Training in progress, step 560000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +303 -3
- 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 586828837
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:047de29e872fa886935b0856cae368679a5024ec78d3b02056971d0dafe03f46
|
| 3 |
size 586828837
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2db06e17c94930e25ba4fa153fb1d09bc548975dd61b046eadd4ef82210ad5b
|
| 3 |
size 146774203
|
last-checkpoint/rng_state.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 sha256:6925d15f0ca8b085673c2a9c495fa03dd265589a6d0e5da63276f20be7165697
|
| 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:b1866493c6437f9be9b061bda7fb54561f6f075e18eb8ff9def3d978f033c740
|
| 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 733555848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f637d7b8ff1440e6b42939ee3d5db1515f248a64a9ccc57bfd7e929c8ce06320
|
| 3 |
size 733555848
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -16506,11 +16506,311 @@
|
|
| 16506 |
"learning_rate": 0.007174402227596965,
|
| 16507 |
"loss": 8.0567,
|
| 16508 |
"step": 550000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16509 |
}
|
| 16510 |
],
|
| 16511 |
"max_steps": 1000000,
|
| 16512 |
"num_train_epochs": 5,
|
| 16513 |
-
"total_flos": 8.
|
| 16514 |
"trial_name": null,
|
| 16515 |
"trial_params": null
|
| 16516 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.4064596251939134,
|
| 5 |
+
"global_step": 560000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 16506 |
"learning_rate": 0.007174402227596965,
|
| 16507 |
"loss": 8.0567,
|
| 16508 |
"step": 550000
|
| 16509 |
+
},
|
| 16510 |
+
{
|
| 16511 |
+
"epoch": 2.36,
|
| 16512 |
+
"learning_rate": 0.007170359981885019,
|
| 16513 |
+
"loss": 8.0657,
|
| 16514 |
+
"step": 550200
|
| 16515 |
+
},
|
| 16516 |
+
{
|
| 16517 |
+
"epoch": 2.37,
|
| 16518 |
+
"learning_rate": 0.007166315987569351,
|
| 16519 |
+
"loss": 8.0443,
|
| 16520 |
+
"step": 550400
|
| 16521 |
+
},
|
| 16522 |
+
{
|
| 16523 |
+
"epoch": 2.37,
|
| 16524 |
+
"learning_rate": 0.007162270247908135,
|
| 16525 |
+
"loss": 8.0611,
|
| 16526 |
+
"step": 550600
|
| 16527 |
+
},
|
| 16528 |
+
{
|
| 16529 |
+
"epoch": 2.37,
|
| 16530 |
+
"learning_rate": 0.00715824300789773,
|
| 16531 |
+
"loss": 8.061,
|
| 16532 |
+
"step": 550800
|
| 16533 |
+
},
|
| 16534 |
+
{
|
| 16535 |
+
"epoch": 2.37,
|
| 16536 |
+
"learning_rate": 0.007154193796011567,
|
| 16537 |
+
"loss": 8.0521,
|
| 16538 |
+
"step": 551000
|
| 16539 |
+
},
|
| 16540 |
+
{
|
| 16541 |
+
"epoch": 2.37,
|
| 16542 |
+
"learning_rate": 0.007150142848546487,
|
| 16543 |
+
"loss": 8.057,
|
| 16544 |
+
"step": 551200
|
