Training in progress, step 63000, 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 sha256:556e04061439aefa2faf42602d8335f6056e7c2d8ccff02572fb79ee53c3a2ac
|
| 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:b505fb8a4aad264bf26959233c456abd8ffc13521341e6244296dda957682cab
|
| 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 sha256:51cec976f0b6bc46df42f80a3a5910d24a915ac4f9ffe69f3a0b56ab5793fb69
|
| 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:b77e72d201987fbdefae243e7de5979b9b0d513ed9dbf08e44762424ba46e273
|
| 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 sha256:017ef0e270526cf1c1fac5d228b8134fd7141a73ad6fb2e06942745b3291e5c1
|
| 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 sha256:51342e581dc082f4f5875d43b80e54af74d9b981269f28ece8a2973868ae8791
|
| 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 sha256:833e7904537342d6a70168a0886564cda3a0784722dc75bdf590e9222202000a
|
| 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,
|
|
@@ -21708,6 +21708,356 @@
|
|
| 21708 |
"learning_rate": 0.0004848130217984836,
|
| 21709 |
"loss": 16.7898,
|
| 21710 |
"step": 62000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21711 |
}
|
| 21712 |
],
|
| 21713 |
"logging_steps": 20,
|
|
@@ -21727,7 +22077,7 @@
|
|
| 21727 |
"attributes": {}
|
| 21728 |
}
|
| 21729 |
},
|
| 21730 |
-
"total_flos": 4.
|
| 21731 |
"train_batch_size": 48,
|
| 21732 |
"trial_name": null,
|
| 21733 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.09332282587442006,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 63000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 21708 |
"learning_rate": 0.0004848130217984836,
|
| 21709 |
"loss": 16.7898,
|
| 21710 |
"step": 62000
|
| 21711 |
+
},
|
| 21712 |
+
{
|
| 21713 |
+
"epoch": 0.09187113747192908,
|
| 21714 |
+
"grad_norm": 6.625,
|
| 21715 |
+
"learning_rate": 0.000484808082863476,
|
| 21716 |
+
"loss": 16.8082,
|
| 21717 |
+
"step": 62020
|
| 21718 |
+
},
|
| 21719 |
+
{
|
| 21720 |
+
"epoch": 0.09190076376585747,
|
| 21721 |
+
"grad_norm": 7.40625,
|
| 21722 |
+
"learning_rate": 0.00048480314392846844,
|
| 21723 |
+
"loss": 16.8028,
|
| 21724 |
+
"step": 62040
|
| 21725 |
+
},
|
| 21726 |
+
{
|
| 21727 |
+
"epoch": 0.09193039005978586,
|
| 21728 |
+
"grad_norm": 6.78125,
|
| 21729 |
+
"learning_rate": 0.00048479820499346083,
|
| 21730 |
+
"loss": 16.8189,
|
| 21731 |
+
"step": 62060
|
| 21732 |
+
},
|
| 21733 |
+
{
|
| 21734 |
+
"epoch": 0.09196001635371424,
|
| 21735 |
+
"grad_norm": 7.15625,
|
| 21736 |
+
"learning_rate": 0.0004847932660584533,
|
| 21737 |
+
"loss": 16.8504,
|
| 21738 |
+
"step": 62080
|
| 21739 |
+
},
|
| 21740 |
+
