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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91939e0b72ed547f5c93280b369185295f37271995fd46a6edb271145c07605c
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4519573d36d90ba131c7875410ba23ca2fd486818679adec360ef2a2dd49f18
|
| 3 |
size 938825803
|
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 sha256:68a1e729745879daefb80abbed0a2e5c919e4730374ec35c85a8be9176df6bb5
|
| 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:d44e1b79b7ca3c1d7f485201d49324d3b81b5df8a48270324b94dd9cdfe85a81
|
| 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": 84.397,
|
| 1569 |
"eval_steps_per_second": 21.099,
|
| 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": 0.21818181818181817,
|
| 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": 84.397,
|
| 1569 |
"eval_steps_per_second": 21.099,
|
| 1570 |
"step": 20000
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.18272727272727274,
|
| 1574 |
+
"grad_norm": 0.1414630264043808,
|
| 1575 |
+
"learning_rate": 0.000920810102137561,
|
| 1576 |
+
"loss": 2.8807022094726564,
|
| 1577 |
+
"step": 20100
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.18363636363636363,
|
| 1581 |
+
"grad_norm": 0.1559121161699295,
|
| 1582 |
+
"learning_rate": 0.0009200361112663695,
|
| 1583 |
+
"loss": 2.845583190917969,
|
| 1584 |
+
"step": 20200
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.18454545454545454,
|
| 1588 |
+
"grad_norm": 0.13616813719272614,
|
| 1589 |
+
"learning_rate": 0.0009192586849267957,
|
| 1590 |
+
"loss": 2.8783746337890626,
|
| 1591 |
+
"step": 20300
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.18545454545454546,
|
| 1595 |
+
"grad_norm": 0.15556134283542633,
|
| 1596 |
+
"learning_rate": 0.0009184778294773968,
|
| 1597 |
+
"loss": 2.84674072265625,
|
| 1598 |
+
"step": 20400
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.18636363636363637,
|
| 1602 |
+
"grad_norm": 0.1401907503604889,
|
| 1603 |
+
"learning_rate": 0.0009176935513047762,
|
| 1604 |
+
"loss": 2.8818963623046874,
|
| 1605 |
+
"step": 20500
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.18727272727272729,
|
| 1609 |
+
"grad_norm": 0.1431131362915039,
|
| 1610 |
+
"learning_rate": 0.0009169058568235323,
|
| 1611 |
+
"loss": 2.8781854248046876,
|
| 1612 |
+
"step": 20600
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.18818181818181817,
|
| 1616 |
+
"grad_norm": 0.17515692114830017,
|
| 1617 |
+
"learning_rate": 0.0009161147524762053,
|
| 1618 |
+
"loss": 2.85051025390625,
|
| 1619 |
+
"step": 20700
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.1890909090909091,
|
| 1623 |
+
"grad_norm": 0.1567743867635727,
|
| 1624 |
+
"learning_rate": 0.0009153202447332243,
|
| 1625 |
+
"loss": 2.8653643798828123,
|
| 1626 |
+
"step": 20800
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.19,
|
| 1630 |
+
"grad_norm": 0.14393377304077148,
|
| 1631 |
+
"learning_rate": 0.000914522340092855,
|
| 1632 |
+
"loss": 2.881787109375,
|
| 1633 |
+
"step": 20900
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.19090909090909092,
|
| 1637 |
+
"grad_norm": 0.1467711478471756,
|
| 1638 |
+
"learning_rate": 0.0009137210450811462,
|
| 1639 |
+
"loss": 2.9003524780273438,
|
| 1640 |
+
"step": 21000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.19090909090909092,
|
| 1644 |
+
"eval_loss": 3.210813283920288,
|
| 1645 |
+
"eval_runtime": 6.8446,
|
| 1646 |
+
"eval_samples_per_second": 84.154,
|
| 1647 |
+
"eval_steps_per_second": 21.038,
|
| 1648 |
+
"step": 21000
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.1918181818181818,
|
| 1652 |
+
"grad_norm": 0.14093157649040222,
|
| 1653 |
+
"learning_rate": 0.0009129163662518766,
|
| 1654 |
+
"loss": 2.834397277832031,
|
| 1655 |
+
"step": 21100
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.19272727272727272,
|
| 1659 |
+
"grad_norm": 0.14963804185390472,
|
| 1660 |
+
"learning_rate": 0.000912108310186501,
