Training in progress, step 225000
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 sha256:50fc4f5007998f9e0c8b05a6d7aa10fc7aa8e9c0c498ef55ff813ecf68239041
|
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 sha256:12e9e80ef103fec8dfd14f34cf7a92efa9b5125caadc4f0111694b90aea51176
|
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 sha256:4c730062ab687df991abf790ecffee896c6da67634c371edbf38c21e8ed6dc25
|
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:f23ca214c27fef7c044e6f4ea07e9b7ac6dda71a37c5aa88841bf1377a012b0b
|
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 sha256:453e8605c31050b20c9e793d787062c0641dc017cdc04c8540ccc02399bafef5
|
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 sha256:341983a1f04af7aeff145fe231e24c857cb129e35aa06a4b171c14d677164c26
|
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 sha256:8806be31aecf1262340090ea766f7f1c372c650aa78674d3ce72b7d8bba4cced
|
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 sha256:9cc25b635b70457687f7497bdda44fec5fb0f3608664a7ea6c364ccea2c146b2
|
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,
|
@@ -2646,6 +2646,66 @@
|
|
2646 |
"learning_rate": 9.31529809222136e-05,
|
2647 |
"loss": 0.3317,
|
2648 |
"step": 220000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2649 |
}
|
2650 |
],
|
2651 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.829787234042553,
|
5 |
+
"global_step": 225000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2646 |
"learning_rate": 9.31529809222136e-05,
|
2647 |
"loss": 0.3317,
|
2648 |
"step": 220000
|
2649 |
+
},
|
2650 |
+
{
|
2651 |
+
"epoch": 3.75,
|
2652 |
+
"learning_rate": 9.293692190024998e-05,
|
2653 |
+
"loss": 0.3321,
|
2654 |
+
"step": 220500
|
2655 |
+
},
|
2656 |
+
{
|
2657 |
+
"epoch": 3.76,
|
2658 |
+
"learning_rate": 9.272073519609008e-05,
|
2659 |
+
"loss": 0.3322,
|
2660 |
+
"step": 221000
|
2661 |
+
},
|
2662 |
+
{
|
2663 |
+
"epoch": 3.77,
|
2664 |
+
"learning_rate": 9.250485569179332e-05,
|
2665 |
+
"loss": 0.3319,
|
2666 |
+
"step": 221500
|
2667 |
+
},
|
2668 |
+
{
|
2669 |
+
"epoch": 3.78,
|
2670 |
+
"learning_rate": 9.22884202702021e-05,
|
2671 |
+
"loss": 0.332,
|
2672 |
+
"step": 222000
|
2673 |
+
},
|
2674 |
+
{
|
2675 |
+
"epoch": 3.79,
|
2676 |
+
"learning_rate": 9.207186356686387e-05,
|
2677 |
+
"loss": 0.3318,
|
2678 |
+
"step": 222500
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 3.8,
|
2682 |
+
"learning_rate": 9.185518771910584e-05,
|
2683 |
+
"loss": 0.3316,
|
2684 |
+
"step": 223000
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 3.8,
|
2688 |
+
"learning_rate": 9.163839486543117e-05,
|
2689 |
+
"loss": 0.3317,
|
2690 |
+
"step": 223500
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 3.81,
|
2694 |
+
"learning_rate": 9.142192107415142e-05,
|
2695 |
+
"loss": 0.3317,
|
2696 |
+
"step": 224000
|
2697 |
+
},
|
2698 |
+
{
|
2699 |
+
"epoch": 3.82,
|
2700 |
+
"learning_rate": 9.120490085206463e-05,
|
2701 |
+
"loss": 0.3318,
|
2702 |
+
"step": 224500
|
2703 |
+
},
|
2704 |
+
{
|
2705 |
+
"epoch": 3.83,
|
2706 |
+
"learning_rate": 9.098777004213002e-05,
|
2707 |
+
"loss": 0.3316,
|
2708 |
+
"step": 225000
|
2709 |
}
|
2710 |
],
|
2711 |
"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 sha256:12e9e80ef103fec8dfd14f34cf7a92efa9b5125caadc4f0111694b90aea51176
|
3 |
size 201355195
|