{
|
| 21741 |
+
"epoch": 0.09198964264764263,
|
| 21742 |
+
"grad_norm": 6.6875,
|
| 21743 |
+
"learning_rate": 0.00048478832712344573,
|
| 21744 |
+
"loss": 16.7952,
|
| 21745 |
+
"step": 62100
|
| 21746 |
+
},
|
| 21747 |
+
{
|
| 21748 |
+
"epoch": 0.09201926894157102,
|
| 21749 |
+
"grad_norm": 7.65625,
|
| 21750 |
+
"learning_rate": 0.0004847833881884381,
|
| 21751 |
+
"loss": 16.7928,
|
| 21752 |
+
"step": 62120
|
| 21753 |
+
},
|
| 21754 |
+
{
|
| 21755 |
+
"epoch": 0.09204889523549942,
|
| 21756 |
+
"grad_norm": 7.65625,
|
| 21757 |
+
"learning_rate": 0.0004847784492534306,
|
| 21758 |
+
"loss": 16.7917,
|
| 21759 |
+
"step": 62140
|
| 21760 |
+
},
|
| 21761 |
+
{
|
| 21762 |
+
"epoch": 0.0920785215294278,
|
| 21763 |
+
"grad_norm": 7.125,
|
| 21764 |
+
"learning_rate": 0.000484773510318423,
|
| 21765 |
+
"loss": 16.7933,
|
| 21766 |
+
"step": 62160
|
| 21767 |
+
},
|
| 21768 |
+
{
|
| 21769 |
+
"epoch": 0.09210814782335619,
|
| 21770 |
+
"grad_norm": 7.53125,
|
| 21771 |
+
"learning_rate": 0.00048476857138341547,
|
| 21772 |
+
"loss": 16.8126,
|
| 21773 |
+
"step": 62180
|
| 21774 |
+
},
|
| 21775 |
+
{
|
| 21776 |
+
"epoch": 0.09213777411728458,
|
| 21777 |
+
"grad_norm": 6.65625,
|
| 21778 |
+
"learning_rate": 0.00048476363244840786,
|
| 21779 |
+
"loss": 16.7553,
|
| 21780 |
+
"step": 62200
|
| 21781 |
+
},
|
| 21782 |
+
{
|
| 21783 |
+
"epoch": 0.09216740041121296,
|
| 21784 |
+
"grad_norm": 6.78125,
|
| 21785 |
+
"learning_rate": 0.00048475869351340036,
|
| 21786 |
+
"loss": 16.7727,
|
| 21787 |
+
"step": 62220
|
| 21788 |
+
},
|
| 21789 |
+
{
|
| 21790 |
+
"epoch": 0.09219702670514135,
|
| 21791 |
+
"grad_norm": 6.6875,
|
| 21792 |
+
"learning_rate": 0.00048475375457839276,
|
| 21793 |
+
"loss": 16.879,
|
| 21794 |
+
"step": 62240
|
| 21795 |
+
},
|
| 21796 |
+
{
|
| 21797 |
+
"epoch": 0.09222665299906974,
|
| 21798 |
+
"grad_norm": 6.78125,
|
| 21799 |
+
"learning_rate": 0.0004847488156433852,
|
| 21800 |
+
"loss": 16.7929,
|
| 21801 |
+
"step": 62260
|
| 21802 |
+
},
|
| 21803 |
+
{
|
| 21804 |
+
"epoch": 0.09225627929299812,
|
| 21805 |
+
"grad_norm": 7.25,
|
| 21806 |
+
"learning_rate": 0.0004847438767083776,
|
| 21807 |
+
"loss": 16.7963,
|
| 21808 |
+
"step": 62280
|
| 21809 |
+
},
|
| 21810 |
+
{
|
| 21811 |
+
"epoch": 0.09228590558692651,
|
| 21812 |
+
"grad_norm": 6.4375,
|
| 21813 |
+
"learning_rate": 0.0004847389377733701,
|
| 21814 |
+
"loss": 16.7686,
|
| 21815 |
+
"step": 62300
|
| 21816 |
+
},
|
| 21817 |
+
{
|
| 21818 |
+
"epoch": 0.0923155318808549,
|
| 21819 |
+
"grad_norm": 6.96875,
|
| 21820 |
+
"learning_rate": 0.0004847339988383625,
|
| 21821 |
+
"loss": 16.8297,
|
| 21822 |
