Training in progress, step 100000, 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 sha256:798e4c08328ff72dd804b4b821f83d713d3bf3f7a62da31d51dad0c1d955a1f1
|
| 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 sha256:49e4a6e85c05c84c1454f6858ed124ea574d045e8a46bf97bb6ce2e8fdb6ad68
|
| 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:e696340926f87bd0cbe9acb97696741cec50b1e6dab1f632fbf68502deed4c91
|
| 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 sha256:9ca42d928672e5c145d25c855c4dc0f68ef33c95da86902e3f719c48aef2783d
|
| 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 sha256:16534bd8da014a8888b580d751a72391b76bdb93bc39b9827227800635511b3f
|
| 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:acc911890512190de2007bd19cfdb8686d83789a3d9f07e00219c8ca4868a224
|
| 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 sha256:2c1f2d019d5e0e424fcb2007c1b18b654131001c25986230c4d24a2d4d5a546b
|
| 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,
|
|
@@ -34658,6 +34658,356 @@
|
|
| 34658 |
"learning_rate": 0.00047567599203448565,
|
| 34659 |
"loss": 15.8396,
|
| 34660 |
"step": 99000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34661 |
}
|
| 34662 |
],
|
| 34663 |
"logging_steps": 20,
|
|
@@ -34677,7 +35027,7 @@
|
|
| 34677 |
"attributes": {}
|
| 34678 |
}
|
| 34679 |
},
|
| 34680 |
-
"total_flos": 7.
|
| 34681 |
"train_batch_size": 48,
|
| 34682 |
"trial_name": null,
|
| 34683 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.1481314696419366,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 100000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 34658 |
"learning_rate": 0.00047567599203448565,
|
| 34659 |
"loss": 15.8396,
|
| 34660 |
"step": 99000
|
| 34661 |
+
},
|
| 34662 |
+
{
|
| 34663 |
+
"epoch": 0.14667978123944564,
|
| 34664 |
+
"grad_norm": 6.75,
|
| 34665 |
+
"learning_rate": 0.00047567105309947804,
|
| 34666 |
+
"loss": 15.8544,
|
| 34667 |
+
"step": 99020
|
| 34668 |
+
},
|
| 34669 |
+
{
|
| 34670 |
+
"epoch": 0.14670940753337403,
|
| 34671 |
+
"grad_norm": 6.3125,
|
| 34672 |
+
"learning_rate": 0.0004756661141644705,
|
| 34673 |
+
"loss": 15.8167,
|
| 34674 |
+
"step": 99040
|
| 34675 |
+
},
|
| 34676 |
+
{
|
| 34677 |
+
"epoch": 0.1467390338273024,
|
| 34678 |
+
"grad_norm": 7.5,
|
| 34679 |
+
"learning_rate": 0.00047566117522946294,
|
| 34680 |
+
"loss": 15.8752,
|
| 34681 |
+
"step": 99060
|
| 34682 |
+
},
|
| 34683 |
+
{
|
| 34684 |
+
"epoch": 0.1467686601212308,
|
| 34685 |
+
"grad_norm": 6.0,
|
| 34686 |
+
"learning_rate": 0.0004756562362944554,
|
| 34687 |
+
"loss": 15.9426,
|
| 34688 |
+
"step": 99080
|
| 34689 |
+
},
|
| 34690 |
+
{
|