|
| 1661 |
+
"loss": 2.869900817871094,
|
| 1662 |
+
"step": 21200
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.19363636363636363,
|
| 1666 |
+
"grad_norm": 0.13998101651668549,
|
| 1667 |
+
"learning_rate": 0.0009112968834940965,
|
| 1668 |
+
"loss": 2.8689230346679686,
|
| 1669 |
+
"step": 21300
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.19454545454545455,
|
| 1673 |
+
"grad_norm": 0.13820187747478485,
|
| 1674 |
+
"learning_rate": 0.0009104820928113083,
|
| 1675 |
+
"loss": 2.840967102050781,
|
| 1676 |
+
"step": 21400
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.19545454545454546,
|
| 1680 |
+
"grad_norm": 0.1391438990831375,
|
| 1681 |
+
"learning_rate": 0.0009096639448022963,
|
| 1682 |
+
"loss": 2.839700927734375,
|
| 1683 |
+
"step": 21500
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.19636363636363635,
|
| 1687 |
+
"grad_norm": 0.15131688117980957,
|
| 1688 |
+
"learning_rate": 0.0009088424461586793,
|
| 1689 |
+
"loss": 2.8546661376953124,
|
| 1690 |
+
"step": 21600
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.19727272727272727,
|
| 1694 |
+
"grad_norm": 0.14853839576244354,
|
| 1695 |
+
"learning_rate": 0.000908017603599481,
|
| 1696 |
+
"loss": 2.8781912231445315,
|
| 1697 |
+
"step": 21700
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.19818181818181818,
|
| 1701 |
+
"grad_norm": 0.16618646681308746,
|
| 1702 |
+
"learning_rate": 0.0009071894238710749,
|
| 1703 |
+
"loss": 2.8425857543945314,
|
| 1704 |
+
"step": 21800
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.1990909090909091,
|
| 1708 |
+
"grad_norm": 0.13768044114112854,
|
| 1709 |
+
"learning_rate": 0.0009063579137471296,
|
| 1710 |
+
"loss": 2.8587716674804686,
|
| 1711 |
+
"step": 21900
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.2,
|
| 1715 |
+
"grad_norm": 0.1462126523256302,
|
| 1716 |
+
"learning_rate": 0.0009055230800285523,
|
| 1717 |
+
"loss": 2.854002685546875,
|
| 1718 |
+
"step": 22000
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.2,
|
| 1722 |
+
"eval_loss": 3.1955888271331787,
|
| 1723 |
+
"eval_runtime": 6.8048,
|
| 1724 |
+
"eval_samples_per_second": 84.646,
|
| 1725 |
+
"eval_steps_per_second": 21.161,
|
| 1726 |
+
"step": 22000
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 0.2009090909090909,
|
| 1730 |
+
"grad_norm": 0.1481468826532364,
|
| 1731 |
+
"learning_rate": 0.0009046849295434343,
|
| 1732 |
+
"loss": 2.848748779296875,
|
| 1733 |
+
"step": 22100
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 0.2018181818181818,
|
| 1737 |
+
"grad_norm": 0.13478662073612213,
|
| 1738 |
+
"learning_rate": 0.0009038434691469946,
|
| 1739 |
+
"loss": 2.859345703125,
|
| 1740 |
+
"step": 22200
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 0.20272727272727273,
|
| 1744 |
+
"grad_norm": 0.1626402586698532,
|
| 1745 |
+
"learning_rate": 0.0009029987057215234,
|
| 1746 |
+
"loss": 2.879791259765625,
|
| 1747 |
+
"step": 22300
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.20363636363636364,
|
| 1751 |
+
"grad_norm": 0.1763114631175995,
|
| 1752 |
+
"learning_rate": 0.0009021506461763272,
|
| 1753 |
+
"loss": 2.8198529052734376,
|
| 1754 |
+
"step": 22400
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.20454545454545456,
|
| 1758 |
+
"grad_norm": 0.1592358946800232,
|
| 1759 |
+
"learning_rate": 0.0009012992974476706,
|
| 1760 |
+
"loss": 2.8292422485351563,
|
| 1761 |
+
"step": 22500
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.20545454545454545,
|
| 1765 |
+
"grad_norm": 0.16374371945858002,
|
| 1766 |
+
"learning_rate": 0.0009004446664987209,
|
| 1767 |
+
"loss": 2.839366149902344,
|
| 1768 |
+
"step": 22600
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 0.20636363636363636,
|
| 1772 |
+
"grad_norm": 0.16180269420146942,
|
| 1773 |
+
"learning_rate": 0.0008995867603194905,
|
| 1774 |
+
"loss": 2.824099426269531,
|
| 1775 |
+
"step": 22700
