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 sha256:340c057c14851ae833de3cc710450e92f28b73faba3e6e2b797775c590c9112f
|
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:ed3477a9cbd8106a26fce5dc6885670b82a628ff97f5f44a25b28c6803baa0b7
|
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 sha256:78bfcdc5f8d31603c243202ea2e17ab1950c927dc5c5016fae62b983ebe9e1e1
|
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:ddbbbcc0085c3c3412d4ad08f1489a0e2b5ac8e2c094ba1211fb11dee05d5e38
|
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:c129f476dc2862f36a419e15a11aed6247ca6f392bcfb1f0e011d6fd682b02d0
|
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:eff4296aefa46c24bf3575f40d88d08cfe8b434da2fa9f20d5131da4319a6071
|
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 sha256:602374283a35c3573b57bcdea4b872e46b2c01ee008a17814427fffa842d87fa
|
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 sha256:7e39b8e2ce44c4392d7d60aaf96fb597369284a27e068da332c89dde5d5e7950
|
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": 0.00012292364754923295,
|
1747 |
"loss": 0.3444,
|
1748 |
"step": 145000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1749 |
}
|
1750 |
],
|
1751 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.5531867813890945,
|
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": 0.00012292364754923295,
|
1747 |
"loss": 0.3444,
|
1748 |
"step": 145000
|
1749 |
+
},
|
1750 |
+
{
|
1751 |
+
"epoch": 2.48,
|
1752 |
+
"learning_rate": 0.0001227497209833376,
|
1753 |
+
"loss": 0.3441,
|
1754 |
+
"step": 145500
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 2.49,
|
1758 |
+
"learning_rate": 0.00012257572161186733,
|
1759 |
+
"loss": 0.3439,
|
1760 |
+
"step": 146000
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 2.49,
|
1764 |
+
"learning_rate": 0.00012240095376042992,
|
1765 |
+
"loss": 0.3436,
|
1766 |
+
"step": 146500
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 2.5,
|
1770 |
+
"learning_rate": 0.00012222576742869685,
|
1771 |
+
"loss": 0.3434,
|
1772 |
+
"step": 147000
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 2.51,
|
1776 |
+
"learning_rate": 0.00012205016434568649,
|
1777 |
+
"loss": 0.3434,
|
1778 |
+
"step": 147500
|
1779 |
+
},
|
1780 |
+
{
|
1781 |
+
"epoch": 2.52,
|
1782 |
+
"learning_rate": 0.00012187414624453037,
|
1783 |
+
"loss": 0.3433,
|
1784 |
+
"step": 148000
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 2.53,
|
1788 |
+
"learning_rate": 0.00012169771486245609,
|
1789 |
+
"loss": 0.3429,
|
1790 |
+
"step": 148500
|
1791 |
+
},
|
1792 |
+
{
|
1793 |
+
"epoch": 2.54,
|
1794 |
+
"learning_rate": 0.00012152087194077019,
|
1795 |
+
"loss": 0.3429,
|
1796 |
+
"step": 149000
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 2.54,
|
1800 |
+
"learning_rate": 0.00012134361922484087,
|
1801 |
+
"loss": 0.3435,
|
1802 |
+
"step": 149500
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 2.55,
|
1806 |
+
"learning_rate": 0.0001211659584640809,
|
1807 |
+
"loss": 0.3427,
|
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:ed3477a9cbd8106a26fce5dc6885670b82a628ff97f5f44a25b28c6803baa0b7
|
3 |
size 201355195
|