Training in progress, step 395000
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 sha256:8badaf858040e9a408943a6e9fbd7b673381f667c74f44da38b93b7faa806cd6
|
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:a7e0679255ea6b36201b0d808a362cef9e0cc4250bf2a27a7d227fb77c38b5a3
|
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 sha256:321f848c05abd7bede59850502e9582f8a2efa51300e70f7c4e42416383b1f9d
|
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 sha256:7173cab8fec53de370fc776b8ec60abd28823c70815e5aae8f471b1d4cd8593a
|
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 sha256:9bbf3b61889bf57772bca69e3fa2b3a58e51beabaa460befd9b8ff1bc01f45da
|
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 sha256:053726ed745fa923b4c9b6b87c5501b19122cc00993e8b017178f10a7f218f5b
|
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 sha256:062ee8ab98f80273aee87dab235a0bc7258dc420c22cabc1af7c5b580c42129d
|
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 sha256:09de475ccd38f92b9bb28c41a7de8a4a2d4763ec7818473a0c7e4d4586d6efeb
|
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": 6.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -4686,6 +4686,66 @@
|
|
4686 |
"learning_rate": 2.6106711361365064e-05,
|
4687 |
"loss": 0.3206,
|
4688 |
"step": 390000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4689 |
}
|
4690 |
],
|
4691 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.723398098739585,
|
5 |
+
"global_step": 395000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
4686 |
"learning_rate": 2.6106711361365064e-05,
|
4687 |
"loss": 0.3206,
|
4688 |
"step": 390000
|
4689 |
+
},
|
4690 |
+
{
|
4691 |
+
"epoch": 6.65,
|
4692 |
+
"learning_rate": 2.5966638924843332e-05,
|
4693 |
+
"loss": 0.3204,
|
4694 |
+
"step": 390500
|
4695 |
+
},
|
4696 |
+
{
|
4697 |
+
"epoch": 6.66,
|
4698 |
+
"learning_rate": 2.5827099775781274e-05,
|
4699 |
+
"loss": 0.3204,
|
4700 |
+
"step": 391000
|
4701 |
+
},
|
4702 |
+
{
|
4703 |
+
"epoch": 6.66,
|
4704 |
+
"learning_rate": 2.5688095291373918e-05,
|
4705 |
+
"loss": 0.3203,
|
4706 |
+
"step": 391500
|
4707 |
+
},
|
4708 |
+
{
|
4709 |
+
"epoch": 6.67,
|
4710 |
+
"learning_rate": 2.554962684353946e-05,
|
4711 |
+
"loss": 0.3203,
|
4712 |
+
"step": 392000
|
4713 |
+
},
|
4714 |
+
{
|
4715 |
+
"epoch": 6.68,
|
4716 |
+
"learning_rate": 2.5411695798905557e-05,
|
4717 |
+
"loss": 0.3205,
|
4718 |
+
"step": 392500
|
4719 |
+
},
|
4720 |
+
{
|
4721 |
+
"epoch": 6.69,
|
4722 |
+
"learning_rate": 2.5274303518795908e-05,
|
4723 |
+
"loss": 0.3206,
|
4724 |
+
"step": 393000
|
4725 |
+
},
|
4726 |
+
{
|
4727 |
+
"epoch": 6.7,
|
4728 |
+
"learning_rate": 2.513745135921688e-05,
|
4729 |
+
"loss": 0.3203,
|
4730 |
+
"step": 393500
|
4731 |
+
},
|
4732 |
+
{
|
4733 |
+
"epoch": 6.71,
|
4734 |
+
"learning_rate": 2.5001412750937412e-05,
|
4735 |
+
"loss": 0.3205,
|
4736 |
+
"step": 394000
|
4737 |
+
},
|
4738 |
+
{
|
4739 |
+
"epoch": 6.71,
|
4740 |
+
"learning_rate": 2.4865643792130036e-05,
|
4741 |
+
"loss": 0.3204,
|
4742 |
+
"step": 394500
|
4743 |
+
},
|
4744 |
+
{
|
4745 |
+
"epoch": 6.72,
|
4746 |
+
"learning_rate": 2.473041898715981e-05,
|
4747 |
+
"loss": 0.3201,
|
4748 |
+
"step": 395000
|
4749 |
}
|
4750 |
],
|
4751 |
"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:a7e0679255ea6b36201b0d808a362cef9e0cc4250bf2a27a7d227fb77c38b5a3
|
3 |
size 201355195
|