| 34691 |
+
"epoch": 0.14679828641515918,
|
| 34692 |
+
"grad_norm": 5.90625,
|
| 34693 |
+
"learning_rate": 0.0004756512973594478,
|
| 34694 |
+
"loss": 15.8358,
|
| 34695 |
+
"step": 99100
|
| 34696 |
+
},
|
| 34697 |
+
{
|
| 34698 |
+
"epoch": 0.14682791270908757,
|
| 34699 |
+
"grad_norm": 6.65625,
|
| 34700 |
+
"learning_rate": 0.0004756463584244402,
|
| 34701 |
+
"loss": 15.8739,
|
| 34702 |
+
"step": 99120
|
| 34703 |
+
},
|
| 34704 |
+
{
|
| 34705 |
+
"epoch": 0.14685753900301596,
|
| 34706 |
+
"grad_norm": 6.6875,
|
| 34707 |
+
"learning_rate": 0.0004756414194894327,
|
| 34708 |
+
"loss": 15.91,
|
| 34709 |
+
"step": 99140
|
| 34710 |
+
},
|
| 34711 |
+
{
|
| 34712 |
+
"epoch": 0.14688716529694434,
|
| 34713 |
+
"grad_norm": 7.0,
|
| 34714 |
+
"learning_rate": 0.0004756364805544251,
|
| 34715 |
+
"loss": 15.8444,
|
| 34716 |
+
"step": 99160
|
| 34717 |
+
},
|
| 34718 |
+
{
|
| 34719 |
+
"epoch": 0.14691679159087273,
|
| 34720 |
+
"grad_norm": 5.96875,
|
| 34721 |
+
"learning_rate": 0.0004756315416194175,
|
| 34722 |
+
"loss": 15.9179,
|
| 34723 |
+
"step": 99180
|
| 34724 |
+
},
|
| 34725 |
+
{
|
| 34726 |
+
"epoch": 0.14694641788480112,
|
| 34727 |
+
"grad_norm": 6.46875,
|
| 34728 |
+
"learning_rate": 0.00047562660268441,
|
| 34729 |
+
"loss": 15.9259,
|
| 34730 |
+
"step": 99200
|
| 34731 |
+
},
|
| 34732 |
+
{
|
| 34733 |
+
"epoch": 0.1469760441787295,
|
| 34734 |
+
"grad_norm": 7.4375,
|
| 34735 |
+
"learning_rate": 0.0004756216637494024,
|
| 34736 |
+
"loss": 15.8124,
|
| 34737 |
+
"step": 99220
|
| 34738 |
+
},
|
| 34739 |
+
{
|
| 34740 |
+
"epoch": 0.1470056704726579,
|
| 34741 |
+
"grad_norm": 6.625,
|
| 34742 |
+
"learning_rate": 0.0004756167248143948,
|
| 34743 |
+
"loss": 15.8876,
|
| 34744 |
+
"step": 99240
|
| 34745 |
+
},
|
| 34746 |
+
{
|
| 34747 |
+
"epoch": 0.14703529676658628,
|
| 34748 |
+
"grad_norm": 6.34375,
|
| 34749 |
+
"learning_rate": 0.00047561178587938725,
|
| 34750 |
+
"loss": 15.915,
|
| 34751 |
+
"step": 99260
|
| 34752 |
+
},
|
| 34753 |
+
{
|
| 34754 |
+
"epoch": 0.14706492306051466,
|
| 34755 |
+
"grad_norm": 6.625,
|
| 34756 |
+
"learning_rate": 0.0004756068469443797,
|
| 34757 |
+
"loss": 15.9366,
|
| 34758 |
+
"step": 99280
|
| 34759 |
+
},
|
| 34760 |
+
{
|
| 34761 |
+
"epoch": 0.14709454935444305,
|
| 34762 |
+
"grad_norm": 6.0625,
|
| 34763 |
+
"learning_rate": 0.00047560190800937215,
|
| 34764 |
+
"loss": 15.9305,
|
| 34765 |
+
"step": 99300
|
| 34766 |
+
},
|
| 34767 |
+
{
|
| 34768 |
+
"epoch": 0.14712417564837144,
|
| 34769 |
+
"grad_norm": 7.03125,
|
| 34770 |
+
"learning_rate": 0.00047559696907436454,
|
| 34771 |
+
"loss": 15.8623,
|
| 34772 |
+
