Training in progress, step 2136, checkpoint
Browse files- last-checkpoint/model-00001-of-00004.safetensors +1 -1
- last-checkpoint/model-00002-of-00004.safetensors +1 -1
- last-checkpoint/model-00003-of-00004.safetensors +1 -1
- last-checkpoint/model-00004-of-00004.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +256 -4
last-checkpoint/model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4903351912
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ffed5f8c81d4bcc1c3949f7ae2640c2980c4515a7bf471d7277700e4a42dc62
|
| 3 |
size 4903351912
|
last-checkpoint/model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4947570872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2776b66179020970a8f8df643b6376fa54d907b9a0ab7de3152df871e8519472
|
| 3 |
size 4947570872
|
last-checkpoint/model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4962221464
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:637c9d5ccb29c2571a60e81aba1229d7c57a7860baf764cefb86807c1fd55c51
|
| 3 |
size 4962221464
|
last-checkpoint/model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3670322200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6e6a180710afa8be7623704d675a1486d890f8acd593108fd30e06f8faf9d99
|
| 3 |
size 3670322200
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2216
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe0c40a4a813653ed70995efe5d8a8fed35d5d52cf0ca2d406ae22aa69dd62dc
|
| 3 |
size 2216
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:638959202e00ec8e922c9fefb3271344d643c48007a3ce5c5efbd2a02e4157e6
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -14707,6 +14707,258 @@
|
|
| 14707 |
"learning_rate": 3.106191336121222e-08,
|
| 14708 |
"loss": 1.1671,
|
| 14709 |
"step": 2100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14710 |
}
|
| 14711 |
],
|
| 14712 |
"logging_steps": 1,
|
|
@@ -14721,12 +14973,12 @@
|
|
| 14721 |
"should_evaluate": false,
|
| 14722 |
"should_log": false,
|
| 14723 |
"should_save": true,
|
| 14724 |
-
"should_training_stop":
|
| 14725 |
},
|
| 14726 |
"attributes": {}
|
| 14727 |
}
|
| 14728 |
},
|
| 14729 |
-
"total_flos": 6.
|
| 14730 |
"train_batch_size": 8,
|
| 14731 |
"trial_name": null,
|
| 14732 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2136,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 14707 |
"learning_rate": 3.106191336121222e-08,
|
| 14708 |
"loss": 1.1671,
|
| 14709 |
"step": 2100
|
| 14710 |
+
},
|
| 14711 |
+
{
|
| 14712 |
+
"epoch": 1.9672284644194757,
|
| 14713 |
+
"grad_norm": 0.0,
|
| 14714 |
+
"learning_rate": 2.936063551628454e-08,
|
| 14715 |
+
"loss": 1.1406,
|
| 14716 |
+
"step": 2101
|
| 14717 |
+
},
|
| 14718 |
+
{
|
| 14719 |
+
"epoch": 1.9681647940074907,
|
| 14720 |
+
"grad_norm": 0.0,
|
| 14721 |
+
"learning_rate": 2.7707234737970325e-08,
|
| 14722 |
+
"loss": 1.155,
|
| 14723 |
+
"step": 2102
|
| 14724 |
+
},
|
| 14725 |
+
{
|
| 14726 |
+
"epoch": 1.9691011235955056,
|
| 14727 |
+
"grad_norm": 0.0,
|
| 14728 |
+
"learning_rate": 2.6101714990083292e-08,
|
| 14729 |
+
"loss": 1.1179,
|
| 14730 |
