Training in progress, step 45000
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:f7d06d0eceb624a93f15c1ff7d5200ba9ef94286529cf32d4edad055ad078ea0
|
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 sha256:03baa03a47a5c1f3c54451145a1853ad32051aa5484ab5c4947f83b3fe9e5f85
|
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 sha256:35ea75c60f66228862cd92e9088324385ce9aed769205f3b1551a63c6fe60f8a
|
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:bdf8835b2df6fbbc9c3403b592687a613dd65cafea09e7ef351835386dae4b27
|
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 sha256:474818e6d0125304282978c1c8542265c44eb5493d61b3978a6c3f69535ce59f
|
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 sha256:01b5c2f5adb77a01453d635e6c166adf9b4123b6d5fa75b83d11790aeec5a33c
|
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:bec99c9bd76f872a36dc1adeac79fca3a56a878cf6a77beb9bd3ef47bd234f37
|
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:b09f8c1cd14309b3eed15dc1e7f72362ffe87586c0b4ccac82d9ab818c4a6f3f
|
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,
|
@@ -486,6 +486,66 @@
|
|
486 |
"learning_rate": 0.00014780224298665108,
|
487 |
"loss": 0.3684,
|
488 |
"step": 40000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
489 |
}
|
490 |
],
|
491 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7659574468085106,
|
5 |
+
"global_step": 45000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
486 |
"learning_rate": 0.00014780224298665108,
|
487 |
"loss": 0.3684,
|
488 |
"step": 40000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.69,
|
492 |
+
"learning_rate": 0.0001477472361221548,
|
493 |
+
"loss": 0.3681,
|
494 |
+
"step": 40500
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.7,
|
498 |
+
"learning_rate": 0.0001476915606197887,
|
499 |
+
"loss": 0.3677,
|
500 |
+
"step": 41000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.71,
|
504 |
+
"learning_rate": 0.00014763521702904748,
|
505 |
+
"loss": 0.3677,
|
506 |
+
"step": 41500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.71,
|
510 |
+
"learning_rate": 0.0001475782059060196,
|
511 |
+
"loss": 0.3672,
|
512 |
+
"step": 42000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.72,
|
516 |
+
"learning_rate": 0.00014752052781338187,
|
517 |
+
"loss": 0.3673,
|
518 |
+
"step": 42500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.73,
|
522 |
+
"learning_rate": 0.00014746218332039373,
|
523 |
+
"loss": 0.3669,
|
524 |
+
"step": 43000
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.74,
|
528 |
+
"learning_rate": 0.00014740317300289185,
|
529 |
+
"loss": 0.3669,
|
530 |
+
"step": 43500
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.75,
|
534 |
+
"learning_rate": 0.0001473436174579246,
|
535 |
+
"loss": 0.3666,
|
536 |
+
"step": 44000
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.76,
|
540 |
+
"learning_rate": 0.00014728327857389895,
|
541 |
+
"loss": 0.3659,
|
542 |
+
"step": 44500
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.77,
|
546 |
+
"learning_rate": 0.00014722227563107712,
|
547 |
+
"loss": 0.3661,
|
548 |
+
"step": 45000
|
549 |
}
|
550 |
],
|
551 |
"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 sha256:03baa03a47a5c1f3c54451145a1853ad32051aa5484ab5c4947f83b3fe9e5f85
|
3 |
size 201355195
|