Training in progress, step 24000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac08b42599d1bde48be74806637c6c061e7123fe79086fdd5f3704e9fd3d6ce1
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a587cba38b05004cfdcf48f4bea4b6d068091255cf02ec07324ae8e96318e4f0
|
| 3 |
size 1082379659
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a804dd9b4962bc1e7c8e5b51c83ce95f04ab0a366340b47fc4849e7d4ecffd6d
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:668b318436d635cfc651258a221542355f21124096cff5d5c7e78a7d5c81ab33
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1568,6 +1568,318 @@
|
|
| 1568 |
"eval_samples_per_second": 38.297,
|
| 1569 |
"eval_steps_per_second": 9.574,
|
| 1570 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1571 |
}
|
| 1572 |
],
|
| 1573 |
"logging_steps": 100,
|
|
@@ -1587,7 +1899,7 @@
|
|
| 1587 |
"attributes": {}
|
| 1588 |
}
|
| 1589 |
},
|
| 1590 |
-
"total_flos":
|
| 1591 |
"train_batch_size": 22,
|
| 1592 |
"trial_name": null,
|
| 1593 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3116883116883117,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 24000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1568 |
"eval_samples_per_second": 38.297,
|
| 1569 |
"eval_steps_per_second": 9.574,
|
| 1570 |
"step": 20000
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.261038961038961,
|
| 1574 |
+
"grad_norm": 0.1809331625699997,
|
| 1575 |
+
"learning_rate": 0.0009264499766083365,
|
| 1576 |
+
"loss": 2.8836,
|
| 1577 |
+
"step": 20100
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.2623376623376623,
|
| 1581 |
+
"grad_norm": 0.19160114228725433,
|
| 1582 |
+
"learning_rate": 0.0009256954993538877,
|
| 1583 |
+
"loss": 2.8881,
|
| 1584 |
+
"step": 20200
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.2636363636363636,
|
| 1588 |
+
"grad_norm": 0.1818685233592987,
|
| 1589 |
+
"learning_rate": 0.0009249374825821832,
|
| 1590 |
+
"loss": 2.8543,
|
| 1591 |
+
"step": 20300
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.2649350649350649,
|
| 1595 |
+
"grad_norm": 0.1778269112110138,
|
| 1596 |
+
"learning_rate": 0.0009241759325958815,
|
| 1597 |
+
"loss": 2.8741,
|
| 1598 |
+
"step": 20400
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.2662337662337662,
|
| 1602 |
+
"grad_norm": 0.1888059824705124,
|
| 1603 |
+
"learning_rate": 0.0009234108557270187,
|
| 1604 |
+
"loss": 2.8772,
|
| 1605 |
+
"step": 20500
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.2675324675324675,
|
| 1609 |
+
"grad_norm": 0.22666007280349731,
|
| 1610 |
+
"learning_rate": 0.000922642258336956,
|
| 1611 |
+
"loss": 2.9021,
|
| 1612 |
+
"step": 20600
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.2688311688311688,
|
| 1616 |
+
"grad_norm": 0.18350407481193542,
|
| 1617 |
+
"learning_rate": 0.0009218701468163267,
|
| 1618 |
+
"loss": 2.8845,
|
| 1619 |
+
"step": 20700
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.2701298701298701,
|
| 1623 |
+
"grad_norm": 0.17511753737926483,
|
| 1624 |
+
"learning_rate": 0.000921094527584982,
|
| 1625 |
+
"loss": 2.9005,
|
| 1626 |
+
"step": 20800
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.2714285714285714,
|
| 1630 |
+
"grad_norm": 0.18808013200759888,
|
| 1631 |
+
"learning_rate": 0.0009203154070919398,
|
| 1632 |
+
"loss": 2.8658,
|
| 1633 |
+
"step": 20900
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.2727272727272727,
|
| 1637 |
+
"grad_norm": 0.18752652406692505,
|
| 1638 |
+
"learning_rate": 0.0009195327918153292,
|
| 1639 |
+
"loss": 2.8649,
|
| 1640 |
+
"step": 21000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.2727272727272727,
|
| 1644 |
+
"eval_loss": 3.2498960494995117,
|
| 1645 |
+
"eval_runtime": 15.6914,
|
| 1646 |
+
"eval_samples_per_second": 36.708,
|
| 1647 |
+
"eval_steps_per_second": 9.177,
|
| 1648 |
+
"step": 21000
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.274025974025974,
|
| 1652 |
+
