Training in progress, step 34000, checkpoint
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/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +353 -3
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 304481530
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f93d8842f0c954c3661adb051b7c777a2074dc17881db4c6482f77fdfea35689
|
| 3 |
size 304481530
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 402029570
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9464fea72d20548378873ca9649a6f50ba6b4db96c4791b86a40e68cd2f117f
|
| 3 |
size 402029570
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f6f0cdf802dda1436ff1b5753ea2fc9cd6b41b89c8d768c845ca45c23f1a3a6
|
| 3 |
size 14960
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71ec4a27d72e766749c21a3cce4e8501c09e87bb4a01a766b92af927b987955e
|
| 3 |
size 14960
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1baeda778fb69c752b27c376bfc33c15cdeb99901a2e400eec901308e9c4d165
|
| 3 |
size 14960
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45464bdd935d8dda7cf7e54e49055c416b048cbf68607bf5b4772a85a0d72865
|
| 3 |
size 14960
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76c65f9b06bc61f9a6e0b66a7fae0c308064f158a8b952ec27830bd12572afeb
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -11558,6 +11558,356 @@
|
|
| 11558 |
"learning_rate": 0.0004894345248738443,
|
| 11559 |
"loss": 17.8699,
|
| 11560 |
"step": 33000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11561 |
}
|
| 11562 |
],
|
| 11563 |
"logging_steps": 20,
|
|
@@ -11577,7 +11927,7 @@
|
|
| 11577 |
"attributes": {}
|
| 11578 |
}
|
| 11579 |
},
|
| 11580 |
-
"total_flos": 2.
|
| 11581 |
"train_batch_size": 48,
|
| 11582 |
"trial_name": null,
|
| 11583 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.06629909667480781,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 34000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11558 |
"learning_rate": 0.0004894345248738443,
|
| 11559 |
"loss": 17.8699,
|
| 11560 |
"step": 33000
|
| 11561 |
+
},
|
| 11562 |
+
{
|
| 11563 |
+
"epoch": 0.06438812271182805,
|
| 11564 |
+
"grad_norm": 7.8125,
|
| 11565 |
+
"learning_rate": 0.000489428022842935,
|
| 11566 |
+
"loss": 17.9012,
|
| 11567 |
+
"step": 33020
|
| 11568 |
+
},
|
| 11569 |
+
{
|
| 11570 |
+
"epoch": 0.06442712218046029,
|
| 11571 |
+
"grad_norm": 7.5625,
|
| 11572 |
+
"learning_rate": 0.0004894215208120256,
|
| 11573 |
+
"loss": 17.9211,
|
| 11574 |
+
"step": 33040
|
| 11575 |
+
},
|
| 11576 |
+
{
|
| 11577 |
+
"epoch": 0.06446612164909253,
|
| 11578 |
+
"grad_norm": 8.1875,
|
| 11579 |
+
"learning_rate": 0.0004894150187811163,
|
| 11580 |
+
"loss": 17.8865,
|
| 11581 |
+
"step": 33060
|
| 11582 |
+
