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 sha256:41f31ed99ac50d8a42aa6b413e7478ffbd7d1dfbc772ab8511d3b3b75fd1899c
|
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 sha256:4fb4d935d11ba6033587680595edc43fd64fd737c3be5158fbcdf9371f04ac78
|
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:f1c28906920029ac9ce9c615fd5b981da6cee6ee307da93316552699c06dd0d8
|
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 sha256:1db71468cc35abbe3233665444fcdeb1b603788cc33799c069c2330157b18b25
|
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 sha256:02b1024dd114b6aa2efdc0fa8bb7079fe2acdd150a795d28ca88d4d8399c30f1
|
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 sha256:45a4cd7801d5de30bd7931cd21d1aabbdc1c2f3d8bd7445d825b0f32527254ed
|
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 sha256:21471e253207884541d85024a35c3a29deaeacd24d8008e7113140c70a286357
|
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 sha256:3112556147fa4a1d4a95dbfe65421b0df3a84502bf12cca7ab12f007ec4d80ba
|
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": 9.099037625899677e-05,
|
2707 |
"loss": 0.3333,
|
2708 |
"step": 225000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2709 |
}
|
2710 |
],
|
2711 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.9148858307588874,
|
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": 9.099037625899677e-05,
|
2707 |
"loss": 0.3333,
|
2708 |
"step": 225000
|
2709 |
+
},
|
2710 |
+
{
|
2711 |
+
"epoch": 3.84,
|
2712 |
+
"learning_rate": 9.077313829283815e-05,
|
2713 |
+
"loss": 0.3331,
|
2714 |
+
"step": 225500
|
2715 |
+
},
|
2716 |
+
{
|
2717 |
+
"epoch": 3.85,
|
2718 |
+
"learning_rate": 9.055579400015386e-05,
|
2719 |
+
"loss": 0.3331,
|
2720 |
+
"step": 226000
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 3.86,
|
2724 |
+
"learning_rate": 9.033834552604434e-05,
|
2725 |
+
"loss": 0.3331,
|
2726 |
+
"step": 226500
|
2727 |
+
},
|
2728 |
+
{
|
2729 |
+
"epoch": 3.86,
|
2730 |
+
"learning_rate": 9.012079501663827e-05,
|
2731 |
+
"loss": 0.3329,
|
2732 |
+
"step": 227000
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 3.87,
|
2736 |
+
"learning_rate": 8.990314461907129e-05,
|
2737 |
+
"loss": 0.3329,
|
2738 |
+
"step": 227500
|
2739 |
+
},
|
2740 |
+
{
|
2741 |
+
"epoch": 3.88,
|
2742 |
+
"learning_rate": 8.968583207385645e-05,
|
2743 |
+
"loss": 0.3324,
|
2744 |
+
"step": 228000
|
2745 |
+
},
|
2746 |
+
{
|
2747 |
+
"epoch": 3.89,
|
2748 |
+
"learning_rate": 8.946798853433352e-05,
|
2749 |
+
"loss": 0.3328,
|
2750 |
+
"step": 228500
|
2751 |
+
},
|
2752 |
+
{
|
2753 |
+
"epoch": 3.9,
|
2754 |
+
"learning_rate": 8.925005154958616e-05,
|
2755 |
+
"loss": 0.3326,
|
2756 |
+
"step": 229000
|
2757 |
+
},
|
2758 |
+
{
|
2759 |
+
"epoch": 3.91,
|
2760 |
+
"learning_rate": 8.903202327056435e-05,
|
2761 |
+
"loss": 0.3324,
|
2762 |
+
"step": 229500
|
2763 |
+
},
|
2764 |
+
{
|
2765 |
+
"epoch": 3.91,
|
2766 |
+
"learning_rate": 8.881390584911924e-05,
|
2767 |
+
"loss": 0.3322,
|
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 sha256:4fb4d935d11ba6033587680595edc43fd64fd737c3be5158fbcdf9371f04ac78
|
3 |
size 201355195
|