+
"step": 62320
|
| 21823 |
+
},
|
| 21824 |
+
{
|
| 21825 |
+
"epoch": 0.09234515817478328,
|
| 21826 |
+
"grad_norm": 6.875,
|
| 21827 |
+
"learning_rate": 0.00048472905990335494,
|
| 21828 |
+
"loss": 16.8149,
|
| 21829 |
+
"step": 62340
|
| 21830 |
+
},
|
| 21831 |
+
{
|
| 21832 |
+
"epoch": 0.09237478446871167,
|
| 21833 |
+
"grad_norm": 7.3125,
|
| 21834 |
+
"learning_rate": 0.00048472412096834733,
|
| 21835 |
+
"loss": 16.8835,
|
| 21836 |
+
"step": 62360
|
| 21837 |
+
},
|
| 21838 |
+
{
|
| 21839 |
+
"epoch": 0.09240441076264005,
|
| 21840 |
+
"grad_norm": 7.03125,
|
| 21841 |
+
"learning_rate": 0.00048471918203333984,
|
| 21842 |
+
"loss": 16.8404,
|
| 21843 |
+
"step": 62380
|
| 21844 |
+
},
|
| 21845 |
+
{
|
| 21846 |
+
"epoch": 0.09243403705656844,
|
| 21847 |
+
"grad_norm": 6.75,
|
| 21848 |
+
"learning_rate": 0.00048471424309833223,
|
| 21849 |
+
"loss": 16.8179,
|
| 21850 |
+
"step": 62400
|
| 21851 |
+
},
|
| 21852 |
+
{
|
| 21853 |
+
"epoch": 0.09246366335049683,
|
| 21854 |
+
"grad_norm": 6.3125,
|
| 21855 |
+
"learning_rate": 0.0004847093041633246,
|
| 21856 |
+
"loss": 16.7695,
|
| 21857 |
+
"step": 62420
|
| 21858 |
+
},
|
| 21859 |
+
{
|
| 21860 |
+
"epoch": 0.09249328964442521,
|
| 21861 |
+
"grad_norm": 6.25,
|
| 21862 |
+
"learning_rate": 0.0004847043652283171,
|
| 21863 |
+
"loss": 16.8396,
|
| 21864 |
+
"step": 62440
|
| 21865 |
+
},
|
| 21866 |
+
{
|
| 21867 |
+
"epoch": 0.09252291593835361,
|
| 21868 |
+
"grad_norm": 7.09375,
|
| 21869 |
+
"learning_rate": 0.0004846994262933095,
|
| 21870 |
+
"loss": 16.8195,
|
| 21871 |
+
"step": 62460
|
| 21872 |
+
},
|
| 21873 |
+
{
|
| 21874 |
+
"epoch": 0.092552542232282,
|
| 21875 |
+
"grad_norm": 7.375,
|
| 21876 |
+
"learning_rate": 0.00048469448735830197,
|
| 21877 |
+
"loss": 16.7936,
|
| 21878 |
+
"step": 62480
|
| 21879 |
+
},
|
| 21880 |
+
{
|
| 21881 |
+
"epoch": 0.09258216852621039,
|
| 21882 |
+
"grad_norm": 6.5625,
|
| 21883 |
+
"learning_rate": 0.00048468954842329436,
|
| 21884 |
+
"loss": 16.846,
|
| 21885 |
+
"step": 62500
|
| 21886 |
+
},
|
| 21887 |
+
{
|
| 21888 |
+
"epoch": 0.09261179482013877,
|
| 21889 |
+
"grad_norm": 7.15625,
|
| 21890 |
+
"learning_rate": 0.00048468460948828686,
|
| 21891 |
+
"loss": 16.7826,
|
| 21892 |
+
"step": 62520
|
| 21893 |
+
},
|
| 21894 |
+
{
|
| 21895 |
+
"epoch": 0.09264142111406716,
|
| 21896 |
+
"grad_norm": 6.90625,
|
| 21897 |
+
"learning_rate": 0.00048467967055327926,
|
| 21898 |
+
"loss": 16.8026,
|
| 21899 |
+
"step": 62540
|
| 21900 |
+
},
|
| 21901 |
+
{
|
| 21902 |
+
"epoch": 0.09267104740799555,
|
| 21903 |
+
"grad_norm": 7.3125,
|
| 21904 |
+
"learning_rate": 0.0004846747316182717,
