Training in progress, epoch 2
Browse files- adapter_model.safetensors +1 -1
- phi-2-custom-2.ipynb +302 -2
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 73433680
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34ecb306e596ab7e8a83d72bc9999223a6484896db2856e61f9a32f760074964
|
| 3 |
size 73433680
|
phi-2-custom-2.ipynb
CHANGED
|
@@ -978,8 +978,8 @@
|
|
| 978 |
"\n",
|
| 979 |
" <div>\n",
|
| 980 |
" \n",
|
| 981 |
-
" <progress value='
|
| 982 |
-
" [
|
| 983 |
" </div>\n",
|
| 984 |
" <table border=\"1\" class=\"dataframe\">\n",
|
| 985 |
" <thead>\n",
|
|
@@ -1313,6 +1313,306 @@
|
|
| 1313 |
" <td>4050</td>\n",
|
| 1314 |
" <td>1.051500</td>\n",
|
| 1315 |
" </tr>\n",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1316 |
" </tbody>\n",
|
| 1317 |
"</table><p>"
|
| 1318 |
],
|
|
|
|
| 978 |
"\n",
|
| 979 |
" <div>\n",
|
| 980 |
" \n",
|
| 981 |
+
" <progress value='7850' max='10000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
|
| 982 |
+
" [ 7850/10000 29:06 < 07:58, 4.49 it/s, Epoch 1.91/3]\n",
|
| 983 |
" </div>\n",
|
| 984 |
" <table border=\"1\" class=\"dataframe\">\n",
|
| 985 |
" <thead>\n",
|
|
|
|
| 1313 |
" <td>4050</td>\n",
|
| 1314 |
" <td>1.051500</td>\n",
|
| 1315 |
" </tr>\n",
|
| 1316 |
+
" <tr>\n",
|
| 1317 |
+
" <td>4100</td>\n",
|
| 1318 |
+
" <td>1.052600</td>\n",
|
| 1319 |
+
" </tr>\n",
|
| 1320 |
+
" <tr>\n",
|
| 1321 |
+
" <td>4150</td>\n",
|
| 1322 |
+
" <td>1.029600</td>\n",
|
| 1323 |
+
" </tr>\n",
|
| 1324 |
+
" <tr>\n",
|
| 1325 |
+
" <td>4200</td>\n",
|
| 1326 |
+
" <td>0.997700</td>\n",
|
| 1327 |
+
" </tr>\n",
|
| 1328 |
+
" <tr>\n",
|
| 1329 |
+
" <td>4250</td>\n",
|
| 1330 |
+
" <td>0.982800</td>\n",
|
| 1331 |
+
" </tr>\n",
|
| 1332 |
+
" <tr>\n",
|
| 1333 |
+
" <td>4300</td>\n",
|
| 1334 |
+
" <td>0.984900</td>\n",
|
| 1335 |
+
" </tr>\n",
|
| 1336 |
+
" <tr>\n",
|
| 1337 |
+
" <td>4350</td>\n",
|
| 1338 |
+
" <td>1.020700</td>\n",
|
| 1339 |
+
" </tr>\n",
|
| 1340 |
+
" <tr>\n",
|
| 1341 |
+
" <td>4400</td>\n",
|
| 1342 |
+
" <td>1.021000</td>\n",
|
| 1343 |
+
" </tr>\n",
|
| 1344 |
+
" <tr>\n",
|
| 1345 |
+
" <td>4450</td>\n",
|
| 1346 |
+
" <td>0.967500</td>\n",
|
| 1347 |
+
" </tr>\n",
|
| 1348 |
+
" <tr>\n",
|
| 1349 |
+
" <td>4500</td>\n",
|
| 1350 |
+
" <td>1.000800</td>\n",
|
| 1351 |
+
" </tr>\n",
|
| 1352 |
+
" <tr>\n",
|
| 1353 |
+
" <td>4550</td>\n",
|
| 1354 |
+
" <td>0.973400</td>\n",
|
| 1355 |
+
" </tr>\n",
|
| 1356 |
+
" <tr>\n",
|
| 1357 |
+
" <td>4600</td>\n",
|
| 1358 |
+
" <td>0.986600</td>\n",
|
| 1359 |
+
" </tr>\n",
|
| 1360 |