| 16545 |
+
},
|
| 16546 |
+
{
|
| 16547 |
+
"epoch": 2.37,
|
| 16548 |
+
"learning_rate": 0.007146090168766263,
|
| 16549 |
+
"loss": 8.0605,
|
| 16550 |
+
"step": 551400
|
| 16551 |
+
},
|
| 16552 |
+
{
|
| 16553 |
+
"epoch": 2.37,
|
| 16554 |
+
"learning_rate": 0.007142035759936066,
|
| 16555 |
+
"loss": 8.0472,
|
| 16556 |
+
"step": 551600
|
| 16557 |
+
},
|
| 16558 |
+
{
|
| 16559 |
+
"epoch": 2.37,
|
| 16560 |
+
"learning_rate": 0.007137979625322462,
|
| 16561 |
+
"loss": 8.0535,
|
| 16562 |
+
"step": 551800
|
| 16563 |
+
},
|
| 16564 |
+
{
|
| 16565 |
+
"epoch": 2.37,
|
| 16566 |
+
"learning_rate": 0.0071339217681934035,
|
| 16567 |
+
"loss": 8.0519,
|
| 16568 |
+
"step": 552000
|
| 16569 |
+
},
|
| 16570 |
+
{
|
| 16571 |
+
"epoch": 2.37,
|
| 16572 |
+
"learning_rate": 0.007129862191818233,
|
| 16573 |
+
"loss": 8.0626,
|
| 16574 |
+
"step": 552200
|
| 16575 |
+
},
|
| 16576 |
+
{
|
| 16577 |
+
"epoch": 2.37,
|
| 16578 |
+
"learning_rate": 0.007125800899467677,
|
| 16579 |
+
"loss": 8.0612,
|
| 16580 |
+
"step": 552400
|
| 16581 |
+
},
|
| 16582 |
+
{
|
| 16583 |
+
"epoch": 2.37,
|
| 16584 |
+
"learning_rate": 0.007121737894413849,
|
| 16585 |
+
"loss": 8.051,
|
| 16586 |
+
"step": 552600
|
| 16587 |
+
},
|
| 16588 |
+
{
|
| 16589 |
+
"epoch": 2.38,
|
| 16590 |
+
"learning_rate": 0.007117693507749444,
|
| 16591 |
+
"loss": 8.0404,
|
| 16592 |
+
"step": 552800
|
| 16593 |
+
},
|
| 16594 |
+
{
|
| 16595 |
+
"epoch": 2.38,
|
| 16596 |
+
"learning_rate": 0.0071136270956335375,
|
| 16597 |
+
"loss": 8.0493,
|
| 16598 |
+
"step": 553000
|
| 16599 |
+
},
|
| 16600 |
+
{
|
| 16601 |
+
"epoch": 2.38,
|
| 16602 |
+
"learning_rate": 0.007109558980622571,
|
| 16603 |
+
"loss": 8.0652,
|
| 16604 |
+
"step": 553200
|
| 16605 |
+
},
|
| 16606 |
+
{
|
| 16607 |
+
"epoch": 2.38,
|
| 16608 |
+
"learning_rate": 0.007105489165994151,
|
| 16609 |
+
"loss": 8.0499,
|
| 16610 |
+
"step": 553400
|
| 16611 |
+
},
|
| 16612 |
+
{
|
| 16613 |
+
"epoch": 2.38,
|
| 16614 |
+
"learning_rate": 0.007101417655027253,
|
| 16615 |
+
"loss": 8.0657,
|
| 16616 |
+
"step": 553600
|
| 16617 |
+
},
|
| 16618 |
+
{
|
| 16619 |
+
"epoch": 2.38,
|
| 16620 |
+
"learning_rate": 0.007097344451002222,
|
| 16621 |
+
"loss": 8.0415,
|
| 16622 |
+
"step": 553800
|
| 16623 |
+
},
|
| 16624 |
+
{
|
| 16625 |
+
"epoch": 2.38,
|
| 16626 |
+
"learning_rate": 0.0070932695572007605,
|
| 16627 |
+
"loss": 8.0431,
|
| 16628 |
+
"step": 554000
|
| 16629 |
+
},
|
| 16630 |
+
{
|
| 16631 |
+
"epoch": 2.38,
|
| 16632 |
+
"learning_rate": 0.007089192976905942,
|
| 16633 |
+
"loss": 8.0563,
|
| 16634 |
+
"step": 554200
|
| 16635 |
+
},
|
| 16636 |
+
{
|
| 16637 |
+
"epoch": 2.38,