"step": 99320
|
| 34773 |
+
},
|
| 34774 |
+
{
|
| 34775 |
+
"epoch": 0.14715380194229982,
|
| 34776 |
+
"grad_norm": 7.53125,
|
| 34777 |
+
"learning_rate": 0.000475592030139357,
|
| 34778 |
+
"loss": 15.9174,
|
| 34779 |
+
"step": 99340
|
| 34780 |
+
},
|
| 34781 |
+
{
|
| 34782 |
+
"epoch": 0.1471834282362282,
|
| 34783 |
+
"grad_norm": 6.375,
|
| 34784 |
+
"learning_rate": 0.00047558709120434944,
|
| 34785 |
+
"loss": 15.8917,
|
| 34786 |
+
"step": 99360
|
| 34787 |
+
},
|
| 34788 |
+
{
|
| 34789 |
+
"epoch": 0.1472130545301566,
|
| 34790 |
+
"grad_norm": 6.3125,
|
| 34791 |
+
"learning_rate": 0.0004755821522693419,
|
| 34792 |
+
"loss": 15.8335,
|
| 34793 |
+
"step": 99380
|
| 34794 |
+
},
|
| 34795 |
+
{
|
| 34796 |
+
"epoch": 0.14724268082408498,
|
| 34797 |
+
"grad_norm": 6.3125,
|
| 34798 |
+
"learning_rate": 0.0004755772133343343,
|
| 34799 |
+
"loss": 15.8639,
|
| 34800 |
+
"step": 99400
|
| 34801 |
+
},
|
| 34802 |
+
{
|
| 34803 |
+
"epoch": 0.14727230711801337,
|
| 34804 |
+
"grad_norm": 6.65625,
|
| 34805 |
+
"learning_rate": 0.0004755722743993267,
|
| 34806 |
+
"loss": 15.858,
|
| 34807 |
+
"step": 99420
|
| 34808 |
+
},
|
| 34809 |
+
{
|
| 34810 |
+
"epoch": 0.14730193341194175,
|
| 34811 |
+
"grad_norm": 6.375,
|
| 34812 |
+
"learning_rate": 0.0004755673354643192,
|
| 34813 |
+
"loss": 15.8239,
|
| 34814 |
+
"step": 99440
|
| 34815 |
+
},
|
| 34816 |
+
{
|
| 34817 |
+
"epoch": 0.14733155970587014,
|
| 34818 |
+
"grad_norm": 5.9375,
|
| 34819 |
+
"learning_rate": 0.0004755623965293116,
|
| 34820 |
+
"loss": 15.849,
|
| 34821 |
+
"step": 99460
|
| 34822 |
+
},
|
| 34823 |
+
{
|
| 34824 |
+
"epoch": 0.14736118599979853,
|
| 34825 |
+
"grad_norm": 6.0,
|
| 34826 |
+
"learning_rate": 0.000475557457594304,
|
| 34827 |
+
"loss": 15.8021,
|
| 34828 |
+
"step": 99480
|
| 34829 |
+
},
|
| 34830 |
+
{
|
| 34831 |
+
"epoch": 0.14739081229372694,
|
| 34832 |
+
"grad_norm": 7.0625,
|
| 34833 |
+
"learning_rate": 0.0004755525186592965,
|
| 34834 |
+
"loss": 15.8675,
|
| 34835 |
+
"step": 99500
|
| 34836 |
+
},
|
| 34837 |
+
{
|
| 34838 |
+
"epoch": 0.14742043858765533,
|
| 34839 |
+
"grad_norm": 6.375,
|
| 34840 |
+
"learning_rate": 0.0004755475797242889,
|
| 34841 |
+
"loss": 15.8739,
|
| 34842 |
+
"step": 99520
|
| 34843 |
+
},
|
| 34844 |
+
{
|
| 34845 |
+
"epoch": 0.14745006488158371,
|
| 34846 |
+
"grad_norm": 6.21875,
|
| 34847 |
+
"learning_rate": 0.00047554264078928136,
|
| 34848 |
+
"loss": 15.8996,
|
| 34849 |
+
"step": 99540
|
| 34850 |
+
},
|
| 34851 |
+
{
|
| 34852 |
+
"epoch": 0.1474796911755121,
|
| 34853 |
+
"grad_norm": 7.09375,
|
| 34854 |
+
"learning_rate": 0.00047553770185427375,