"grad_norm": 0.19540126621723175,
|
| 1653 |
+
"learning_rate": 0.0009187466882623372,
|
| 1654 |
+
"loss": 2.8755,
|
| 1655 |
+
"step": 21100
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.2753246753246753,
|
| 1659 |
+
"grad_norm": 0.18758288025856018,
|
| 1660 |
+
"learning_rate": 0.0009179571029691546,
|
| 1661 |
+
"loss": 2.8737,
|
| 1662 |
+
"step": 21200
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.2766233766233766,
|
| 1666 |
+
"grad_norm": 0.18555940687656403,
|
| 1667 |
+
"learning_rate": 0.0009171640425009224,
|
| 1668 |
+
"loss": 2.8626,
|
| 1669 |
+
"step": 21300
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.2779220779220779,
|
| 1673 |
+
"grad_norm": 0.18831279873847961,
|
| 1674 |
+
"learning_rate": 0.0009163675134516758,
|
| 1675 |
+
"loss": 2.883,
|
| 1676 |
+
"step": 21400
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.2792207792207792,
|
| 1680 |
+
"grad_norm": 0.19656601548194885,
|
| 1681 |
+
"learning_rate": 0.0009155675224442904,
|
| 1682 |
+
"loss": 2.8959,
|
| 1683 |
+
"step": 21500
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.2805194805194805,
|
| 1687 |
+
"grad_norm": 0.18778946995735168,
|
| 1688 |
+
"learning_rate": 0.0009147640761304266,
|
| 1689 |
+
"loss": 2.8723,
|
| 1690 |
+
"step": 21600
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.2818181818181818,
|
| 1694 |
+
"grad_norm": 0.1975911557674408,
|
| 1695 |
+
"learning_rate": 0.000913957181190475,
|
| 1696 |
+
"loss": 2.8724,
|
| 1697 |
+
"step": 21700
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.2831168831168831,
|
| 1701 |
+
"grad_norm": 0.18618452548980713,
|
| 1702 |
+
"learning_rate": 0.0009131468443334998,
|
| 1703 |
+
"loss": 2.8597,
|
| 1704 |
+
"step": 21800
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.2844155844155844,
|
| 1708 |
+
"grad_norm": 0.19419926404953003,
|
| 1709 |
+
"learning_rate": 0.0009123330722971841,
|
| 1710 |
+
"loss": 2.8398,
|
| 1711 |
+
"step": 21900
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.2857142857142857,
|
| 1715 |
+
"grad_norm": 0.1885763257741928,
|
| 1716 |
+
"learning_rate": 0.0009115158718477732,
|
| 1717 |
+
"loss": 2.875,
|
| 1718 |
+
"step": 22000
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.2857142857142857,
|
| 1722 |
+
"eval_loss": 3.2455015182495117,
|
| 1723 |
+
"eval_runtime": 14.7497,
|
| 1724 |
+
"eval_samples_per_second": 39.052,
|
| 1725 |
+
"eval_steps_per_second": 9.763,
|
| 1726 |
+
"step": 22000
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 0.287012987012987,
|
| 1730 |
+
"grad_norm": 0.17821335792541504,
|
| 1731 |
+
"learning_rate": 0.0009106952497800183,
|
| 1732 |
+
"loss": 2.8378,
|
| 1733 |
+
"step": 22100
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 0.2883116883116883,
|
| 1737 |
+
"grad_norm": 0.20162396132946014,
|
| 1738 |
+
"learning_rate": 0.0009098712129171207,
|
| 1739 |
+
"loss": 2.8512,
|
| 1740 |
+
"step": 22200
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 0.2896103896103896,
|
| 1744 |
+
"grad_norm": 0.21083980798721313,
|
| 1745 |
+
"learning_rate": 0.0009090437681106742,
|
| 1746 |
+
"loss": 2.8587,
|
| 1747 |
+
"step": 22300
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.2909090909090909,
|
| 1751 |
+
"grad_norm": 0.1923542320728302,
|
| 1752 |
+
"learning_rate": 0.0009082129222406087,
|
| 1753 |
+
"loss": 2.843,
|
| 1754 |
+
"step": 22400
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.2922077922077922,
|
| 1758 |
+
"grad_norm": 0.19237105548381805,
|
| 1759 |
+
"learning_rate": 0.0009073786822151326,
|
| 1760 |
+
"loss": 2.8554,
|
| 1761 |
+
"step": 22500
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.2935064935064935,
|
| 1765 |
+
"grad_norm": 0.1831800788640976,
|
| 1766 |
+
"learning_rate": 0.000906541054970676,
|
| 1767 |
+
"loss": 2.8928,
|
| 1768 |
+
"step": 22600
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 0.2948051948051948,
|
| 1772 |
+