|
| 21905 |
+
"loss": 16.7603,
|
| 21906 |
+
"step": 62560
|
| 21907 |
+
},
|
| 21908 |
+
{
|
| 21909 |
+
"epoch": 0.09270067370192393,
|
| 21910 |
+
"grad_norm": 7.84375,
|
| 21911 |
+
"learning_rate": 0.0004846697926832641,
|
| 21912 |
+
"loss": 16.8185,
|
| 21913 |
+
"step": 62580
|
| 21914 |
+
},
|
| 21915 |
+
{
|
| 21916 |
+
"epoch": 0.09273029999585232,
|
| 21917 |
+
"grad_norm": 6.625,
|
| 21918 |
+
"learning_rate": 0.0004846648537482566,
|
| 21919 |
+
"loss": 16.7457,
|
| 21920 |
+
"step": 62600
|
| 21921 |
+
},
|
| 21922 |
+
{
|
| 21923 |
+
"epoch": 0.0927599262897807,
|
| 21924 |
+
"grad_norm": 7.3125,
|
| 21925 |
+
"learning_rate": 0.000484659914813249,
|
| 21926 |
+
"loss": 16.7269,
|
| 21927 |
+
"step": 62620
|
| 21928 |
+
},
|
| 21929 |
+
{
|
| 21930 |
+
"epoch": 0.09278955258370909,
|
| 21931 |
+
"grad_norm": 6.21875,
|
| 21932 |
+
"learning_rate": 0.00048465497587824144,
|
| 21933 |
+
"loss": 16.7724,
|
| 21934 |
+
"step": 62640
|
| 21935 |
+
},
|
| 21936 |
+
{
|
| 21937 |
+
"epoch": 0.09281917887763748,
|
| 21938 |
+
"grad_norm": 7.4375,
|
| 21939 |
+
"learning_rate": 0.00048465003694323383,
|
| 21940 |
+
"loss": 16.7531,
|
| 21941 |
+
"step": 62660
|
| 21942 |
+
},
|
| 21943 |
+
{
|
| 21944 |
+
"epoch": 0.09284880517156587,
|
| 21945 |
+
"grad_norm": 6.53125,
|
| 21946 |
+
"learning_rate": 0.00048464509800822634,
|
| 21947 |
+
"loss": 16.7827,
|
| 21948 |
+
"step": 62680
|
| 21949 |
+
},
|
| 21950 |
+
{
|
| 21951 |
+
"epoch": 0.09287843146549425,
|
| 21952 |
+
"grad_norm": 6.375,
|
| 21953 |
+
"learning_rate": 0.00048464015907321873,
|
| 21954 |
+
"loss": 16.7857,
|
| 21955 |
+
"step": 62700
|
| 21956 |
+
},
|
| 21957 |
+
{
|
| 21958 |
+
"epoch": 0.09290805775942264,
|
| 21959 |
+
"grad_norm": 6.25,
|
| 21960 |
+
"learning_rate": 0.0004846352201382112,
|
| 21961 |
+
"loss": 16.7486,
|
| 21962 |
+
"step": 62720
|
| 21963 |
+
},
|
| 21964 |
+
{
|
| 21965 |
+
"epoch": 0.09293768405335102,
|
| 21966 |
+
"grad_norm": 6.3125,
|
| 21967 |
+
"learning_rate": 0.0004846302812032036,
|
| 21968 |
+
"loss": 16.7855,
|
| 21969 |
+
"step": 62740
|
| 21970 |
+
},
|
| 21971 |
+
{
|
| 21972 |
+
"epoch": 0.09296731034727941,
|
| 21973 |
+
"grad_norm": 5.84375,
|
| 21974 |
+
"learning_rate": 0.000484625342268196,
|
| 21975 |
+
"loss": 16.745,
|
| 21976 |
+
"step": 62760
|
| 21977 |
+
},
|
| 21978 |
+
{
|
| 21979 |
+
"epoch": 0.09299693664120781,
|
| 21980 |
+
"grad_norm": 25.875,
|
| 21981 |
+
"learning_rate": 0.00048462040333318847,
|
| 21982 |
+
"loss": 16.8632,
|
| 21983 |
+
"step": 62780
|
| 21984 |
+
},
|
| 21985 |
+
{
|
| 21986 |
+
"epoch": 0.0930265629351362,
|
| 21987 |
+
"grad_norm": 7.03125,
