Training in progress, step 145000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- 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 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dfe64e849ed38be0c116bf69502ab6ef673c3bfbb07d2a79ac601fd7abada84
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:655b828bf25e09d93b3a829341a96b780ef65754b049aae3719f02e2c2832c66
|
3 |
size 201355195
|
last-checkpoint/rng_state_0.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:eaa575de425b3b6c389e6e8114c168b50828ecdc45cd1c9d7720b1b0c56d3927
|
3 |
size 14503
|
last-checkpoint/rng_state_1.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 sha256:0e2381d7111aef0a952be74ccc43cf3d5aa266953bd08dd244c0a6b9d757e25d
|
3 |
size 14503
|
last-checkpoint/rng_state_2.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:da9027a0e55164e62a390848b61914abfd2e8c206179d8f0b6727d85ed77643f
|
3 |
size 14503
|
last-checkpoint/rng_state_3.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:d8e2fe6e6bdabd7edc33ae3f760b1ec4396638c232770774464ee59bd6e64ff7
|
3 |
size 14503
|
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 sha256:5da286168e5064f0d0a7ce456ddb33da625498b14979026402cfccd39d5838b1
|
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 sha256:79d75c9447e835638ffa3474c117803239ed9981e80652713d41db8acbe224ff
|
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": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1686,6 +1686,66 @@
|
|
1686 |
"learning_rate": 0.00012463797674266635,
|
1687 |
"loss": 0.3409,
|
1688 |
"step": 140000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1689 |
}
|
1690 |
],
|
1691 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.4680851063829787,
|
5 |
+
"global_step": 145000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1686 |
"learning_rate": 0.00012463797674266635,
|
1687 |
"loss": 0.3409,
|
1688 |
"step": 140000
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 2.39,
|
1692 |
+
"learning_rate": 0.00012446835960053801,
|
1693 |
+
"loss": 0.3407,
|
1694 |
+
"step": 140500
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 2.4,
|
1698 |
+
"learning_rate": 0.000124298303573653,
|
1699 |
+
"loss": 0.3406,
|
1700 |
+
"step": 141000
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 2.41,
|
1704 |
+
"learning_rate": 0.0001241278103403957,
|
1705 |
+
"loss": 0.3405,
|
1706 |
+
"step": 141500
|
1707 |
+
},
|
1708 |
+
{
|
1709 |
+
"epoch": 2.42,
|
1710 |
+
"learning_rate": 0.00012395722387451133,
|
1711 |
+
"loss": 0.3406,
|
1712 |
+
"step": 142000
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 2.43,
|
1716 |
+
"learning_rate": 0.00012378586214689284,
|
1717 |
+
"loss": 0.3403,
|
1718 |
+
"step": 142500
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 2.43,
|
1722 |
+
"learning_rate": 0.000123614068270492,
|
1723 |
+
"loss": 0.3402,
|
1724 |
+
"step": 143000
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 2.44,
|
1728 |
+
"learning_rate": 0.00012344184394084504,
|
1729 |
+
"loss": 0.3398,
|
1730 |
+
"step": 143500
|
1731 |
+
},
|
1732 |
+
{
|
1733 |
+
"epoch": 2.45,
|
1734 |
+
"learning_rate": 0.00012326919085773659,
|
1735 |
+
"loss": 0.34,
|
1736 |
+
"step": 144000
|
1737 |
+
},
|
1738 |
+
{
|
1739 |
+
"epoch": 2.46,
|
1740 |
+
"learning_rate": 0.00012309611072518285,
|
1741 |
+
"loss": 0.3397,
|
1742 |
+
"step": 144500
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 2.47,
|
1746 |
+
"learning_rate": 0.00012292260525141485,
|
1747 |
+
"loss": 0.34,
|
1748 |
+
"step": 145000
|
1749 |
}
|
1750 |
],
|
1751 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:655b828bf25e09d93b3a829341a96b780ef65754b049aae3719f02e2c2832c66
|
3 |
size 201355195
|