},
|
| 11583 |
+
{
|
| 11584 |
+
"epoch": 0.06450512111772477,
|
| 11585 |
+
"grad_norm": 8.8125,
|
| 11586 |
+
"learning_rate": 0.000489408516750207,
|
| 11587 |
+
"loss": 17.9138,
|
| 11588 |
+
"step": 33080
|
| 11589 |
+
},
|
| 11590 |
+
{
|
| 11591 |
+
"epoch": 0.06454412058635701,
|
| 11592 |
+
"grad_norm": 7.625,
|
| 11593 |
+
"learning_rate": 0.0004894020147192976,
|
| 11594 |
+
"loss": 17.9299,
|
| 11595 |
+
"step": 33100
|
| 11596 |
+
},
|
| 11597 |
+
{
|
| 11598 |
+
"epoch": 0.06458312005498926,
|
| 11599 |
+
"grad_norm": 7.6875,
|
| 11600 |
+
"learning_rate": 0.0004893955126883883,
|
| 11601 |
+
"loss": 17.8413,
|
| 11602 |
+
"step": 33120
|
| 11603 |
+
},
|
| 11604 |
+
{
|
| 11605 |
+
"epoch": 0.06462211952362149,
|
| 11606 |
+
"grad_norm": 8.0,
|
| 11607 |
+
"learning_rate": 0.0004893890106574788,
|
| 11608 |
+
"loss": 17.8209,
|
| 11609 |
+
"step": 33140
|
| 11610 |
+
},
|
| 11611 |
+
{
|
| 11612 |
+
"epoch": 0.06466111899225373,
|
| 11613 |
+
"grad_norm": 7.4375,
|
| 11614 |
+
"learning_rate": 0.0004893825086265695,
|
| 11615 |
+
"loss": 17.8805,
|
| 11616 |
+
"step": 33160
|
| 11617 |
+
},
|
| 11618 |
+
{
|
| 11619 |
+
"epoch": 0.06470011846088597,
|
| 11620 |
+
"grad_norm": 7.65625,
|
| 11621 |
+
"learning_rate": 0.0004893760065956601,
|
| 11622 |
+
"loss": 17.9232,
|
| 11623 |
+
"step": 33180
|
| 11624 |
+
},
|
| 11625 |
+
{
|
| 11626 |
+
"epoch": 0.06473911792951821,
|
| 11627 |
+
"grad_norm": 8.125,
|
| 11628 |
+
"learning_rate": 0.0004893695045647508,
|
| 11629 |
+
"loss": 17.9263,
|
| 11630 |
+
"step": 33200
|
| 11631 |
+
},
|
| 11632 |
+
{
|
| 11633 |
+
"epoch": 0.06477811739815045,
|
| 11634 |
+
"grad_norm": 8.0625,
|
| 11635 |
+
"learning_rate": 0.0004893630025338414,
|
| 11636 |
+
"loss": 17.9114,
|
| 11637 |
+
"step": 33220
|
| 11638 |
+
},
|
| 11639 |
+
{
|
| 11640 |
+
"epoch": 0.0648171168667827,
|
| 11641 |
+
"grad_norm": 7.71875,
|
| 11642 |
+
"learning_rate": 0.0004893565005029321,
|
| 11643 |
+
"loss": 17.8717,
|
| 11644 |
+
"step": 33240
|
| 11645 |
+
},
|
| 11646 |
+
{
|
| 11647 |
+
"epoch": 0.06485611633541492,
|
| 11648 |
+
"grad_norm": 7.96875,
|
| 11649 |
+
"learning_rate": 0.0004893499984720228,
|
| 11650 |
+
"loss": 17.8552,
|
| 11651 |
+
"step": 33260
|
| 11652 |
+
},
|
| 11653 |
+
{
|
| 11654 |
+
"epoch": 0.06489511580404717,
|
| 11655 |
+
"grad_norm": 7.96875,
|
| 11656 |
+
"learning_rate": 0.0004893434964411134,
|
| 11657 |
+
"loss": 17.9458,
|
| 11658 |
+
"step": 33280
|
| 11659 |
+
},
|
| 11660 |
+
{
|
| 11661 |
+
"epoch": 0.06493411527267941,
|
| 11662 |
+
"grad_norm": 7.875,
|
| 11663 |
+
"learning_rate": 0.000489336994410204,
|
| 11664 |
+
"loss": 17.8794,
|
| 11665 |
+
"step": 33300
|
| 11666 |
+
},
|
