Training in progress, step 455000
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:a9e77557bb66ce4270711a710d0d175d7e43e66f9e38b4e5ee5bb7d0ee834456
|
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:c9e643b1be746d1d219ae789272c70c12926b3a1bc054821da29526428c714cf
|
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:a242571589433bf07b6289fd4aa672d49fbab8c09f5d93a973062fef732a2be7
|
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 sha256:29f8bdb19d14fb6a62a5a5137ee6a671443146772658badbac02da89f5c71b9d
|
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 sha256:7f7dd0c48542a895bfb7f457346b49fd044eeb564ba3cf819ce08a34e796ff9f
|
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 sha256:1705970879b713a03d8b8a88095b340777c9f8f6cb545000cb0ba1b4d9c3329d
|
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:fd14307bc142481802417c9963d82ec3114f2f67244998c8001a545c3ddecdbc
|
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 sha256:41a328ec8e0315b290b80c0a4b6167380929f170c27662cbb0dcd078967a9097
|
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,
|
@@ -5406,6 +5406,66 @@
|
|
5406 |
"learning_rate": 1.3449732463288913e-05,
|
5407 |
"loss": 0.3191,
|
5408 |
"step": 450000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5409 |
}
|
5410 |
],
|
5411 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.7446745134083965,
|
5 |
+
"global_step": 455000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
5406 |
"learning_rate": 1.3449732463288913e-05,
|
5407 |
"loss": 0.3191,
|
5408 |
"step": 450000
|
5409 |
+
},
|
5410 |
+
{
|
5411 |
+
"epoch": 7.67,
|
5412 |
+
"learning_rate": 1.3381875985491348e-05,
|
5413 |
+
"loss": 0.3188,
|
5414 |
+
"step": 450500
|
5415 |
+
},
|
5416 |
+
{
|
5417 |
+
"epoch": 7.68,
|
5418 |
+
"learning_rate": 1.3314677001682987e-05,
|
5419 |
+
"loss": 0.3186,
|
5420 |
+
"step": 451000
|
5421 |
+
},
|
5422 |
+
{
|
5423 |
+
"epoch": 7.69,
|
5424 |
+
"learning_rate": 1.324813617509066e-05,
|
5425 |
+
"loss": 0.3191,
|
5426 |
+
"step": 451500
|
5427 |
+
},
|
5428 |
+
{
|
5429 |
+
"epoch": 7.69,
|
5430 |
+
"learning_rate": 1.3182254162445461e-05,
|
5431 |
+
"loss": 0.3189,
|
5432 |
+
"step": 452000
|
5433 |
+
},
|
5434 |
+
{
|
5435 |
+
"epoch": 7.7,
|
5436 |
+
"learning_rate": 1.3117031613976277e-05,
|
5437 |
+
"loss": 0.3188,
|
5438 |
+
"step": 452500
|
5439 |
+
},
|
5440 |
+
{
|
5441 |
+
"epoch": 7.71,
|
5442 |
+
"learning_rate": 1.30524691734033e-05,
|
5443 |
+
"loss": 0.3189,
|
5444 |
+
"step": 453000
|
5445 |
+
},
|
5446 |
+
{
|
5447 |
+
"epoch": 7.72,
|
5448 |
+
"learning_rate": 1.2988567477931785e-05,
|
5449 |
+
"loss": 0.3188,
|
5450 |
+
"step": 453500
|
5451 |
+
},
|
5452 |
+
{
|
5453 |
+
"epoch": 7.73,
|
5454 |
+
"learning_rate": 1.2925327158245641e-05,
|
5455 |
+
"loss": 0.319,
|
5456 |
+
"step": 454000
|
5457 |
+
},
|
5458 |
+
{
|
5459 |
+
"epoch": 7.74,
|
5460 |
+
"learning_rate": 1.286274883850132e-05,
|
5461 |
+
"loss": 0.3187,
|
5462 |
+
"step": 454500
|
5463 |
+
},
|
5464 |
+
{
|
5465 |
+
"epoch": 7.74,
|
5466 |
+
"learning_rate": 1.2800833136321545e-05,
|
5467 |
+
"loss": 0.3189,
|
5468 |
+
"step": 455000
|
5469 |
}
|
5470 |
],
|
5471 |
"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:c9e643b1be746d1d219ae789272c70c12926b3a1bc054821da29526428c714cf
|
3 |
size 201355195
|