Training in progress, step 130000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +139 -3
- last-checkpoint/training_args.bin +2 -2
- pytorch_model.bin +1 -1
- training_args.bin +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893439185
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90898868bd889ea276f797a53d8b665e23905ceffbb0c399cdd9fdf53208357f
|
3 |
size 893439185
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44e09bdae8806b91fbc10b97bb78e984559d5843803f34f83ae13bec03f9aedd
|
3 |
size 449471589
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15587
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88004fc539503ca7b97859aa1d0c5a82fcb7f351b44fb5ff1b5865391c2b3cde
|
3 |
size 15587
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c66d64016310bb2663dcec6c225164473113a433baa255e11fdf3b0cbfe9cd7
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f5e5f4eb24c3d48634235c80df17254ed52671e30811d1041e058ad2570720f
|
3 |
size 623
|
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,
|
@@ -1638,11 +1638,147 @@
|
|
1638 |
"eval_samples_per_second": 147.554,
|
1639 |
"eval_steps_per_second": 2.306,
|
1640 |
"step": 120000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1641 |
}
|
1642 |
],
|
1643 |
"max_steps": 200000,
|
1644 |
"num_train_epochs": 9223372036854775807,
|
1645 |
-
"total_flos":
|
1646 |
"trial_name": null,
|
1647 |
"trial_params": null
|
1648 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.05,
|
5 |
+
"global_step": 130000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1638 |
"eval_samples_per_second": 147.554,
|
1639 |
"eval_steps_per_second": 2.306,
|
1640 |
"step": 120000
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.0,
|
1644 |
+
"learning_rate": 4.105597684039436e-05,
|
1645 |
+
"loss": 0.4022,
|
1646 |
+
"step": 120500
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 0.01,
|
1650 |
+
"learning_rate": 4.071816951499159e-05,
|
1651 |
+
"loss": 0.3996,
|
1652 |
+
"step": 121000
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 0.01,
|
1656 |
+
"learning_rate": 4.038194014319665e-05,
|
1657 |
+
"loss": 0.3976,
|
1658 |
+
"step": 121500
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 0.01,
|
1662 |
+
"learning_rate": 4.00459618594495e-05,
|
1663 |
+
"loss": 0.3971,
|
1664 |
+
"step": 122000
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 0.01,
|
1668 |
+
"learning_rate": 3.971093010680468e-05,
|
1669 |
+
"loss": 0.3963,
|
1670 |
+
"step": 122500
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 0.01,
|
1674 |
+
"learning_rate": 3.937686555159882e-05,
|
1675 |
+
"loss": 0.3957,
|
1676 |
+
"step": 123000
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 0.02,
|
1680 |
+
"learning_rate": 3.9044453954514625e-05,
|
1681 |
+
"loss": 0.395,
|
1682 |
+
"step": 123500
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.02,
|
1686 |
+
"learning_rate": 3.871238351611711e-05,
|
1687 |
+
"loss": 0.3956,
|
1688 |
+
"step": 124000
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 0.02,
|
1692 |
+
"learning_rate": 3.83820029131894e-05,
|
1693 |
+
"loss": 0.3954,
|
1694 |
+
"step": 124500
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 0.03,
|
1698 |
+
"learning_rate": 3.805200836123052e-05,
|
1699 |
+
"loss": 0.394,
|
1700 |
+
"step": 125000
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 0.03,
|
1704 |
+
"eval_loss": 0.3622290790081024,
|
1705 |
+
"eval_runtime": 282.4866,
|
1706 |
+
"eval_samples_per_second": 152.22,
|
1707 |
+
"eval_steps_per_second": 2.379,
|
1708 |
+
"step": 125000
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"epoch": 0.03,
|
1712 |
+
"learning_rate": 3.772308333681807e-05,
|
1713 |
+
"loss": 0.3947,
|
1714 |
+
"step": 125500
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 0.03,
|
1718 |
+
"learning_rate": 3.739524812959698e-05,
|
1719 |
+
"loss": 0.3934,
|
1720 |
+
"step": 126000
|
1721 |
+
},
|
1722 |
+
{
|
1723 |
+
"epoch": 0.03,
|
1724 |
+
"learning_rate": 3.7068522961987034e-05,
|
1725 |
+
"loss": 0.3918,
|
1726 |
+
"step": 126500
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 0.04,
|
1730 |
+
"learning_rate": 3.6742927987935615e-05,
|
1731 |
+
"loss": 0.3942,
|
1732 |
+
"step": 127000
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 0.04,
|
1736 |
+
"learning_rate": 3.6418483291674376e-05,
|
1737 |
+
"loss": 0.3934,
|
1738 |
+
"step": 127500
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.04,
|
1742 |
+
"learning_rate": 3.6095208886480486e-05,
|
1743 |
+
"loss": 0.3927,
|
1744 |
+
"step": 128000
|
1745 |
+
},
|
1746 |
+
{
|
1747 |
+
"epoch": 0.04,
|
1748 |
+
"learning_rate": 3.577312471344201e-05,
|
1749 |
+
"loss": 0.3949,
|
1750 |
+
"step": 128500
|
1751 |
+
},
|
1752 |
+
{
|
1753 |
+
"epoch": 0.04,
|
1754 |
+
"learning_rate": 3.545225064022787e-05,
|
1755 |
+
"loss": 0.3927,
|
1756 |
+
"step": 129000
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 0.05,
|
1760 |
+
"learning_rate": 3.513324450767193e-05,
|
1761 |
+
"loss": 0.3933,
|
1762 |
+
"step": 129500
|
1763 |
+
},
|
1764 |
+
{
|
1765 |
+
"epoch": 0.05,
|
1766 |
+
"learning_rate": 3.481484741846708e-05,
|
1767 |
+
"loss": 0.3911,
|
1768 |
+
"step": 130000
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 0.05,
|
1772 |
+
"eval_loss": 0.3602633476257324,
|
1773 |
+
"eval_runtime": 265.9858,
|
1774 |
+
"eval_samples_per_second": 161.663,
|
1775 |
+
"eval_steps_per_second": 2.526,
|
1776 |
+
"step": 130000
|
1777 |
}
|
1778 |
],
|
1779 |
"max_steps": 200000,
|
1780 |
"num_train_epochs": 9223372036854775807,
|
1781 |
+
"total_flos": 3.061409875741901e+21,
|
1782 |
"trial_name": null,
|
1783 |
"trial_params": null
|
1784 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:841f2226ec981588ac5154e03a2609704f2d84e74bad6f5a9c0f405b772a0001
|
3 |
+
size 5551
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44e09bdae8806b91fbc10b97bb78e984559d5843803f34f83ae13bec03f9aedd
|
3 |
size 449471589
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:841f2226ec981588ac5154e03a2609704f2d84e74bad6f5a9c0f405b772a0001
|
3 |
+
size 5551
|