|
| 21988 |
+
"learning_rate": 0.00048461546439818086,
|
| 21989 |
+
"loss": 16.7818,
|
| 21990 |
+
"step": 62800
|
| 21991 |
+
},
|
| 21992 |
+
{
|
| 21993 |
+
"epoch": 0.09305618922906458,
|
| 21994 |
+
"grad_norm": 7.6875,
|
| 21995 |
+
"learning_rate": 0.00048461052546317336,
|
| 21996 |
+
"loss": 16.7971,
|
| 21997 |
+
"step": 62820
|
| 21998 |
+
},
|
| 21999 |
+
{
|
| 22000 |
+
"epoch": 0.09308581552299297,
|
| 22001 |
+
"grad_norm": 6.46875,
|
| 22002 |
+
"learning_rate": 0.00048460558652816576,
|
| 22003 |
+
"loss": 16.7621,
|
| 22004 |
+
"step": 62840
|
| 22005 |
+
},
|
| 22006 |
+
{
|
| 22007 |
+
"epoch": 0.09311544181692136,
|
| 22008 |
+
"grad_norm": 6.78125,
|
| 22009 |
+
"learning_rate": 0.0004846006475931582,
|
| 22010 |
+
"loss": 16.7443,
|
| 22011 |
+
"step": 62860
|
| 22012 |
+
},
|
| 22013 |
+
{
|
| 22014 |
+
"epoch": 0.09314506811084974,
|
| 22015 |
+
"grad_norm": 6.875,
|
| 22016 |
+
"learning_rate": 0.0004845957086581506,
|
| 22017 |
+
"loss": 16.8043,
|
| 22018 |
+
"step": 62880
|
| 22019 |
+
},
|
| 22020 |
+
{
|
| 22021 |
+
"epoch": 0.09317469440477813,
|
| 22022 |
+
"grad_norm": 7.3125,
|
| 22023 |
+
"learning_rate": 0.0004845907697231431,
|
| 22024 |
+
"loss": 16.797,
|
| 22025 |
+
"step": 62900
|
| 22026 |
+
},
|
| 22027 |
+
{
|
| 22028 |
+
"epoch": 0.09320432069870652,
|
| 22029 |
+
"grad_norm": 6.3125,
|
| 22030 |
+
"learning_rate": 0.0004845858307881355,
|
| 22031 |
+
"loss": 16.7884,
|
| 22032 |
+
"step": 62920
|
| 22033 |
+
},
|
| 22034 |
+
{
|
| 22035 |
+
"epoch": 0.0932339469926349,
|
| 22036 |
+
"grad_norm": 6.5625,
|
| 22037 |
+
"learning_rate": 0.00048458089185312794,
|
| 22038 |
+
"loss": 16.7869,
|
| 22039 |
+
"step": 62940
|
| 22040 |
+
},
|
| 22041 |
+
{
|
| 22042 |
+
"epoch": 0.09326357328656329,
|
| 22043 |
+
"grad_norm": 6.21875,
|
| 22044 |
+
"learning_rate": 0.00048457595291812034,
|
| 22045 |
+
"loss": 16.7761,
|
| 22046 |
+
"step": 62960
|
| 22047 |
+
},
|
| 22048 |
+
{
|
| 22049 |
+
"epoch": 0.09329319958049168,
|
| 22050 |
+
"grad_norm": 6.875,
|
| 22051 |
+
"learning_rate": 0.00048457101398311284,
|
| 22052 |
+
"loss": 16.7793,
|
| 22053 |
+
"step": 62980
|
| 22054 |
+
},
|
| 22055 |
+
{
|
| 22056 |
+
"epoch": 0.09332282587442006,
|
| 22057 |
+
"grad_norm": 6.40625,
|
| 22058 |
+
"learning_rate": 0.00048456607504810523,
|
| 22059 |
+
"loss": 16.7568,
|
| 22060 |
+
"step": 63000
|
| 22061 |
}
|
| 22062 |
],
|
| 22063 |
"logging_steps": 20,
|
|
|
|
| 22077 |
"attributes": {}
|
| 22078 |
}
|
| 22079 |
},
|
| 22080 |
+
"total_flos": 4.631878990886758e+19,
|
| 22081 |
"train_batch_size": 48,
|
| 22082 |
"trial_name": null,
|
| 22083 |
"trial_params": null
|