| 11667 |
+
{
|
| 11668 |
+
"epoch": 0.06497311474131165,
|
| 11669 |
+
"grad_norm": 8.125,
|
| 11670 |
+
"learning_rate": 0.0004893304923792946,
|
| 11671 |
+
"loss": 17.9009,
|
| 11672 |
+
"step": 33320
|
| 11673 |
+
},
|
| 11674 |
+
{
|
| 11675 |
+
"epoch": 0.06501211420994389,
|
| 11676 |
+
"grad_norm": 8.0625,
|
| 11677 |
+
"learning_rate": 0.0004893239903483853,
|
| 11678 |
+
"loss": 17.8307,
|
| 11679 |
+
"step": 33340
|
| 11680 |
+
},
|
| 11681 |
+
{
|
| 11682 |
+
"epoch": 0.06505111367857613,
|
| 11683 |
+
"grad_norm": 8.375,
|
| 11684 |
+
"learning_rate": 0.0004893174883174759,
|
| 11685 |
+
"loss": 17.8965,
|
| 11686 |
+
"step": 33360
|
| 11687 |
+
},
|
| 11688 |
+
{
|
| 11689 |
+
"epoch": 0.06509011314720838,
|
| 11690 |
+
"grad_norm": 8.0625,
|
| 11691 |
+
"learning_rate": 0.0004893109862865666,
|
| 11692 |
+
"loss": 17.9195,
|
| 11693 |
+
"step": 33380
|
| 11694 |
+
},
|
| 11695 |
+
{
|
| 11696 |
+
"epoch": 0.0651291126158406,
|
| 11697 |
+
"grad_norm": 7.90625,
|
| 11698 |
+
"learning_rate": 0.0004893044842556573,
|
| 11699 |
+
"loss": 17.7803,
|
| 11700 |
+
"step": 33400
|
| 11701 |
+
},
|
| 11702 |
+
{
|
| 11703 |
+
"epoch": 0.06516811208447285,
|
| 11704 |
+
"grad_norm": 8.25,
|
| 11705 |
+
"learning_rate": 0.0004892979822247479,
|
| 11706 |
+
"loss": 17.8673,
|
| 11707 |
+
"step": 33420
|
| 11708 |
+
},
|
| 11709 |
+
{
|
| 11710 |
+
"epoch": 0.06520711155310509,
|
| 11711 |
+
"grad_norm": 7.71875,
|
| 11712 |
+
"learning_rate": 0.0004892914801938386,
|
| 11713 |
+
"loss": 17.8586,
|
| 11714 |
+
"step": 33440
|
| 11715 |
+
},
|
| 11716 |
+
{
|
| 11717 |
+
"epoch": 0.06524611102173733,
|
| 11718 |
+
"grad_norm": 8.75,
|
| 11719 |
+
"learning_rate": 0.0004892849781629292,
|
| 11720 |
+
"loss": 17.9052,
|
| 11721 |
+
"step": 33460
|
| 11722 |
+
},
|
| 11723 |
+
{
|
| 11724 |
+
"epoch": 0.06528511049036957,
|
| 11725 |
+
"grad_norm": 8.9375,
|
| 11726 |
+
"learning_rate": 0.0004892784761320199,
|
| 11727 |
+
"loss": 17.8737,
|
| 11728 |
+
"step": 33480
|
| 11729 |
+
},
|
| 11730 |
+
{
|
| 11731 |
+
"epoch": 0.06532410995900181,
|
| 11732 |
+
"grad_norm": 8.0625,
|
| 11733 |
+
"learning_rate": 0.0004892719741011105,
|
| 11734 |
+
"loss": 17.9304,
|
| 11735 |
+
"step": 33500
|
| 11736 |
+
},
|
| 11737 |
+
{
|
| 11738 |
+
"epoch": 0.06536310942763404,
|
| 11739 |
+
"grad_norm": 8.6875,
|
| 11740 |
+
"learning_rate": 0.0004892654720702011,
|
| 11741 |
+
"loss": 17.8793,
|
| 11742 |
+
"step": 33520
|
| 11743 |
+
},
|
| 11744 |
+
{
|
| 11745 |
+
"epoch": 0.06540210889626628,
|
| 11746 |
+
"grad_norm": 7.5625,
|
| 11747 |
+
"learning_rate": 0.0004892589700392917,
|
| 11748 |
+
"loss": 17.9025,
|
| 11749 |
+
"step": 33540
|
| 11750 |
+
},
|
| 11751 |
