Training in progress, epoch 2
Browse files- adapter_model.safetensors +1 -1
- phi-2-custom-2.ipynb +178 -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 sha256:914069eb2ddd95d4c2f9b0f997e40f9d1517f8fb71bfeef9e41c8d9bc6f3fe21
|
| 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",
|
|
@@ -1613,6 +1613,182 @@
|
|
| 1613 |
" <td>7800</td>\n",
|
| 1614 |
" <td>0.946200</td>\n",
|
| 1615 |
" </tr>\n",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1616 |
" </tbody>\n",
|
| 1617 |
"</table><p>"
|
| 1618 |
],
|
|
|
|
| 978 |
"\n",
|
| 979 |
" <div>\n",
|
| 980 |
" \n",
|
| 981 |
+
" <progress value='10000' max='10000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
|
| 982 |
+
" [10000/10000 37:06, Epoch 2/3]\n",
|
| 983 |
" </div>\n",
|
| 984 |
" <table border=\"1\" class=\"dataframe\">\n",
|
| 985 |
" <thead>\n",
|
|
|
|
| 1613 |
" <td>7800</td>\n",
|
| 1614 |
" <td>0.946200</td>\n",
|
| 1615 |
" </tr>\n",
|
| 1616 |
+
" <tr>\n",
|
| 1617 |
+
" <td>7850</td>\n",
|
| 1618 |
+
" <td>0.965100</td>\n",
|
| 1619 |
+
" </tr>\n",
|
| 1620 |
+
" <tr>\n",
|
| 1621 |
+
" <td>7900</td>\n",
|
| 1622 |
+
" <td>0.942200</td>\n",
|
| 1623 |
+
" </tr>\n",
|
| 1624 |
+
" <tr>\n",
|
| 1625 |
+
" <td>7950</td>\n",
|
| 1626 |
+
" <td>0.952900</td>\n",
|
| 1627 |
+
" </tr>\n",
|
| 1628 |
+
" <tr>\n",
|
| 1629 |
+
" <td>8000</td>\n",
|
| 1630 |
+
" <td>0.895400</td>\n",
|
| 1631 |
+
" </tr>\n",
|
| 1632 |
+
" <tr>\n",
|
| 1633 |
+
" <td>8050</td>\n",
|
| 1634 |
+
" <td>0.974000</td>\n",
|
| 1635 |
+
" </tr>\n",
|
| 1636 |
+
" <tr>\n",
|
| 1637 |
+
" <td>8100</td>\n",
|
| 1638 |
+
" <td>0.990500</td>\n",
|
| 1639 |
+
" </tr>\n",
|
| 1640 |
+
" <tr>\n",
|
| 1641 |
+
" <td>8150</td>\n",
|
| 1642 |
+
" <td>0.972100</td>\n",
|
| 1643 |
+
" </tr>\n",
|
| 1644 |
+
" <tr>\n",
|
| 1645 |
+
" <td>8200</td>\n",
|
| 1646 |
+
" <td>0.968300</td>\n",
|
| 1647 |
+
" </tr>\n",
|
| 1648 |
+
" <tr>\n",
|
| 1649 |
+
" <td>8250</td>\n",
|
| 1650 |
+
" <td>0.999500</td>\n",
|
| 1651 |
+
" </tr>\n",
|
| 1652 |
+
" <tr>\n",
|
| 1653 |
+
" <td>8300</td>\n",
|
| 1654 |
+
" <td>0.924000</td>\n",
|
| 1655 |
+
" </tr>\n",
|
| 1656 |
+
" <tr>\n",
|
| 1657 |
+
" <td>8350</td>\n",
|
| 1658 |
+
" <td>0.966000</td>\n",
|
| 1659 |
+
" </tr>\n",
|
| 1660 |
+
" <tr>\n",
|
| 1661 |
+
" <td>8400</td>\n",
|
| 1662 |
+
" <td>0.906600</td>\n",
|
| 1663 |
+
" </tr>\n",
|
| 1664 |
+
" <tr>\n",
|
| 1665 |
+
" <td>8450</td>\n",
|
| 1666 |
+
" <td>0.955800</td>\n",
|
| 1667 |
+
" </tr>\n",
|
| 1668 |
+
" <tr>\n",
|
| 1669 |
+
" <td>8500</td>\n",
|
| 1670 |
+
" <td>0.895400</td>\n",
|
| 1671 |
+
" </tr>\n",
|
| 1672 |
+
" <tr>\n",
|
| 1673 |
+
" <td>8550</td>\n",
|
| 1674 |
+
" <td>0.878600</td>\n",
|
| 1675 |
+
" </tr>\n",
|
| 1676 |
+
" <tr>\n",
|
| 1677 |
+
" <td>8600</td>\n",
|
| 1678 |
+
" <td>0.909200</td>\n",
|
| 1679 |
+
" </tr>\n",
|
| 1680 |
+
" <tr>\n",
|
| 1681 |
+
" <td>8650</td>\n",
|
| 1682 |
+
" <td>0.952800</td>\n",
|
| 1683 |
+
" </tr>\n",
|
| 1684 |
+
" <tr>\n",
|
| 1685 |
+
" <td>8700</td>\n",
|
| 1686 |
+
" <td>0.876500</td>\n",
|
| 1687 |
+
" </tr>\n",
|
| 1688 |
+
" <tr>\n",
|
| 1689 |
+