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.20727272727272728,
|
| 1779 |
+
"grad_norm": 0.1817290335893631,
|
| 1780 |
+
"learning_rate": 0.0008987255859267796,
|
| 1781 |
+
"loss": 2.852536926269531,
|
| 1782 |
+
"step": 22800
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.2081818181818182,
|
| 1786 |
+
"grad_norm": 0.1729678362607956,
|
| 1787 |
+
"learning_rate": 0.0008978611503641194,
|
| 1788 |
+
"loss": 2.87031005859375,
|
| 1789 |
+
"step": 22900
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.20909090909090908,
|
| 1793 |
+
"grad_norm": 0.13794034719467163,
|
| 1794 |
+
"learning_rate": 0.000896993460701714,
|
| 1795 |
+
"loss": 2.820664367675781,
|
| 1796 |
+
"step": 23000
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.20909090909090908,
|
| 1800 |
+
"eval_loss": 3.189971923828125,
|
| 1801 |
+
"eval_runtime": 6.8545,
|
| 1802 |
+
"eval_samples_per_second": 84.032,
|
| 1803 |
+
"eval_steps_per_second": 21.008,
|
| 1804 |
+
"step": 23000
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 0.21,
|
| 1808 |
+
"grad_norm": 0.14675737917423248,
|
| 1809 |
+
"learning_rate": 0.0008961225240363826,
|
| 1810 |
+
"loss": 2.834775390625,
|
| 1811 |
+
"step": 23100
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 0.2109090909090909,
|
| 1815 |
+
"grad_norm": 0.14198128879070282,
|
| 1816 |
+
"learning_rate": 0.0008952483474915021,
|
| 1817 |
+
"loss": 2.8415087890625,
|
| 1818 |
+
"step": 23200
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 0.21181818181818182,
|
| 1822 |
+
"grad_norm": 0.15185648202896118,
|
| 1823 |
+
"learning_rate": 0.0008943709382169476,
|
| 1824 |
+
"loss": 2.8519711303710937,
|
| 1825 |
+
"step": 23300
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 0.21272727272727274,
|
| 1829 |
+
"grad_norm": 0.15163777768611908,
|
| 1830 |
+
"learning_rate": 0.0008934903033890352,
|
| 1831 |
+
"loss": 2.8500375366210937,
|
| 1832 |
+
"step": 23400
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 0.21363636363636362,
|
| 1836 |
+
"grad_norm": 0.15410897135734558,
|
| 1837 |
+
"learning_rate": 0.0008926064502104623,
|
| 1838 |
+
"loss": 2.8353033447265625,
|
| 1839 |
+
"step": 23500
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.21454545454545454,
|
| 1843 |
+
"grad_norm": 0.22796989977359772,
|
| 1844 |
+
"learning_rate": 0.0008917193859102497,
|
| 1845 |
+
"loss": 2.8228555297851563,
|
| 1846 |
+
"step": 23600
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 0.21545454545454545,
|
| 1850 |
+
"grad_norm": 0.1605440229177475,
|
| 1851 |
+
"learning_rate": 0.0008908291177436813,
|
| 1852 |
+
"loss": 2.8567230224609377,
|
| 1853 |
+
"step": 23700
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 0.21636363636363637,
|
| 1857 |
+
"grad_norm": 0.16412964463233948,
|
| 1858 |
+
"learning_rate": 0.0008899356529922459,
|
| 1859 |
+
"loss": 2.8504483032226564,
|
| 1860 |
+
"step": 23800
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 0.21727272727272728,
|
| 1864 |
+
"grad_norm": 0.13510747253894806,
|
| 1865 |
+
"learning_rate": 0.0008890389989635767,
|
| 1866 |
+
"loss": 2.87345458984375,
|
| 1867 |
+
"step": 23900
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 0.21818181818181817,
|
| 1871 |
+
"grad_norm": 0.14522412419319153,
|
| 1872 |
+
"learning_rate": 0.0008881391629913921,
|
| 1873 |
+
"loss": 2.827217712402344,
|
| 1874 |
+
"step": 24000
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 0.21818181818181817,
|
| 1878 |
+
"eval_loss": 3.1835873126983643,
|
| 1879 |
+
"eval_runtime": 6.8315,
|
| 1880 |
+
"eval_samples_per_second": 84.315,
|
| 1881 |
+
"eval_steps_per_second": 21.079,
|
| 1882 |
+
"step": 24000
|
| 1883 |
}
|
| 1884 |
],
|
| 1885 |
"logging_steps": 100,
|
|
|
|
| 1899 |
"attributes": {}
|
| 1900 |
}
|
| 1901 |
},
|
| 1902 |
+
"total_flos": 5.97949943906304e+17,
|
| 1903 |
"train_batch_size": 22,
|
| 1904 |
"trial_name": null,
|
| 1905 |
"trial_params": null
|