|
| 16638 |
+
"learning_rate": 0.007085114713402188,
|
| 16639 |
+
"loss": 8.0635,
|
| 16640 |
+
"step": 554400
|
| 16641 |
+
},
|
| 16642 |
+
{
|
| 16643 |
+
"epoch": 2.38,
|
| 16644 |
+
"learning_rate": 0.007081034769975286,
|
| 16645 |
+
"loss": 8.0628,
|
| 16646 |
+
"step": 554600
|
| 16647 |
+
},
|
| 16648 |
+
{
|
| 16649 |
+
"epoch": 2.38,
|
| 16650 |
+
"learning_rate": 0.00707697356217788,
|
| 16651 |
+
"loss": 8.0692,
|
| 16652 |
+
"step": 554800
|
| 16653 |
+
},
|
| 16654 |
+
{
|
| 16655 |
+
"epoch": 2.38,
|
| 16656 |
+
"learning_rate": 0.007072890277125996,
|
| 16657 |
+
"loss": 8.0654,
|
| 16658 |
+
"step": 555000
|
| 16659 |
+
},
|
| 16660 |
+
{
|
| 16661 |
+
"epoch": 2.39,
|
| 16662 |
+
"learning_rate": 0.00706880532199997,
|
| 16663 |
+
"loss": 8.0595,
|
| 16664 |
+
"step": 555200
|
| 16665 |
+
},
|
| 16666 |
+
{
|
| 16667 |
+
"epoch": 2.39,
|
| 16668 |
+
"learning_rate": 0.007064718700090976,
|
| 16669 |
+
"loss": 8.0514,
|
| 16670 |
+
"step": 555400
|
| 16671 |
+
},
|
| 16672 |
+
{
|
| 16673 |
+
"epoch": 2.39,
|
| 16674 |
+
"learning_rate": 0.007060630414691535,
|
| 16675 |
+
"loss": 8.0607,
|
| 16676 |
+
"step": 555600
|
| 16677 |
+
},
|
| 16678 |
+
{
|
| 16679 |
+
"epoch": 2.39,
|
| 16680 |
+
"learning_rate": 0.0070565404690954995,
|
| 16681 |
+
"loss": 8.0671,
|
| 16682 |
+
"step": 555800
|
| 16683 |
+
},
|
| 16684 |
+
{
|
| 16685 |
+
"epoch": 2.39,
|
| 16686 |
+
"learning_rate": 0.007052448866598068,
|
| 16687 |
+
"loss": 8.0563,
|
| 16688 |
+
"step": 556000
|
| 16689 |
+
},
|
| 16690 |
+
{
|
| 16691 |
+
"epoch": 2.39,
|
| 16692 |
+
"learning_rate": 0.00704835561049577,
|
| 16693 |
+
"loss": 8.0695,
|
| 16694 |
+
"step": 556200
|
| 16695 |
+
},
|
| 16696 |
+
{
|
| 16697 |
+
"epoch": 2.39,
|
| 16698 |
+
"learning_rate": 0.007044260704086468,
|
| 16699 |
+
"loss": 8.0473,
|
| 16700 |
+
"step": 556400
|
| 16701 |
+
},
|
| 16702 |
+
{
|
| 16703 |
+
"epoch": 2.39,
|
| 16704 |
+
"learning_rate": 0.007040164150669354,
|
| 16705 |
+
"loss": 8.0468,
|
| 16706 |
+
"step": 556600
|
| 16707 |
+
},
|
| 16708 |
+
{
|
| 16709 |
+
"epoch": 2.39,
|
| 16710 |
+
"learning_rate": 0.007036086448613831,
|
| 16711 |
+
"loss": 8.0611,
|
| 16712 |
+
"step": 556800
|
| 16713 |
+
},
|
| 16714 |
+
{
|
| 16715 |
+
"epoch": 2.39,
|
| 16716 |
+
"learning_rate": 0.007031986619277786,
|
| 16717 |
+
"loss": 8.0643,
|
| 16718 |
+
"step": 557000
|
| 16719 |
+
},
|
| 16720 |
+
{
|
| 16721 |
+
"epoch": 2.39,
|
| 16722 |
+
"learning_rate": 0.0070278851528229385,
|
| 16723 |
+
"loss": 8.0717,
|
| 16724 |
+
"step": 557200
|
| 16725 |
+
},
|
| 16726 |
+
{
|
| 16727 |
+
"epoch": 2.4,
|
| 16728 |
+
"learning_rate": 0.0070237820525537635,
|
