Training in progress, step 150000
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 sha256:00644d818ff497bb1ee5035ac9bd29773dc09e3c847d082ac89b8b660a93f283
|
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:fc73d937b13e43d07dbd84b605991d31cbd5d8d105f10d736bdbd49ff9359e2d
|
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 sha256:29cd6bff983422dc3fa401599990cb1ce2b90385e3e6b747946b3071d36173b8
|
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:d1a2aceb01417e513c0402d0d17e59f29156da08bdf6aaacb43cfcfb0f89ff4a
|
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:ce27f23459e69adbbc6e341cbf9d0313f0e42965a648e33742059ad101c809a6
|
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:ebb9ab29108fa9d623bd7d45a3f814c6a94891c38f7f8756e419093f81e4e750
|
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 sha256:1581f9b4c29a0528724a9edeb9d1f7269085b00ba45b0b7758df752247cead11
|
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 sha256:3c2a622a59a99625cf86c0d431005ad8a5f3dc2878b6160d374c0b02a1aa886f
|
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,
|
@@ -1746,6 +1746,66 @@
|
|
1746 |
"learning_rate": 0.00012292260525141485,
|
1747 |
"loss": 0.34,
|
1748 |
"step": 145000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1749 |
}
|
1750 |
],
|
1751 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.5531914893617023,
|
5 |
+
"global_step": 150000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1746 |
"learning_rate": 0.00012292260525141485,
|
1747 |
"loss": 0.34,
|
1748 |
"step": 145000
|
1749 |
+
},
|
1750 |
+
{
|
1751 |
+
"epoch": 2.48,
|
1752 |
+
"learning_rate": 0.00012274867614886156,
|
1753 |
+
"loss": 0.3397,
|
1754 |
+
"step": 145500
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 2.49,
|
1758 |
+
"learning_rate": 0.00012257432513413305,
|
1759 |
+
"loss": 0.3396,
|
1760 |
+
"step": 146000
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 2.49,
|
1764 |
+
"learning_rate": 0.0001223995539280034,
|
1765 |
+
"loss": 0.3392,
|
1766 |
+
"step": 146500
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 2.5,
|
1770 |
+
"learning_rate": 0.00012222471505122007,
|
1771 |
+
"loss": 0.3394,
|
1772 |
+
"step": 147000
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 2.51,
|
1776 |
+
"learning_rate": 0.00012204910947292852,
|
1777 |
+
"loss": 0.3396,
|
1778 |
+
"step": 147500
|
1779 |
+
},
|
1780 |
+
{
|
1781 |
+
"epoch": 2.52,
|
1782 |
+
"learning_rate": 0.0001218730888869024,
|
1783 |
+
"loss": 0.3394,
|
1784 |
+
"step": 148000
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 2.53,
|
1788 |
+
"learning_rate": 0.00012169700830939406,
|
1789 |
+
"loss": 0.3393,
|
1790 |
+
"step": 148500
|
1791 |
+
},
|
1792 |
+
{
|
1793 |
+
"epoch": 2.54,
|
1794 |
+
"learning_rate": 0.00012152016374505169,
|
1795 |
+
"loss": 0.3392,
|
1796 |
+
"step": 149000
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 2.54,
|
1800 |
+
"learning_rate": 0.00012134290939345552,
|
1801 |
+
"loss": 0.3396,
|
1802 |
+
"step": 149500
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 2.55,
|
1806 |
+
"learning_rate": 0.00012116524700403446,
|
1807 |
+
"loss": 0.3391,
|
1808 |
+
"step": 150000
|
1809 |
}
|
1810 |
],
|
1811 |
"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:fc73d937b13e43d07dbd84b605991d31cbd5d8d105f10d736bdbd49ff9359e2d
|
3 |
size 201355195
|