"grad_norm": 0.20052975416183472,
|
| 1773 |
+
"learning_rate": 0.000905700047471832,
|
| 1774 |
+
"loss": 2.8462,
|
| 1775 |
+
"step": 22700
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.2961038961038961,
|
| 1779 |
+
"grad_norm": 0.20518037676811218,
|
| 1780 |
+
"learning_rate": 0.0009048556667113002,
|
| 1781 |
+
"loss": 2.8624,
|
| 1782 |
+
"step": 22800
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.2974025974025974,
|
| 1786 |
+
"grad_norm": 0.18524277210235596,
|
| 1787 |
+
"learning_rate": 0.0009040079197098268,
|
| 1788 |
+
"loss": 2.8683,
|
| 1789 |
+
"step": 22900
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.2987012987012987,
|
| 1793 |
+
"grad_norm": 0.18116071820259094,
|
| 1794 |
+
"learning_rate": 0.000903156813516148,
|
| 1795 |
+
"loss": 2.8335,
|
| 1796 |
+
"step": 23000
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.2987012987012987,
|
| 1800 |
+
"eval_loss": 3.236686944961548,
|
| 1801 |
+
"eval_runtime": 16.906,
|
| 1802 |
+
"eval_samples_per_second": 34.071,
|
| 1803 |
+
"eval_steps_per_second": 8.518,
|
| 1804 |
+
"step": 23000
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 0.3,
|
| 1808 |
+
"grad_norm": 0.2058299481868744,
|
| 1809 |
+
"learning_rate": 0.0009023023552069303,
|
| 1810 |
+
"loss": 2.8548,
|
| 1811 |
+
"step": 23100
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 0.3012987012987013,
|
| 1815 |
+
"grad_norm": 0.21021772921085358,
|
| 1816 |
+
"learning_rate": 0.0009014445518867116,
|
| 1817 |
+
"loss": 2.8435,
|
| 1818 |
+
"step": 23200
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 0.3025974025974026,
|
| 1822 |
+
"grad_norm": 0.18895122408866882,
|
| 1823 |
+
"learning_rate": 0.000900583410687843,
|
| 1824 |
+
"loss": 2.839,
|
| 1825 |
+
"step": 23300
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 0.3038961038961039,
|
| 1829 |
+
"grad_norm": 0.18983018398284912,
|
| 1830 |
+
"learning_rate": 0.0008997189387704286,
|
| 1831 |
+
"loss": 2.843,
|
| 1832 |
+
"step": 23400
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 0.3051948051948052,
|
| 1836 |
+
"grad_norm": 0.21453820168972015,
|
| 1837 |
+
"learning_rate": 0.0008988511433222664,
|
| 1838 |
+
"loss": 2.8443,
|
| 1839 |
+
"step": 23500
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.3064935064935065,
|
| 1843 |
+
"grad_norm": 0.1873568445444107,
|
| 1844 |
+
"learning_rate": 0.0008979800315587885,
|
| 1845 |
+
"loss": 2.8473,
|
| 1846 |
+
"step": 23600
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 0.3077922077922078,
|
| 1850 |
+
"grad_norm": 0.19516156613826752,
|
| 1851 |
+
"learning_rate": 0.000897105610723001,
|
| 1852 |
+
"loss": 2.8579,
|
| 1853 |
+
"step": 23700
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 0.3090909090909091,
|
| 1857 |
+
"grad_norm": 0.1961786150932312,
|
| 1858 |
+
"learning_rate": 0.000896227888085424,
|
| 1859 |
+
"loss": 2.8282,
|
| 1860 |
+
"step": 23800
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 0.3103896103896104,
|
| 1864 |
+
"grad_norm": 0.19147805869579315,
|
| 1865 |
+
"learning_rate": 0.0008953468709440309,
|
| 1866 |
+
"loss": 2.8734,
|
| 1867 |
+
"step": 23900
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 0.3116883116883117,
|
| 1871 |
+
"grad_norm": 0.20040926337242126,
|
| 1872 |
+
"learning_rate": 0.0008944625666241877,
|
| 1873 |
+
"loss": 2.8491,
|
| 1874 |
+
"step": 24000
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 0.3116883116883117,
|
| 1878 |
+
"eval_loss": 3.2374658584594727,
|
| 1879 |
+
"eval_runtime": 16.1905,
|
| 1880 |
+
"eval_samples_per_second": 35.576,
|
| 1881 |
+
"eval_steps_per_second": 8.894,
|
| 1882 |
+
"step": 24000
|
| 1883 |
}
|
| 1884 |
],
|
| 1885 |
"logging_steps": 100,
|
|
|
|
| 1899 |
"attributes": {}
|
| 1900 |
}
|
| 1901 |
},
|
| 1902 |
+
"total_flos": 7.1446353149952e+17,
|
| 1903 |
"train_batch_size": 22,
|
| 1904 |
"trial_name": null,
|
| 1905 |
"trial_params": null
|