Training in progress, step 470000
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:ca77a5dbd8026f76af848254207870eb2ccd175c0dee4a8c0fee44891a87588e
|
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:d23760072e5a7125a31204d73f6355de96639a56aca3dd44d457dd0c4eb6f41e
|
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 sha256:21c75708378bb3a4f0d72676110aa9ff474cd2117cc84f11d618f13edbd722d3
|
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:aba69dd8ff4d24bad26948637df922ba7515fea7cf8eb37732b35bd310c4bd05
|
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 sha256:700ce99772259361623e1887fedad42faf671219e9892827c68ca1bdd62d6c20
|
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 sha256:364d3ce7d0b7d1d3913115fb3dbb4222a2d7297db87154518774c80eff073be5
|
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 sha256:0731dd739865cc8a6e81a2a5c07511dd29f52f75cc4568cab5c57bfbd230f902
|
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 sha256:229f76646f963bb7bb363aeab52140886626dd987202d9c29e3f40f18b9b0846
|
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": 7.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -5586,6 +5586,66 @@
|
|
5586 |
"learning_rate": 1.1703043916064376e-05,
|
5587 |
"loss": 0.3188,
|
5588 |
"step": 465000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5589 |
}
|
5590 |
],
|
5591 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.999991489434133,
|
5 |
+
"global_step": 470000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
5586 |
"learning_rate": 1.1703043916064376e-05,
|
5587 |
"loss": 0.3188,
|
5588 |
"step": 465000
|
5589 |
+
},
|
5590 |
+
{
|
5591 |
+
"epoch": 7.92,
|
5592 |
+
"learning_rate": 1.1655167477409934e-05,
|
5593 |
+
"loss": 0.3187,
|
5594 |
+
"step": 465500
|
5595 |
+
},
|
5596 |
+
{
|
5597 |
+
"epoch": 7.93,
|
5598 |
+
"learning_rate": 1.1607965574660545e-05,
|
5599 |
+
"loss": 0.3186,
|
5600 |
+
"step": 466000
|
5601 |
+
},
|
5602 |
+
{
|
5603 |
+
"epoch": 7.94,
|
5604 |
+
"learning_rate": 1.1561438673679967e-05,
|
5605 |
+
"loss": 0.3187,
|
5606 |
+
"step": 466500
|
5607 |
+
},
|
5608 |
+
{
|
5609 |
+
"epoch": 7.95,
|
5610 |
+
"learning_rate": 1.1515587233669903e-05,
|
5611 |
+
"loss": 0.3187,
|
5612 |
+
"step": 467000
|
5613 |
+
},
|
5614 |
+
{
|
5615 |
+
"epoch": 7.96,
|
5616 |
+
"learning_rate": 1.1470411707165581e-05,
|
5617 |
+
"loss": 0.3188,
|
5618 |
+
"step": 467500
|
5619 |
+
},
|
5620 |
+
{
|
5621 |
+
"epoch": 7.97,
|
5622 |
+
"learning_rate": 1.142600086306578e-05,
|
5623 |
+
"loss": 0.3186,
|
5624 |
+
"step": 468000
|
5625 |
+
},
|
5626 |
+
{
|
5627 |
+
"epoch": 7.97,
|
5628 |
+
"learning_rate": 1.1382177140459145e-05,
|
5629 |
+
"loss": 0.3187,
|
5630 |
+
"step": 468500
|
5631 |
+
},
|
5632 |
+
{
|
5633 |
+
"epoch": 7.98,
|
5634 |
+
"learning_rate": 1.1339030648061997e-05,
|
5635 |
+
"loss": 0.3186,
|
5636 |
+
"step": 469000
|
5637 |
+
},
|
5638 |
+
{
|
5639 |
+
"epoch": 7.99,
|
5640 |
+
"learning_rate": 1.1296561811712808e-05,
|
5641 |
+
"loss": 0.3188,
|
5642 |
+
"step": 469500
|
5643 |
+
},
|
5644 |
+
{
|
5645 |
+
"epoch": 8.0,
|
5646 |
+
"learning_rate": 1.1254771050561826e-05,
|
5647 |
+
"loss": 0.3186,
|
5648 |
+
"step": 470000
|
5649 |
}
|
5650 |
],
|
5651 |
"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:d23760072e5a7125a31204d73f6355de96639a56aca3dd44d457dd0c4eb6f41e
|
3 |
size 201355195
|