" <td>8750</td>\n",
|
| 1690 |
+
" <td>0.932500</td>\n",
|
| 1691 |
+
" </tr>\n",
|
| 1692 |
+
" <tr>\n",
|
| 1693 |
+
" <td>8800</td>\n",
|
| 1694 |
+
" <td>0.892700</td>\n",
|
| 1695 |
+
" </tr>\n",
|
| 1696 |
+
" <tr>\n",
|
| 1697 |
+
" <td>8850</td>\n",
|
| 1698 |
+
" <td>0.956300</td>\n",
|
| 1699 |
+
" </tr>\n",
|
| 1700 |
+
" <tr>\n",
|
| 1701 |
+
" <td>8900</td>\n",
|
| 1702 |
+
" <td>0.948300</td>\n",
|
| 1703 |
+
" </tr>\n",
|
| 1704 |
+
" <tr>\n",
|
| 1705 |
+
" <td>8950</td>\n",
|
| 1706 |
+
" <td>0.939900</td>\n",
|
| 1707 |
+
" </tr>\n",
|
| 1708 |
+
" <tr>\n",
|
| 1709 |
+
" <td>9000</td>\n",
|
| 1710 |
+
" <td>0.893700</td>\n",
|
| 1711 |
+
" </tr>\n",
|
| 1712 |
+
" <tr>\n",
|
| 1713 |
+
" <td>9050</td>\n",
|
| 1714 |
+
" <td>0.947700</td>\n",
|
| 1715 |
+
" </tr>\n",
|
| 1716 |
+
" <tr>\n",
|
| 1717 |
+
" <td>9100</td>\n",
|
| 1718 |
+
" <td>0.922700</td>\n",
|
| 1719 |
+
" </tr>\n",
|
| 1720 |
+
" <tr>\n",
|
| 1721 |
+
" <td>9150</td>\n",
|
| 1722 |
+
" <td>0.865500</td>\n",
|
| 1723 |
+
" </tr>\n",
|
| 1724 |
+
" <tr>\n",
|
| 1725 |
+
" <td>9200</td>\n",
|
| 1726 |
+
" <td>0.883100</td>\n",
|
| 1727 |
+
" </tr>\n",
|
| 1728 |
+
" <tr>\n",
|
| 1729 |
+
" <td>9250</td>\n",
|
| 1730 |
+
" <td>0.863200</td>\n",
|
| 1731 |
+
" </tr>\n",
|
| 1732 |
+
" <tr>\n",
|
| 1733 |
+
" <td>9300</td>\n",
|
| 1734 |
+
" <td>0.901800</td>\n",
|
| 1735 |
+
" </tr>\n",
|
| 1736 |
+
" <tr>\n",
|
| 1737 |
+
" <td>9350</td>\n",
|
| 1738 |
+
" <td>0.914500</td>\n",
|
| 1739 |
+
" </tr>\n",
|
| 1740 |
+
" <tr>\n",
|
| 1741 |
+
" <td>9400</td>\n",
|
| 1742 |
+
" <td>0.922100</td>\n",
|
| 1743 |
+
" </tr>\n",
|
| 1744 |
+
" <tr>\n",
|
| 1745 |
+
" <td>9450</td>\n",
|
| 1746 |
+
" <td>0.897600</td>\n",
|
| 1747 |
+
" </tr>\n",
|
| 1748 |
+
" <tr>\n",
|
| 1749 |
+
" <td>9500</td>\n",
|
| 1750 |
+
" <td>0.911700</td>\n",
|
| 1751 |
+
" </tr>\n",
|
| 1752 |
+
" <tr>\n",
|
| 1753 |
+
" <td>9550</td>\n",
|
| 1754 |
+
" <td>0.903800</td>\n",
|
| 1755 |
+
" </tr>\n",
|
| 1756 |
+
" <tr>\n",
|
| 1757 |
+
" <td>9600</td>\n",
|
| 1758 |
+
" <td>0.965100</td>\n",
|
| 1759 |
+
" </tr>\n",
|
| 1760 |
+
" <tr>\n",
|
| 1761 |
+
" <td>9650</td>\n",
|
| 1762 |
+
" <td>0.851700</td>\n",
|
| 1763 |
+
" </tr>\n",
|
| 1764 |
+
" <tr>\n",
|
| 1765 |
+
" <td>9700</td>\n",
|
| 1766 |
+
" <td>0.935000</td>\n",
|
| 1767 |
+
" </tr>\n",
|
| 1768 |
+
" <tr>\n",
|
| 1769 |
+
" <td>9750</td>\n",
|
| 1770 |
+
" <td>0.954300</td>\n",
|
| 1771 |
+
" </tr>\n",
|
| 1772 |
+
" <tr>\n",
|
| 1773 |
+
" <td>9800</td>\n",
|
| 1774 |
+
" <td>0.908300</td>\n",
|
| 1775 |
+
" </tr>\n",
|
| 1776 |
+
" <tr>\n",
|
| 1777 |
+
" <td>9850</td>\n",
|
| 1778 |
+
" <td>0.892500</td>\n",
|
| 1779 |
+
" </tr>\n",
|
| 1780 |
+
" <tr>\n",
|
| 1781 |
+
" <td>9900</td>\n",
|
| 1782 |
+
" <td>0.936300</td>\n",
|
| 1783 |
+
" </tr>\n",
|
| 1784 |
+
" <tr>\n",
|
| 1785 |
+
" <td>9950</td>\n",
|
| 1786 |
+
" <td>0.986800</td>\n",
|
| 1787 |
+
" </tr>\n",
|
| 1788 |
+
" <tr>\n",
|
| 1789 |
+
" <td>10000</td>\n",
|
| 1790 |
+
" <td>0.915300</td>\n",
|
| 1791 |
+
" </tr>\n",
|
| 1792 |
" </tbody>\n",
|
| 1793 |
"</table><p>"
|
| 1794 |
],
|