Training in progress, step 230000
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 sha256:019e0083e8c1cc7f00db376e397126b778e47e394963b93169d92a9188260199
|
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 sha256:32c85a7c2ce765db029c997d5acec10ec3d16f04689e08bcae2741931de5cc62
|
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 sha256:63d37194e9033b501e8f714c2c2d449de4d7dcfa22a431d7094f9bb81dfbada2
|
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 sha256:81e4cd91d923d83a12babaebe9aaac215dfc6b91fff4e277c8bdade82db5af54
|
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 sha256:6aa4b475e3aa2c69ece7cc1641cb9e314fc1dd4d05ee3cae8f033a2b4a7b88f7
|
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 sha256:36d410b7e24b5411b3d8b00a302d4e848a61f62fb8c2d287ab92142456dce677
|
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 sha256:2caaf840c159502ffa904ced006676eb15f32de2833627cbff4bd2cc520ff341
|
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:a33eaf3253a2dd450ccafac4f612d27d8b5b8314e0fa42f84a7ff80939d599df
|
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": 3.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2706,6 +2706,66 @@
|
|
2706 |
"learning_rate": 9.098777004213002e-05,
|
2707 |
"loss": 0.3316,
|
2708 |
"step": 225000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2709 |
}
|
2710 |
],
|
2711 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.9148936170212765,
|
5 |
+
"global_step": 230000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2706 |
"learning_rate": 9.098777004213002e-05,
|
2707 |
"loss": 0.3316,
|
2708 |
"step": 225000
|
2709 |
+
},
|
2710 |
+
{
|
2711 |
+
"epoch": 3.84,
|
2712 |
+
"learning_rate": 9.077053078734103e-05,
|
2713 |
+
"loss": 0.3314,
|
2714 |
+
"step": 225500
|
2715 |
+
},
|
2716 |
+
{
|
2717 |
+
"epoch": 3.85,
|
2718 |
+
"learning_rate": 9.055318523176143e-05,
|
2719 |
+
"loss": 0.331,
|
2720 |
+
"step": 226000
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 3.86,
|
2724 |
+
"learning_rate": 9.033573552050405e-05,
|
2725 |
+
"loss": 0.3311,
|
2726 |
+
"step": 226500
|
2727 |
+
},
|
2728 |
+
{
|
2729 |
+
"epoch": 3.86,
|
2730 |
+
"learning_rate": 9.011818379970982e-05,
|
2731 |
+
"loss": 0.331,
|
2732 |
+
"step": 227000
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 3.87,
|
2736 |
+
"learning_rate": 8.990053221652635e-05,
|
2737 |
+
"loss": 0.3311,
|
2738 |
+
"step": 227500
|
2739 |
+
},
|
2740 |
+
{
|
2741 |
+
"epoch": 3.88,
|
2742 |
+
"learning_rate": 8.968321851377233e-05,
|
2743 |
+
"loss": 0.3311,
|
2744 |
+
"step": 228000
|
2745 |
+
},
|
2746 |
+
{
|
2747 |
+
"epoch": 3.89,
|
2748 |
+
"learning_rate": 8.946537384015948e-05,
|
2749 |
+
"loss": 0.3309,
|
2750 |
+
"step": 228500
|
2751 |
+
},
|
2752 |
+
{
|
2753 |
+
"epoch": 3.9,
|
2754 |
+
"learning_rate": 8.924787171511725e-05,
|
2755 |
+
"loss": 0.3307,
|
2756 |
+
"step": 229000
|
2757 |
+
},
|
2758 |
+
{
|
2759 |
+
"epoch": 3.91,
|
2760 |
+
"learning_rate": 8.902984253401809e-05,
|
2761 |
+
"loss": 0.3307,
|
2762 |
+
"step": 229500
|
2763 |
+
},
|
2764 |
+
{
|
2765 |
+
"epoch": 3.91,
|
2766 |
+
"learning_rate": 8.88117242320186e-05,
|
2767 |
+
"loss": 0.3307,
|
2768 |
+
"step": 230000
|
2769 |
}
|
2770 |
],
|
2771 |
"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 sha256:32c85a7c2ce765db029c997d5acec10ec3d16f04689e08bcae2741931de5cc62
|
3 |
size 201355195
|