Training in progress, step 50000
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 402587859
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:585dc16d735672778f127a50a104f1dd435dd6961982b55a3048c7509e1a0606
|
3 |
size 402587859
|
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:a3b7ae155a06728642638731f6de2c2f5afc3e981ea2fdb85c38fb6a64b25b0c
|
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:c214fb929216c2b57a561db0a033cee82210e2640667cbc8b9831673fb9add6b
|
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 sha256:44ecb07ac2162f527064f2737413d021caa039db7ccee830bdf0538ff05d4093
|
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 sha256:7a5ac6e08b327e2d192624409abaa145fec824a1b1c826ed5c288c5e1790e3b9
|
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 sha256:50af050c43186589343af9bb992fc787c0a783d8c2b49498b7c1931805c39e02
|
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 sha256:7e2dbdff4ea032b46d21433a227047ff3118604187bcfab711dfc4fa85bb0b8c
|
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 sha256:9b02d21f408cca9174ccc2664126f6b167a3474ba9d60c95500be18ad93c90a5
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -546,6 +546,66 @@
|
|
546 |
"learning_rate": 0.00014722227563107712,
|
547 |
"loss": 0.3661,
|
548 |
"step": 45000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
549 |
}
|
550 |
],
|
551 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.851063829787234,
|
5 |
+
"global_step": 50000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
546 |
"learning_rate": 0.00014722227563107712,
|
547 |
"loss": 0.3661,
|
548 |
"step": 45000
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.77,
|
552 |
+
"learning_rate": 0.00014716060923153354,
|
553 |
+
"loss": 0.3656,
|
554 |
+
"step": 45500
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.78,
|
558 |
+
"learning_rate": 0.00014709840530350058,
|
559 |
+
"loss": 0.3656,
|
560 |
+
"step": 46000
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.79,
|
564 |
+
"learning_rate": 0.00014703541514677053,
|
565 |
+
"loss": 0.3652,
|
566 |
+
"step": 46500
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.8,
|
570 |
+
"learning_rate": 0.00014697176337755626,
|
571 |
+
"loss": 0.365,
|
572 |
+
"step": 47000
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.81,
|
576 |
+
"learning_rate": 0.0001469074506240751,
|
577 |
+
"loss": 0.365,
|
578 |
+
"step": 47500
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.82,
|
582 |
+
"learning_rate": 0.00014684260812587756,
|
583 |
+
"loss": 0.3645,
|
584 |
+
"step": 48000
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.83,
|
588 |
+
"learning_rate": 0.00014677710855432052,
|
589 |
+
"loss": 0.3647,
|
590 |
+
"step": 48500
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.83,
|
594 |
+
"learning_rate": 0.00014671081931749022,
|
595 |
+
"loss": 0.3645,
|
596 |
+
"step": 49000
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.84,
|
600 |
+
"learning_rate": 0.00014664387167180547,
|
601 |
+
"loss": 0.3638,
|
602 |
+
"step": 49500
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.85,
|
606 |
+
"learning_rate": 0.00014657626627801257,
|
607 |
+
"loss": 0.3638,
|
608 |
+
"step": 50000
|
609 |
}
|
610 |
],
|
611 |
"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:a3b7ae155a06728642638731f6de2c2f5afc3e981ea2fdb85c38fb6a64b25b0c
|
3 |
size 201355195
|