| 16729 |
+
"loss": 8.0483,
|
| 16730 |
+
"step": 557400
|
| 16731 |
+
},
|
| 16732 |
+
{
|
| 16733 |
+
"epoch": 2.4,
|
| 16734 |
+
"learning_rate": 0.007019677321776058,
|
| 16735 |
+
"loss": 8.0599,
|
| 16736 |
+
"step": 557600
|
| 16737 |
+
},
|
| 16738 |
+
{
|
| 16739 |
+
"epoch": 2.4,
|
| 16740 |
+
"learning_rate": 0.007015570963796927,
|
| 16741 |
+
"loss": 8.0636,
|
| 16742 |
+
"step": 557800
|
| 16743 |
+
},
|
| 16744 |
+
{
|
| 16745 |
+
"epoch": 2.4,
|
| 16746 |
+
"learning_rate": 0.00701146298192479,
|
| 16747 |
+
"loss": 8.0634,
|
| 16748 |
+
"step": 558000
|
| 16749 |
+
},
|
| 16750 |
+
{
|
| 16751 |
+
"epoch": 2.4,
|
| 16752 |
+
"learning_rate": 0.007007353379469375,
|
| 16753 |
+
"loss": 8.0698,
|
| 16754 |
+
"step": 558200
|
| 16755 |
+
},
|
| 16756 |
+
{
|
| 16757 |
+
"epoch": 2.4,
|
| 16758 |
+
"learning_rate": 0.007003242159741711,
|
| 16759 |
+
"loss": 8.0581,
|
| 16760 |
+
"step": 558400
|
| 16761 |
+
},
|
| 16762 |
+
{
|
| 16763 |
+
"epoch": 2.4,
|
| 16764 |
+
"learning_rate": 0.0069991293260541374,
|
| 16765 |
+
"loss": 8.0534,
|
| 16766 |
+
"step": 558600
|
| 16767 |
+
},
|
| 16768 |
+
{
|
| 16769 |
+
"epoch": 2.4,
|
| 16770 |
+
"learning_rate": 0.006995035457942955,
|
| 16771 |
+
"loss": 8.0641,
|
| 16772 |
+
"step": 558800
|
| 16773 |
+
},
|
| 16774 |
+
{
|
| 16775 |
+
"epoch": 2.4,
|
| 16776 |
+
"learning_rate": 0.006990919414306169,
|
| 16777 |
+
"loss": 8.0571,
|
| 16778 |
+
"step": 559000
|
| 16779 |
+
},
|
| 16780 |
+
{
|
| 16781 |
+
"epoch": 2.4,
|
| 16782 |
+
"learning_rate": 0.0069868017666376864,
|
| 16783 |
+
"loss": 8.0577,
|
| 16784 |
+
"step": 559200
|
| 16785 |
+
},
|
| 16786 |
+
{
|
| 16787 |
+
"epoch": 2.4,
|
| 16788 |
+
"learning_rate": 0.006982703118473221,
|
| 16789 |
+
"loss": 8.0753,
|
| 16790 |
+
"step": 559400
|
| 16791 |
+
},
|
| 16792 |
+
{
|
| 16793 |
+
"epoch": 2.4,
|
| 16794 |
+
"learning_rate": 0.006978582280673894,
|
| 16795 |
+
"loss": 8.0559,
|
| 16796 |
+
"step": 559600
|
| 16797 |
+
},
|
| 16798 |
+
{
|
| 16799 |
+
"epoch": 2.41,
|
| 16800 |
+
"learning_rate": 0.006974459848782675,
|
| 16801 |
+
"loss": 8.0529,
|
| 16802 |
+
"step": 559800
|
| 16803 |
+
},
|
| 16804 |
+
{
|
| 16805 |
+
"epoch": 2.41,
|
| 16806 |
+
"learning_rate": 0.006970335826120932,
|
| 16807 |
+
"loss": 8.046,
|
| 16808 |
+
"step": 560000
|
| 16809 |
}
|
| 16810 |
],
|
| 16811 |
"max_steps": 1000000,
|
| 16812 |
"num_train_epochs": 5,
|
| 16813 |
+
"total_flos": 8.925433954352456e+17,
|
| 16814 |
"trial_name": null,
|
| 16815 |
"trial_params": null
|
| 16816 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2db06e17c94930e25ba4fa153fb1d09bc548975dd61b046eadd4ef82210ad5b
|
| 3 |
size 146774203
|