Training in progress, step 60000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +303 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100170757
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ceedefb856fd84795e75aee417a2889e7dfef00f9cca82e610fbafac5203514
|
| 3 |
size 100170757
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c51f436fc6ff7c66c8286fca81fd6d00dc485176f29ebe17de85db28a4fa91b5
|
| 3 |
size 146774203
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff9803e49c54da5b93ea63a8f9cfb55e640978474df5d52e215ba5da04a71f90
|
| 3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 246897640
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e429486456e317e2d30183574218e6d221698c823284eb9740704ef563e5d5d
|
| 3 |
size 246897640
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -1506,11 +1506,311 @@
|
|
| 1506 |
"learning_rate": 0.0002800029021041788,
|
| 1507 |
"loss": 3.367,
|
| 1508 |
"step": 50000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1509 |
}
|
| 1510 |
],
|
| 1511 |
"max_steps": 500000,
|
| 1512 |
"num_train_epochs": 3,
|
| 1513 |
-
"total_flos":
|
| 1514 |
"trial_name": null,
|
| 1515 |
"trial_params": null
|
| 1516 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2578427159432746,
|
| 5 |
+
"global_step": 60000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1506 |
"learning_rate": 0.0002800029021041788,
|
| 1507 |
"loss": 3.367,
|
| 1508 |
"step": 50000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.22,
|
| 1512 |
+
"learning_rate": 0.00028174626854371866,
|
| 1513 |
+
"loss": 3.3536,
|
| 1514 |
+
"step": 50200
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.22,
|
| 1518 |
+
"learning_rate": 0.0002834938154241324,
|
| 1519 |
+
"loss": 3.3545,
|
| 1520 |
+
"step": 50400
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.22,
|
| 1524 |
+
"learning_rate": 0.00028524551208266224,
|
| 1525 |
+
"loss": 3.369,
|
| 1526 |
+
"step": 50600
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.22,
|
| 1530 |
+
"learning_rate": 0.0002870013277837379,
|
| 1531 |
+
"loss": 3.3578,
|
| 1532 |
+
"step": 50800
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 0.22,
|
| 1536 |
+
"learning_rate": 0.00028876123171951576,
|
| 1537 |
+
"loss": 3.3439,
|
| 1538 |
+
"step": 51000
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.22,
|
| 1542 |
+
"learning_rate": 0.0002905251930104192,
|
| 1543 |
+
"loss": 3.3568,
|
| 1544 |
+
"step": 51200
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 0.22,
|
| 1548 |
+
"learning_rate": 0.00029229318070568056,
|
| 1549 |
+
"loss": 3.3605,
|
| 1550 |
+
"step": 51400
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.22,
|
| 1554 |
+
"learning_rate": 0.0002940651637838844,
|
| 1555 |
+
"loss": 3.358,
|
| 1556 |
+
"step": 51600
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.22,
|
| 1560 |
+
"learning_rate": 0.0002958411111535111,
|
| 1561 |
+
"loss": 3.3603,
|
| 1562 |
+
"step": 51800
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.22,
|
| 1566 |
+
"learning_rate": 0.00029762099165348357,
|
| 1567 |
+
"loss": 3.3527,
|
| 1568 |
+
"step": 52000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.22,
|
| 1572 |
+
"learning_rate": 0.0002994047740537128,
|
| 1573 |
+
"loss": 3.3409,
|
| 1574 |
+
"step": 52200
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 0.23,
|
| 1578 |
+
"learning_rate": 0.00030119242705564664,
|
| 1579 |
+
"loss": 3.3495,
|
| 1580 |
+
"step": 52400
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 0.23,
|
| 1584 |
+
"learning_rate": 0.00030298391929281857,
|
| 1585 |
+
"loss": 3.328,
|
| 1586 |
+
"step": 52600
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.23,
|
| 1590 |
+
"learning_rate": 0.00030477921933139823,
|
| 1591 |
+
"loss": 3.3592,
|
| 1592 |
+
"step": 52800
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.23,
|
| 1596 |
+
"learning_rate": 0.00030657829567074305,
|
| 1597 |
+
"loss": 3.36,
|
| 1598 |
+
"step": 53000
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.23,
|
| 1602 |
+
"learning_rate": 0.0003083811167439507,
|
| 1603 |
+
"loss": 3.3558,
|
| 1604 |
+
"step": 53200
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 0.23,
|
| 1608 |
+
"learning_rate": 0.0003101876509184131,
|
| 1609 |
+
"loss": 3.3206,
|
| 1610 |
+
"step": 53400
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.23,
|
| 1614 |
+
"learning_rate": 0.00031199786649637145,
|
| 1615 |
+
"loss": 3.3376,
|
| 1616 |
+
"step": 53600
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 0.23,
|
| 1620 |
+
"learning_rate": 0.0003138117317154723,
|
| 1621 |
+
"loss": 3.3242,
|
| 1622 |
+
"step": 53800
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 0.23,
|
| 1626 |
+
"learning_rate": 0.0003156292147493255,
|
| 1627 |
+
"loss": 3.3368,
|
| 1628 |
+
"step": 54000
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 0.23,
|
| 1632 |
+
"learning_rate": 0.00031745028370806165,
|
| 1633 |
+
"loss": 3.3366,
|
| 1634 |
+
"step": 54200
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.23,
|
| 1638 |
+
"learning_rate": 0.00031927490663889203,
|
| 1639 |
+
"loss": 3.3267,
