 |
"sub_M3": {
|
| 2149 |
"full_accuracy": 1.0,
|
| 2150 |
+
"digit_accuracy": 1.0,
|
| 2151 |
+
"n_examples": 50,
|
| 2152 |
"per_subtask": {
|
| 2153 |
"MD": {
|
| 2154 |
"accuracy": 1.0,
|
| 2155 |
+
"count": 97
|
| 2156 |
},
|
| 2157 |
"MB": {
|
| 2158 |
"accuracy": 1.0,
|
| 2159 |
+
"count": 51
|
| 2160 |
},
|
| 2161 |
"ME": {
|
| 2162 |
"accuracy": 1.0,
|
| 2163 |
+
"count": 27
|
| 2164 |
},
|
| 2165 |
"UB": {
|
| 2166 |
"accuracy": 1.0,
|
| 2167 |
+
"count": 74
|
| 2168 |
},
|
| 2169 |
"UD": {
|
| 2170 |
"accuracy": 1.0,
|
| 2171 |
+
"count": 101
|
| 2172 |
}
|
| 2173 |
}
|
| 2174 |
},
|
| 2175 |
"sub_M4": {
|
| 2176 |
"full_accuracy": 1.0,
|
| 2177 |
+
"digit_accuracy": 1.0,
|
| 2178 |
+
"n_examples": 50,
|
| 2179 |
"per_subtask": {
|
| 2180 |
"MD": {
|
| 2181 |
"accuracy": 1.0,
|
| 2182 |
+
"count": 100
|
| 2183 |
},
|
| 2184 |
"MB": {
|
| 2185 |
"accuracy": 1.0,
|
| 2186 |
+
"count": 50
|
| 2187 |
},
|
| 2188 |
"UB": {
|
| 2189 |
"accuracy": 1.0,
|
| 2190 |
+
"count": 50
|
| 2191 |
},
|
| 2192 |
"UD": {
|
| 2193 |
"accuracy": 1.0,
|
| 2194 |
+
"count": 150
|
| 2195 |
}
|
| 2196 |
}
|
| 2197 |
},
|
| 2198 |
"sub_M5": {
|
| 2199 |
+
"full_accuracy": 0.82,
|
| 2200 |
+
"digit_accuracy": 0.9742857142857143,
|
| 2201 |
+
"n_examples": 50,
|
| 2202 |
"per_subtask": {
|
| 2203 |
"MD": {
|
| 2204 |
"accuracy": 1.0,
|
| 2205 |
+
"count": 50
|
| 2206 |
},
|
| 2207 |
"MB": {
|
| 2208 |
"accuracy": 1.0,
|
| 2209 |
+
"count": 50
|
| 2210 |
},
|
| 2211 |
"UB": {
|
| 2212 |
+
"accuracy": 0.82,
|
| 2213 |
+
"count": 50
|
| 2214 |
},
|
| 2215 |
"UD": {
|
| 2216 |
+
"accuracy": 1.0,
|
| 2217 |
+
"count": 200
|
| 2218 |
}
|
| 2219 |
}
|
| 2220 |
},
|
| 2221 |
"sub_random": {
|
| 2222 |
+
"full_accuracy": 1.0,
|
| 2223 |
+
"digit_accuracy": 1.0,
|
| 2224 |
"n_examples": 200,
|
| 2225 |
"per_subtask": {
|
| 2226 |
"MD": {
|
| 2227 |
+
"accuracy": 1.0,
|
| 2228 |
+
"count": 570
|
| 2229 |
},
|
| 2230 |
"MB": {
|
| 2231 |
"accuracy": 1.0,
|
| 2232 |
+
"count": 277
|
| 2233 |
},
|
| 2234 |
"ME": {
|
| 2235 |
"accuracy": 1.0,
|
|
|
|
| 2237 |
},
|
| 2238 |
"UB": {
|
| 2239 |
"accuracy": 1.0,
|
| 2240 |
+
"count": 471
|
| 2241 |
},
|
| 2242 |
"UD": {
|
| 2243 |
"accuracy": 1.0,
|
| 2244 |
+
"count": 29
|
| 2245 |
}
|
| 2246 |
}
|
| 2247 |
},
|
| 2248 |
"sub_B3": {
|
| 2249 |
"full_accuracy": 1.0,
|
| 2250 |
+
"digit_accuracy": 1.0,
|
| 2251 |
+
"n_examples": 50,
|
| 2252 |
"per_subtask": {
|
| 2253 |
"MD": {
|
| 2254 |
"accuracy": 1.0,
|
| 2255 |
+
"count": 150
|
| 2256 |
},
|
| 2257 |
"MB": {
|
| 2258 |
"accuracy": 1.0,
|
| 2259 |
+
"count": 50
|
| 2260 |
},
|
| 2261 |
"UB": {
|
| 2262 |
"accuracy": 1.0,
|
| 2263 |
+
"count": 101
|
| 2264 |
},
|
| 2265 |
"UD": {
|
| 2266 |
"accuracy": 1.0,
|
| 2267 |
+
"count": 49
|
| 2268 |
}
|
| 2269 |
}
|
| 2270 |
},
|
| 2271 |
"sub_B4": {
|
| 2272 |
"full_accuracy": 1.0,
|
| 2273 |
+
"digit_accuracy": 1.0,
|
| 2274 |
+
"n_examples": 50,
|
| 2275 |
"per_subtask": {
|
| 2276 |
"MD": {
|
| 2277 |
"accuracy": 1.0,
|
| 2278 |
+
"count": 100
|
| 2279 |
},
|
| 2280 |
"MB": {
|
| 2281 |
"accuracy": 1.0,
|
| 2282 |
+
"count": 50
|
| 2283 |
},
|
| 2284 |
"UB": {
|
| 2285 |
"accuracy": 1.0,
|
| 2286 |
+
"count": 121
|
| 2287 |
},
|
| 2288 |
"UD": {
|
| 2289 |
"accuracy": 1.0,
|
| 2290 |
+
"count": 79
|
| 2291 |
}
|
| 2292 |
}
|
| 2293 |
},
|
| 2294 |
"sub_B5": {
|
| 2295 |
+
"full_accuracy": 0.96,
|
| 2296 |
+
"digit_accuracy": 0.9942857142857143,
|
| 2297 |
+
"n_examples": 50,
|
| 2298 |
"per_subtask": {
|
| 2299 |
"MD": {
|
| 2300 |
"accuracy": 1.0,
|
| 2301 |
+
"count": 50
|
| 2302 |
},
|
| 2303 |
"MB": {
|
| 2304 |
"accuracy": 1.0,
|
| 2305 |
+
"count": 50
|
| 2306 |
},
|
| 2307 |
"UB": {
|
| 2308 |
+
"accuracy": 0.9868421052631579,
|
| 2309 |
+
"count": 152
|
| 2310 |
},
|
| 2311 |
"UD": {
|
| 2312 |
"accuracy": 1.0,
|
| 2313 |
+
"count": 98
|
| 2314 |
}
|
| 2315 |
}
|
| 2316 |
}
|
| 2317 |
},
|
| 2318 |
"summary": {
|
| 2319 |
+
"overall_accuracy": 0.986,
|
| 2320 |
+
"digit_accuracy": 0.9976190476190476,
|
| 2321 |
+
"total_examples": 1500,
|
| 2322 |
+
"n_splits": 24
|
| 2323 |
}
|
| 2324 |
},
|
| 2325 |
"sorl_overall_accuracy": 0.985,
|