|
| 34855 |
+
"loss": 15.8776,
|
| 34856 |
+
"step": 99560
|
| 34857 |
+
},
|
| 34858 |
+
{
|
| 34859 |
+
"epoch": 0.1475093174694405,
|
| 34860 |
+
"grad_norm": 5.5625,
|
| 34861 |
+
"learning_rate": 0.0004755327629192662,
|
| 34862 |
+
"loss": 15.8426,
|
| 34863 |
+
"step": 99580
|
| 34864 |
+
},
|
| 34865 |
+
{
|
| 34866 |
+
"epoch": 0.14753894376336887,
|
| 34867 |
+
"grad_norm": 6.75,
|
| 34868 |
+
"learning_rate": 0.00047552782398425865,
|
| 34869 |
+
"loss": 15.8734,
|
| 34870 |
+
"step": 99600
|
| 34871 |
+
},
|
| 34872 |
+
{
|
| 34873 |
+
"epoch": 0.14756857005729726,
|
| 34874 |
+
"grad_norm": 6.8125,
|
| 34875 |
+
"learning_rate": 0.00047552288504925104,
|
| 34876 |
+
"loss": 15.8602,
|
| 34877 |
+
"step": 99620
|
| 34878 |
+
},
|
| 34879 |
+
{
|
| 34880 |
+
"epoch": 0.14759819635122565,
|
| 34881 |
+
"grad_norm": 5.90625,
|
| 34882 |
+
"learning_rate": 0.0004755179461142435,
|
| 34883 |
+
"loss": 15.9296,
|
| 34884 |
+
"step": 99640
|
| 34885 |
+
},
|
| 34886 |
+
{
|
| 34887 |
+
"epoch": 0.14762782264515403,
|
| 34888 |
+
"grad_norm": 6.34375,
|
| 34889 |
+
"learning_rate": 0.00047551300717923594,
|
| 34890 |
+
"loss": 15.8599,
|
| 34891 |
+
"step": 99660
|
| 34892 |
+
},
|
| 34893 |
+
{
|
| 34894 |
+
"epoch": 0.14765744893908242,
|
| 34895 |
+
"grad_norm": 5.9375,
|
| 34896 |
+
"learning_rate": 0.0004755080682442284,
|
| 34897 |
+
"loss": 15.9459,
|
| 34898 |
+
"step": 99680
|
| 34899 |
+
},
|
| 34900 |
+
{
|
| 34901 |
+
"epoch": 0.1476870752330108,
|
| 34902 |
+
"grad_norm": 7.1875,
|
| 34903 |
+
"learning_rate": 0.0004755031293092208,
|
| 34904 |
+
"loss": 15.8781,
|
| 34905 |
+
"step": 99700
|
| 34906 |
+
},
|
| 34907 |
+
{
|
| 34908 |
+
"epoch": 0.1477167015269392,
|
| 34909 |
+
"grad_norm": 6.28125,
|
| 34910 |
+
"learning_rate": 0.0004754981903742132,
|
| 34911 |
+
"loss": 15.8215,
|
| 34912 |
+
"step": 99720
|
| 34913 |
+
},
|
| 34914 |
+
{
|
| 34915 |
+
"epoch": 0.14774632782086758,
|
| 34916 |
+
"grad_norm": 6.0625,
|
| 34917 |
+
"learning_rate": 0.0004754932514392057,
|
| 34918 |
+
"loss": 15.8065,
|
| 34919 |
+
"step": 99740
|
| 34920 |
+
},
|
| 34921 |
+
{
|
| 34922 |
+
"epoch": 0.14777595411479597,
|
| 34923 |
+
"grad_norm": 6.53125,
|
| 34924 |
+
"learning_rate": 0.0004754883125041981,
|
| 34925 |
+
"loss": 15.8926,
|
| 34926 |
+
"step": 99760
|
| 34927 |
+
},
|
| 34928 |
+
{
|
| 34929 |
+
"epoch": 0.14780558040872435,
|
| 34930 |
+
"grad_norm": 7.34375,
|
| 34931 |
+
"learning_rate": 0.0004754833735691905,
|
| 34932 |
+
"loss": 15.824,
|
| 34933 |
+
"step": 99780
|
| 34934 |
+
},
|
| 34935 |
+
{
|
| 34936 |
+
"epoch": 0.14783520670265274,
|
| 34937 |
+
"grad_norm": 6.84375,