|
| 1640 |
+
"step": 54400
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.23,
|
| 1644 |
+
"learning_rate": 0.00032110305152666953,
|
| 1645 |
+
"loss": 3.302,
|
| 1646 |
+
"step": 54600
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 0.24,
|
| 1650 |
+
"learning_rate": 0.00032293468629445007,
|
| 1651 |
+
"loss": 3.3237,
|
| 1652 |
+
"step": 54800
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.24,
|
| 1656 |
+
"learning_rate": 0.00032476977880405546,
|
| 1657 |
+
"loss": 3.3207,
|
| 1658 |
+
"step": 55000
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 0.24,
|
| 1662 |
+
"learning_rate": 0.00032660829685663773,
|
| 1663 |
+
"loss": 3.3215,
|
| 1664 |
+
"step": 55200
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 0.24,
|
| 1668 |
+
"learning_rate": 0.00032845020819324334,
|
| 1669 |
+
"loss": 3.3107,
|
| 1670 |
+
"step": 55400
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 0.24,
|
| 1674 |
+
"learning_rate": 0.0003302954804953797,
|
| 1675 |
+
"loss": 3.3153,
|
| 1676 |
+
"step": 55600
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.24,
|
| 1680 |
+
"learning_rate": 0.00033214408138558256,
|
| 1681 |
+
"loss": 3.341,
|
| 1682 |
+
"step": 55800
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.24,
|
| 1686 |
+
"learning_rate": 0.0003339959784279831,
|
| 1687 |
+
"loss": 3.3183,
|
| 1688 |
+
"step": 56000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 0.24,
|
| 1692 |
+
"learning_rate": 0.00033585113912887776,
|
| 1693 |
+
"loss": 3.3295,
|
| 1694 |
+
"step": 56200
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.24,
|
| 1698 |
+
"learning_rate": 0.0003377095309372985,
|
| 1699 |
+
"loss": 3.3293,
|
| 1700 |
+
"step": 56400
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.24,
|
| 1704 |
+
"learning_rate": 0.0003395711212455839,
|
| 1705 |
+
"loss": 3.3181,
|
| 1706 |
+
"step": 56600
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 0.24,
|
| 1710 |
+
"learning_rate": 0.0003414358773899506,
|
| 1711 |
+
"loss": 3.3075,
|
| 1712 |
+
"step": 56800
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 0.24,
|
| 1716 |
+
"learning_rate": 0.00034330376665106695,
|
| 1717 |
+
"loss": 3.3213,
|
| 1718 |
+
"step": 57000
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.25,
|
| 1722 |
+
"learning_rate": 0.0003451747562546278,
|
| 1723 |
+
"loss": 3.3105,
|
| 1724 |
+
"step": 57200
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.25,
|
| 1728 |
+
"learning_rate": 0.00034704881337192784,
|
| 1729 |
+
"loss": 3.2828,
|
| 1730 |
+
"step": 57400
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 0.25,
|
| 1734 |
+
"learning_rate": 0.00034892590512043947,
|
| 1735 |
+
"loss": 3.3044,
|
| 1736 |
+
"step": 57600
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.25,
|
| 1740 |
+
"learning_rate": 0.00035080599856438877,
|
| 1741 |
+
"loss": 3.306,
|
| 1742 |
+
"step": 57800
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 0.25,
|
| 1746 |
+
"learning_rate": 0.00035268906071533304,
|
| 1747 |
+
"loss": 3.3226,
|
| 1748 |
+
"step": 58000
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 0.25,
|
| 1752 |
+
"learning_rate": 0.0003545750585327406,
|
| 1753 |
+
"loss": 3.3227,
|
| 1754 |
+
"step": 58200
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.25,
|
| 1758 |
+
"learning_rate": 0.0003564639589245703,
|
| 1759 |
+
"loss": 3.2888,
|
| 1760 |
+
"step": 58400
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.25,
|
| 1764 |
+
"learning_rate": 0.0003583557287478512,
|
| 1765 |
+
"loss": 3.2918,
|
| 1766 |
+
"step": 58600
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.25,
|
| 1770 |
+
"learning_rate": 0.0003602503348092654,
|
| 1771 |
+
"loss": 3.2857,
|
| 1772 |
+
"step": 58800
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 0.25,
|
| 1776 |
+
"learning_rate": 0.0003621477438657296,
|
| 1777 |
+
"loss": 3.324,
|
| 1778 |
+
"step": 59000
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 0.25,
|
| 1782 |
+
"learning_rate": 0.00036404792262497885,
|
| 1783 |
+
"loss": 3.2991,
|
| 1784 |
+
"step": 59200
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 0.26,
|
| 1788 |
+
"learning_rate": 0.00036595083774615053,
|
| 1789 |
+
"loss": 3.2798,
|
| 1790 |
+
"step": 59400
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 0.26,
|
| 1794 |
+
"learning_rate": 0.0003678564558403689,
|
| 1795 |
+
"loss": 3.3164,
|
| 1796 |
+
"step": 59600
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.26,
|
| 1800 |
+
"learning_rate": 0.0003697647434713321,
|
| 1801 |
+
"loss": 3.2885,
|
| 1802 |
+
"step": 59800
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.26,
|
| 1806 |
+
"learning_rate": 0.0003716756671558975,
|
| 1807 |
+
"loss": 3.3157,
|
| 1808 |
+
"step": 60000
|
| 1809 |
}
|
| 1810 |
],
|
| 1811 |
"max_steps": 500000,
|
| 1812 |
"num_train_epochs": 3,
|
| 1813 |
+
"total_flos": 9.562979893248e+16,
|
| 1814 |
"trial_name": null,
|
| 1815 |
"trial_params": null
|
| 1816 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c51f436fc6ff7c66c8286fca81fd6d00dc485176f29ebe17de85db28a4fa91b5
|
| 3 |
size 146774203
|