+
{
|
| 11752 |
+
"epoch": 0.06544110836489853,
|
| 11753 |
+
"grad_norm": 7.96875,
|
| 11754 |
+
"learning_rate": 0.0004892524680083824,
|
| 11755 |
+
"loss": 17.8407,
|
| 11756 |
+
"step": 33560
|
| 11757 |
+
},
|
| 11758 |
+
{
|
| 11759 |
+
"epoch": 0.06548010783353077,
|
| 11760 |
+
"grad_norm": 7.78125,
|
| 11761 |
+
"learning_rate": 0.0004892459659774731,
|
| 11762 |
+
"loss": 17.9782,
|
| 11763 |
+
"step": 33580
|
| 11764 |
+
},
|
| 11765 |
+
{
|
| 11766 |
+
"epoch": 0.06551910730216301,
|
| 11767 |
+
"grad_norm": 8.0,
|
| 11768 |
+
"learning_rate": 0.0004892394639465637,
|
| 11769 |
+
"loss": 17.9469,
|
| 11770 |
+
"step": 33600
|
| 11771 |
+
},
|
| 11772 |
+
{
|
| 11773 |
+
"epoch": 0.06555810677079525,
|
| 11774 |
+
"grad_norm": 7.21875,
|
| 11775 |
+
"learning_rate": 0.0004892329619156544,
|
| 11776 |
+
"loss": 17.9057,
|
| 11777 |
+
"step": 33620
|
| 11778 |
+
},
|
| 11779 |
+
{
|
| 11780 |
+
"epoch": 0.0655971062394275,
|
| 11781 |
+
"grad_norm": 8.375,
|
| 11782 |
+
"learning_rate": 0.000489226459884745,
|
| 11783 |
+
"loss": 17.8254,
|
| 11784 |
+
"step": 33640
|
| 11785 |
+
},
|
| 11786 |
+
{
|
| 11787 |
+
"epoch": 0.06563610570805972,
|
| 11788 |
+
"grad_norm": 8.4375,
|
| 11789 |
+
"learning_rate": 0.0004892199578538357,
|
| 11790 |
+
"loss": 17.8844,
|
| 11791 |
+
"step": 33660
|
| 11792 |
+
},
|
| 11793 |
+
{
|
| 11794 |
+
"epoch": 0.06567510517669196,
|
| 11795 |
+
"grad_norm": 7.53125,
|
| 11796 |
+
"learning_rate": 0.0004892134558229263,
|
| 11797 |
+
"loss": 17.7609,
|
| 11798 |
+
"step": 33680
|
| 11799 |
+
},
|
| 11800 |
+
{
|
| 11801 |
+
"epoch": 0.0657141046453242,
|
| 11802 |
+
"grad_norm": 8.25,
|
| 11803 |
+
"learning_rate": 0.000489206953792017,
|
| 11804 |
+
"loss": 17.7972,
|
| 11805 |
+
"step": 33700
|
| 11806 |
+
},
|
| 11807 |
+
{
|
| 11808 |
+
"epoch": 0.06575310411395645,
|
| 11809 |
+
"grad_norm": 8.125,
|
| 11810 |
+
"learning_rate": 0.0004892004517611077,
|
| 11811 |
+
"loss": 17.8673,
|
| 11812 |
+
"step": 33720
|
| 11813 |
+
},
|
| 11814 |
+
{
|
| 11815 |
+
"epoch": 0.06579210358258869,
|
| 11816 |
+
"grad_norm": 7.46875,
|
| 11817 |
+
"learning_rate": 0.0004891939497301983,
|
| 11818 |
+
"loss": 17.8256,
|
| 11819 |
+
"step": 33740
|
| 11820 |
+
},
|
| 11821 |
+
{
|
| 11822 |
+
"epoch": 0.06583110305122093,
|
| 11823 |
+
"grad_norm": 8.375,
|
| 11824 |
+
"learning_rate": 0.0004891874476992889,
|
| 11825 |
+
"loss": 17.8436,
|
| 11826 |
+
"step": 33760
|
| 11827 |
+
},
|
| 11828 |
+
{
|
| 11829 |
+
"epoch": 0.06587010251985316,
|
| 11830 |
+
"grad_norm": 8.0625,
|
| 11831 |
+
"learning_rate": 0.0004891809456683795,
|
| 11832 |
+
"loss": 17.8555,
|
| 11833 |
+
"step": 33780
|
| 11834 |
+
},
|
| 11835 |
+
{
|