|
| 34938 |
+
"learning_rate": 0.000475478434634183,
|
| 34939 |
+
"loss": 15.8495,
|
| 34940 |
+
"step": 99800
|
| 34941 |
+
},
|
| 34942 |
+
{
|
| 34943 |
+
"epoch": 0.14786483299658112,
|
| 34944 |
+
"grad_norm": 7.375,
|
| 34945 |
+
"learning_rate": 0.0004754734956991754,
|
| 34946 |
+
"loss": 15.8227,
|
| 34947 |
+
"step": 99820
|
| 34948 |
+
},
|
| 34949 |
+
{
|
| 34950 |
+
"epoch": 0.1478944592905095,
|
| 34951 |
+
"grad_norm": 6.0625,
|
| 34952 |
+
"learning_rate": 0.00047546855676416786,
|
| 34953 |
+
"loss": 15.8278,
|
| 34954 |
+
"step": 99840
|
| 34955 |
+
},
|
| 34956 |
+
{
|
| 34957 |
+
"epoch": 0.1479240855844379,
|
| 34958 |
+
"grad_norm": 6.3125,
|
| 34959 |
+
"learning_rate": 0.00047546361782916025,
|
| 34960 |
+
"loss": 15.8409,
|
| 34961 |
+
"step": 99860
|
| 34962 |
+
},
|
| 34963 |
+
{
|
| 34964 |
+
"epoch": 0.14795371187836628,
|
| 34965 |
+
"grad_norm": 6.21875,
|
| 34966 |
+
"learning_rate": 0.00047545867889415275,
|
| 34967 |
+
"loss": 15.8754,
|
| 34968 |
+
"step": 99880
|
| 34969 |
+
},
|
| 34970 |
+
{
|
| 34971 |
+
"epoch": 0.14798333817229467,
|
| 34972 |
+
"grad_norm": 6.3125,
|
| 34973 |
+
"learning_rate": 0.00047545373995914515,
|
| 34974 |
+
"loss": 15.8956,
|
| 34975 |
+
"step": 99900
|
| 34976 |
+
},
|
| 34977 |
+
{
|
| 34978 |
+
"epoch": 0.14801296446622306,
|
| 34979 |
+
"grad_norm": 6.40625,
|
| 34980 |
+
"learning_rate": 0.00047544880102413754,
|
| 34981 |
+
"loss": 15.8705,
|
| 34982 |
+
"step": 99920
|
| 34983 |
+
},
|
| 34984 |
+
{
|
| 34985 |
+
"epoch": 0.14804259076015144,
|
| 34986 |
+
"grad_norm": 6.90625,
|
| 34987 |
+
"learning_rate": 0.00047544386208913,
|
| 34988 |
+
"loss": 15.8666,
|
| 34989 |
+
"step": 99940
|
| 34990 |
+
},
|
| 34991 |
+
{
|
| 34992 |
+
"epoch": 0.14807221705407983,
|
| 34993 |
+
"grad_norm": 8.0625,
|
| 34994 |
+
"learning_rate": 0.00047543892315412244,
|
| 34995 |
+
"loss": 15.8759,
|
| 34996 |
+
"step": 99960
|
| 34997 |
+
},
|
| 34998 |
+
{
|
| 34999 |
+
"epoch": 0.14810184334800822,
|
| 35000 |
+
"grad_norm": 6.15625,
|
| 35001 |
+
"learning_rate": 0.0004754339842191149,
|
| 35002 |
+
"loss": 15.8608,
|
| 35003 |
+
"step": 99980
|
| 35004 |
+
},
|
| 35005 |
+
{
|
| 35006 |
+
"epoch": 0.1481314696419366,
|
| 35007 |
+
"grad_norm": 6.15625,
|
| 35008 |
+
"learning_rate": 0.0004754290452841073,
|
| 35009 |
+
"loss": 15.8969,
|
| 35010 |
+
"step": 100000
|
| 35011 |
}
|
| 35012 |
],
|
| 35013 |
"logging_steps": 20,
|
|
|
|
| 35027 |
"attributes": {}
|
| 35028 |
}
|
| 35029 |
},
|
| 35030 |
+
"total_flos": 7.35272488710722e+19,
|
| 35031 |
"train_batch_size": 48,
|
| 35032 |
"trial_name": null,
|
| 35033 |
"trial_params": null
|