+
" <tr>\n",
|
| 1361 |
+
" <td>4650</td>\n",
|
| 1362 |
+
" <td>0.985700</td>\n",
|
| 1363 |
+
" </tr>\n",
|
| 1364 |
+
" <tr>\n",
|
| 1365 |
+
" <td>4700</td>\n",
|
| 1366 |
+
" <td>0.924400</td>\n",
|
| 1367 |
+
" </tr>\n",
|
| 1368 |
+
" <tr>\n",
|
| 1369 |
+
" <td>4750</td>\n",
|
| 1370 |
+
" <td>0.978400</td>\n",
|
| 1371 |
+
" </tr>\n",
|
| 1372 |
+
" <tr>\n",
|
| 1373 |
+
" <td>4800</td>\n",
|
| 1374 |
+
" <td>1.031400</td>\n",
|
| 1375 |
+
" </tr>\n",
|
| 1376 |
+
" <tr>\n",
|
| 1377 |
+
" <td>4850</td>\n",
|
| 1378 |
+
" <td>0.952300</td>\n",
|
| 1379 |
+
" </tr>\n",
|
| 1380 |
+
" <tr>\n",
|
| 1381 |
+
" <td>4900</td>\n",
|
| 1382 |
+
" <td>0.995800</td>\n",
|
| 1383 |
+
" </tr>\n",
|
| 1384 |
+
" <tr>\n",
|
| 1385 |
+
" <td>4950</td>\n",
|
| 1386 |
+
" <td>0.985900</td>\n",
|
| 1387 |
+
" </tr>\n",
|
| 1388 |
+
" <tr>\n",
|
| 1389 |
+
" <td>5000</td>\n",
|
| 1390 |
+
" <td>0.981700</td>\n",
|
| 1391 |
+
" </tr>\n",
|
| 1392 |
+
" <tr>\n",
|
| 1393 |
+
" <td>5050</td>\n",
|
| 1394 |
+
" <td>0.957800</td>\n",
|
| 1395 |
+
" </tr>\n",
|
| 1396 |
+
" <tr>\n",
|
| 1397 |
+
" <td>5100</td>\n",
|
| 1398 |
+
" <td>0.908500</td>\n",
|
| 1399 |
+
" </tr>\n",
|
| 1400 |
+
" <tr>\n",
|
| 1401 |
+
" <td>5150</td>\n",
|
| 1402 |
+
" <td>0.957400</td>\n",
|
| 1403 |
+
" </tr>\n",
|
| 1404 |
+
" <tr>\n",
|
| 1405 |
+
" <td>5200</td>\n",
|
| 1406 |
+
" <td>1.009800</td>\n",
|
| 1407 |
+
" </tr>\n",
|
| 1408 |
+
" <tr>\n",
|
| 1409 |
+
" <td>5250</td>\n",
|
| 1410 |
+
" <td>0.973400</td>\n",
|
| 1411 |
+
" </tr>\n",
|
| 1412 |
+
" <tr>\n",
|
| 1413 |
+
" <td>5300</td>\n",
|
| 1414 |
+
" <td>1.014600</td>\n",
|
| 1415 |
+
" </tr>\n",
|
| 1416 |
+
" <tr>\n",
|
| 1417 |
+
" <td>5350</td>\n",
|
| 1418 |
+
" <td>0.925700</td>\n",
|
| 1419 |
+
" </tr>\n",
|
| 1420 |
+
" <tr>\n",
|
| 1421 |
+
" <td>5400</td>\n",
|
| 1422 |
+
" <td>1.018200</td>\n",
|
| 1423 |
+
" </tr>\n",
|
| 1424 |
+
" <tr>\n",
|
| 1425 |
+
" <td>5450</td>\n",
|
| 1426 |
+
" <td>1.001800</td>\n",
|
| 1427 |
+
" </tr>\n",
|
| 1428 |
+
" <tr>\n",
|
| 1429 |
+
" <td>5500</td>\n",
|
| 1430 |
+
" <td>1.015900</td>\n",
|
| 1431 |
+
" </tr>\n",
|
| 1432 |
+
" <tr>\n",
|
| 1433 |
+
" <td>5550</td>\n",
|
| 1434 |
+
" <td>0.976700</td>\n",
|
| 1435 |
+
" </tr>\n",
|
| 1436 |
+
" <tr>\n",
|
| 1437 |
+
" <td>5600</td>\n",
|
| 1438 |
+
" <td>0.994300</td>\n",
|
| 1439 |
+
" </tr>\n",
|
| 1440 |
+
" <tr>\n",
|
| 1441 |
+
" <td>5650</td>\n",
|
| 1442 |
+
" <td>0.986000</td>\n",
|
| 1443 |
+
" </tr>\n",
|
| 1444 |
+
" <tr>\n",
|
| 1445 |
+
" <td>5700</td>\n",
|
| 1446 |
+