| 11836 |
+
"epoch": 0.0659091019884854,
|
| 11837 |
+
"grad_norm": 8.25,
|
| 11838 |
+
"learning_rate": 0.0004891744436374702,
|
| 11839 |
+
"loss": 17.8169,
|
| 11840 |
+
"step": 33800
|
| 11841 |
+
},
|
| 11842 |
+
{
|
| 11843 |
+
"epoch": 0.06594810145711764,
|
| 11844 |
+
"grad_norm": 7.5,
|
| 11845 |
+
"learning_rate": 0.0004891679416065608,
|
| 11846 |
+
"loss": 17.8591,
|
| 11847 |
+
"step": 33820
|
| 11848 |
+
},
|
| 11849 |
+
{
|
| 11850 |
+
"epoch": 0.06598710092574989,
|
| 11851 |
+
"grad_norm": 8.1875,
|
| 11852 |
+
"learning_rate": 0.0004891614395756515,
|
| 11853 |
+
"loss": 17.8805,
|
| 11854 |
+
"step": 33840
|
| 11855 |
+
},
|
| 11856 |
+
{
|
| 11857 |
+
"epoch": 0.06602610039438213,
|
| 11858 |
+
"grad_norm": 8.1875,
|
| 11859 |
+
"learning_rate": 0.0004891549375447421,
|
| 11860 |
+
"loss": 17.822,
|
| 11861 |
+
"step": 33860
|
| 11862 |
+
},
|
| 11863 |
+
{
|
| 11864 |
+
"epoch": 0.06606509986301437,
|
| 11865 |
+
"grad_norm": 7.5,
|
| 11866 |
+
"learning_rate": 0.0004891484355138328,
|
| 11867 |
+
"loss": 17.7957,
|
| 11868 |
+
"step": 33880
|
| 11869 |
+
},
|
| 11870 |
+
{
|
| 11871 |
+
"epoch": 0.06610409933164661,
|
| 11872 |
+
"grad_norm": 7.84375,
|
| 11873 |
+
"learning_rate": 0.0004891419334829235,
|
| 11874 |
+
"loss": 17.7377,
|
| 11875 |
+
"step": 33900
|
| 11876 |
+
},
|
| 11877 |
+
{
|
| 11878 |
+
"epoch": 0.06614309880027884,
|
| 11879 |
+
"grad_norm": 7.625,
|
| 11880 |
+
"learning_rate": 0.000489135431452014,
|
| 11881 |
+
"loss": 17.8446,
|
| 11882 |
+
"step": 33920
|
| 11883 |
+
},
|
| 11884 |
+
{
|
| 11885 |
+
"epoch": 0.06618209826891108,
|
| 11886 |
+
"grad_norm": 8.1875,
|
| 11887 |
+
"learning_rate": 0.0004891289294211047,
|
| 11888 |
+
"loss": 17.8576,
|
| 11889 |
+
"step": 33940
|
| 11890 |
+
},
|
| 11891 |
+
{
|
| 11892 |
+
"epoch": 0.06622109773754332,
|
| 11893 |
+
"grad_norm": 7.59375,
|
| 11894 |
+
"learning_rate": 0.0004891224273901953,
|
| 11895 |
+
"loss": 17.8222,
|
| 11896 |
+
"step": 33960
|
| 11897 |
+
},
|
| 11898 |
+
{
|
| 11899 |
+
"epoch": 0.06626009720617557,
|
| 11900 |
+
"grad_norm": 8.375,
|
| 11901 |
+
"learning_rate": 0.000489115925359286,
|
| 11902 |
+
"loss": 17.8738,
|
| 11903 |
+
"step": 33980
|
| 11904 |
+
},
|
| 11905 |
+
{
|
| 11906 |
+
"epoch": 0.06629909667480781,
|
| 11907 |
+
"grad_norm": 9.5,
|
| 11908 |
+
"learning_rate": 0.0004891094233283766,
|
| 11909 |
+
"loss": 17.7685,
|
| 11910 |
+
"step": 34000
|
| 11911 |
}
|
| 11912 |
],
|
| 11913 |
"logging_steps": 20,
|
|
|
|
| 11927 |
"attributes": {}
|
| 11928 |
}
|
| 11929 |
},
|
| 11930 |
+
"total_flos": 2.49955116052151e+19,
|
| 11931 |
"train_batch_size": 48,
|
| 11932 |
"trial_name": null,
|
| 11933 |
"trial_params": null
|