" <td>0.934200</td>\n",
|
| 1447 |
+
" </tr>\n",
|
| 1448 |
+
" <tr>\n",
|
| 1449 |
+
" <td>5750</td>\n",
|
| 1450 |
+
" <td>0.955100</td>\n",
|
| 1451 |
+
" </tr>\n",
|
| 1452 |
+
" <tr>\n",
|
| 1453 |
+
" <td>5800</td>\n",
|
| 1454 |
+
" <td>0.946400</td>\n",
|
| 1455 |
+
" </tr>\n",
|
| 1456 |
+
" <tr>\n",
|
| 1457 |
+
" <td>5850</td>\n",
|
| 1458 |
+
" <td>0.976700</td>\n",
|
| 1459 |
+
" </tr>\n",
|
| 1460 |
+
" <tr>\n",
|
| 1461 |
+
" <td>5900</td>\n",
|
| 1462 |
+
" <td>0.983900</td>\n",
|
| 1463 |
+
" </tr>\n",
|
| 1464 |
+
" <tr>\n",
|
| 1465 |
+
" <td>5950</td>\n",
|
| 1466 |
+
" <td>0.961400</td>\n",
|
| 1467 |
+
" </tr>\n",
|
| 1468 |
+
" <tr>\n",
|
| 1469 |
+
" <td>6000</td>\n",
|
| 1470 |
+
" <td>0.965800</td>\n",
|
| 1471 |
+
" </tr>\n",
|
| 1472 |
+
" <tr>\n",
|
| 1473 |
+
" <td>6050</td>\n",
|
| 1474 |
+
" <td>0.932600</td>\n",
|
| 1475 |
+
" </tr>\n",
|
| 1476 |
+
" <tr>\n",
|
| 1477 |
+
" <td>6100</td>\n",
|
| 1478 |
+
" <td>0.978700</td>\n",
|
| 1479 |
+
" </tr>\n",
|
| 1480 |
+
" <tr>\n",
|
| 1481 |
+
" <td>6150</td>\n",
|
| 1482 |
+
" <td>0.968300</td>\n",
|
| 1483 |
+
" </tr>\n",
|
| 1484 |
+
" <tr>\n",
|
| 1485 |
+
" <td>6200</td>\n",
|
| 1486 |
+
" <td>1.000700</td>\n",
|
| 1487 |
+
" </tr>\n",
|
| 1488 |
+
" <tr>\n",
|
| 1489 |
+
" <td>6250</td>\n",
|
| 1490 |
+
" <td>0.989300</td>\n",
|
| 1491 |
+
" </tr>\n",
|
| 1492 |
+
" <tr>\n",
|
| 1493 |
+
" <td>6300</td>\n",
|
| 1494 |
+
" <td>0.964000</td>\n",
|
| 1495 |
+
" </tr>\n",
|
| 1496 |
+
" <tr>\n",
|
| 1497 |
+
" <td>6350</td>\n",
|
| 1498 |
+
" <td>0.959000</td>\n",
|
| 1499 |
+
" </tr>\n",
|
| 1500 |
+
" <tr>\n",
|
| 1501 |
+
" <td>6400</td>\n",
|
| 1502 |
+
" <td>0.918600</td>\n",
|
| 1503 |
+
" </tr>\n",
|
| 1504 |
+
" <tr>\n",
|
| 1505 |
+
" <td>6450</td>\n",
|
| 1506 |
+
" <td>0.965600</td>\n",
|
| 1507 |
+
" </tr>\n",
|
| 1508 |
+
" <tr>\n",
|
| 1509 |
+
" <td>6500</td>\n",
|
| 1510 |
+
" <td>0.937600</td>\n",
|
| 1511 |
+
" </tr>\n",
|
| 1512 |
+
" <tr>\n",
|
| 1513 |
+
" <td>6550</td>\n",
|
| 1514 |
+
" <td>1.037600</td>\n",
|
| 1515 |
+
" </tr>\n",
|
| 1516 |
+
" <tr>\n",
|
| 1517 |
+
" <td>6600</td>\n",
|
| 1518 |
+
" <td>0.991400</td>\n",
|
| 1519 |
+
" </tr>\n",
|
| 1520 |
+
" <tr>\n",
|
| 1521 |
+
" <td>6650</td>\n",
|
| 1522 |
+
" <td>1.000300</td>\n",
|
| 1523 |
+
" </tr>\n",
|
| 1524 |
+
" <tr>\n",
|
| 1525 |
+
" <td>6700</td>\n",
|
| 1526 |
+
" <td>1.007200</td>\n",
|
| 1527 |
+
" </tr>\n",
|
| 1528 |
+
" <tr>\n",
|
| 1529 |
+
" <td>6750</td>\n",
|
| 1530 |
+
" <td>1.005800</td>\n",
|
| 1531 |
+
" </tr>\n",
|
| 1532 |
+
" <tr>\n",
|
| 1533 |
+
" <td>6800</td>\n",
|
| 1534 |
+
" <td>1.071100</td>\n",
|
| 1535 |
+
" </tr>\n",
|
| 1536 |
+
" <tr>\n",
|
| 1537 |
+
" <td>6850</td>\n",
|
| 1538 |
+
" <td>0.990100</td>\n",
|
| 1539 |
+
" </tr>\n",
|
| 1540 |
+
" <tr>\n",
|
| 1541 |
+
" <td>6900</td>\n",
|
| 1542 |
+
" <td>0.972700</td>\n",
|
| 1543 |
+
" </tr>\n",
|
| 1544 |
+
" <tr>\n",
|
| 1545 |
+
" <td>6950</td>\n",
|
| 1546 |
+
" <td>0.923800</td>\n",
|
| 1547 |
+
" </tr>\n",
|
| 1548 |
+
" <tr>\n",
|
| 1549 |
+
" <td>7000</td>\n",
|
| 1550 |
+
" <td>0.968300</td>\n",
|
| 1551 |
+
" </tr>\n",
|
| 1552 |
+
" <tr>\n",
|
| 1553 |
+
" <td>7050</td>\n",
|
| 1554 |
+
" <td>0.895400</td>\n",
|
| 1555 |
+
" </tr>\n",
|
| 1556 |
+
" <tr>\n",
|
| 1557 |
+
" <td>7100</td>\n",
|
| 1558 |
+
" <td>0.965400</td>\n",
|
| 1559 |
+
" </tr>\n",
|
| 1560 |
+
" <tr>\n",
|
| 1561 |
+
" <td>7150</td>\n",
|
| 1562 |
+
" <td>0.920500</td>\n",
|
| 1563 |
+
" </tr>\n",
|
| 1564 |
+
" <tr>\n",
|
| 1565 |
+
" <td>7200</td>\n",
|
| 1566 |
+
" <td>0.950700</td>\n",
|
| 1567 |
+
" </tr>\n",
|
| 1568 |
+
" <tr>\n",
|
| 1569 |
+
" <td>7250</td>\n",
|
| 1570 |
+
" <td>0.961400</td>\n",
|
| 1571 |
+
" </tr>\n",
|
| 1572 |
+
" <tr>\n",
|
| 1573 |
+
" <td>7300</td>\n",
|
| 1574 |
+
" <td>0.926500</td>\n",
|
| 1575 |
+
" </tr>\n",
|
| 1576 |
+
" <tr>\n",
|
| 1577 |
+
" <td>7350</td>\n",
|
| 1578 |
+
" <td>0.932500</td>\n",
|
| 1579 |
+
" </tr>\n",
|
| 1580 |
+
" <tr>\n",
|
| 1581 |
+
" <td>7400</td>\n",
|
| 1582 |
+
" <td>0.918000</td>\n",
|
| 1583 |
+
" </tr>\n",
|
| 1584 |
+
" <tr>\n",
|
| 1585 |
+
" <td>7450</td>\n",
|
| 1586 |
+
" <td>0.959700</td>\n",
|
| 1587 |
+
" </tr>\n",
|
| 1588 |
+
" <tr>\n",
|
| 1589 |
+
" <td>7500</td>\n",
|
| 1590 |
+
" <td>0.970300</td>\n",
|
| 1591 |
+
" </tr>\n",
|
| 1592 |
+
" <tr>\n",
|
| 1593 |
+
" <td>7550</td>\n",
|
| 1594 |
+
" <td>0.920800</td>\n",
|
| 1595 |
+
" </tr>\n",
|
| 1596 |
+
" <tr>\n",
|
| 1597 |
+
" <td>7600</td>\n",
|
| 1598 |
+
" <td>0.944500</td>\n",
|
| 1599 |
+
" </tr>\n",
|
| 1600 |
+
" <tr>\n",
|
| 1601 |
+
" <td>7650</td>\n",
|
| 1602 |
+
" <td>1.014300</td>\n",
|
| 1603 |
+
" </tr>\n",
|
| 1604 |
+
" <tr>\n",
|
| 1605 |
+
" <td>7700</td>\n",
|
| 1606 |
+
" <td>0.960400</td>\n",
|
| 1607 |
+
" </tr>\n",
|
| 1608 |
+
" <tr>\n",
|
| 1609 |
+
" <td>7750</td>\n",
|
| 1610 |
+
" <td>0.953300</td>\n",
|
| 1611 |
+
" </tr>\n",
|
| 1612 |
+
" <tr>\n",
|
| 1613 |
+
" <td>7800</td>\n",
|
| 1614 |
+
" <td>0.946200</td>\n",
|
| 1615 |
+
" </tr>\n",
|
| 1616 |
" </tbody>\n",
|
| 1617 |
"</table><p>"
|
| 1618 |
],
|