+
"step": 2103
|
| 14731 |
+
},
|
| 14732 |
+
{
|
| 14733 |
+
"epoch": 1.9700374531835205,
|
| 14734 |
+
"grad_norm": 0.0,
|
| 14735 |
+
"learning_rate": 2.4544080121657877e-08,
|
| 14736 |
+
"loss": 1.1077,
|
| 14737 |
+
"step": 2104
|
| 14738 |
+
},
|
| 14739 |
+
{
|
| 14740 |
+
"epoch": 1.9709737827715355,
|
| 14741 |
+
"grad_norm": 0.0,
|
| 14742 |
+
"learning_rate": 2.3034333866922555e-08,
|
| 14743 |
+
"loss": 1.1038,
|
| 14744 |
+
"step": 2105
|
| 14745 |
+
},
|
| 14746 |
+
{
|
| 14747 |
+
"epoch": 1.9719101123595506,
|
| 14748 |
+
"grad_norm": 0.0,
|
| 14749 |
+
"learning_rate": 2.1572479845299865e-08,
|
| 14750 |
+
"loss": 1.1178,
|
| 14751 |
+
"step": 2106
|
| 14752 |
+
},
|
| 14753 |
+
{
|
| 14754 |
+
"epoch": 1.9728464419475655,
|
| 14755 |
+
"grad_norm": 0.0,
|
| 14756 |
+
"learning_rate": 2.0158521561404188e-08,
|
| 14757 |
+
"loss": 1.1605,
|
| 14758 |
+
"step": 2107
|
| 14759 |
+
},
|
| 14760 |
+
{
|
| 14761 |
+
"epoch": 1.9737827715355807,
|
| 14762 |
+
"grad_norm": 0.0,
|
| 14763 |
+
"learning_rate": 1.879246240501509e-08,
|
| 14764 |
+
"loss": 1.1151,
|
| 14765 |
+
"step": 2108
|
| 14766 |
+
},
|
| 14767 |
+
{
|
| 14768 |
+
"epoch": 1.9747191011235956,
|
| 14769 |
+
"grad_norm": 0.0,
|
| 14770 |
+
"learning_rate": 1.747430565108843e-08,
|
| 14771 |
+
"loss": 1.1017,
|
| 14772 |
+
"step": 2109
|
| 14773 |
+
},
|
| 14774 |
+
{
|
| 14775 |
+
"epoch": 1.9756554307116105,
|
| 14776 |
+
"grad_norm": 0.0,
|
| 14777 |
+
"learning_rate": 1.6204054459736385e-08,
|
| 14778 |
+
"loss": 1.1408,
|
| 14779 |
+
"step": 2110
|
| 14780 |
+
},
|
| 14781 |
+
{
|
| 14782 |
+
"epoch": 1.9765917602996255,
|
| 14783 |
+
"grad_norm": 0.0,
|
| 14784 |
+
"learning_rate": 1.4981711876227435e-08,
|
| 14785 |
+
"loss": 1.1019,
|
| 14786 |
+
"step": 2111
|
| 14787 |
+
},
|
| 14788 |
+
{
|
| 14789 |
+
"epoch": 1.9775280898876404,
|
| 14790 |
+
"grad_norm": 0.0,
|
| 14791 |
+
"learning_rate": 1.3807280830968606e-08,
|
| 14792 |
+
"loss": 1.1559,
|
| 14793 |
+
"step": 2112
|
| 14794 |
+
},
|
| 14795 |
+
{
|
| 14796 |
+
"epoch": 1.9784644194756553,
|
| 14797 |
+
"grad_norm": 0.0,
|
| 14798 |
+
"learning_rate": 1.2680764139509915e-08,
|
| 14799 |
+
"loss": 1.1168,
|
| 14800 |
+
"step": 2113
|
| 14801 |
+
},
|
| 14802 |
+
{
|
| 14803 |
+
"epoch": 1.9794007490636703,
|
| 14804 |
+
"grad_norm": 0.0,
|
| 14805 |
+
"learning_rate": 1.1602164502531043e-08,
|
| 14806 |
+
"loss": 1.1662,
|
| 14807 |
+
"step": 2114
|
| 14808 |
+
},
|
| 14809 |
+
{
|
| 14810 |
+
"epoch": 1.9803370786516854,
|
| 14811 |
+
"grad_norm": 0.0,
|
| 14812 |
+
"learning_rate": 1.0571484505839114e-08,
|
| 14813 |
+
"loss": 1.1558,
|
| 14814 |
+
"step": 2115
|
| 14815 |
+
},
|
| 14816 |
+
{
|
| 14817 |
+
"epoch": 1.9812734082397003,
|
| 14818 |
+
"grad_norm": 0.0,
|
| 14819 |
+
"learning_rate": 9.588726620357591e-09,
|
| 14820 |
+
"loss": 1.1725,
|
| 14821 |
+
"step": 2116
|
| 14822 |
+
},
|
| 14823 |
+
{
|
| 14824 |
+
"epoch": 1.9822097378277155,
|
| 14825 |
+
"grad_norm": 0.0,
|
| 14826 |
+
"learning_rate": 8.653893202124064e-09,
|
| 14827 |
+
"loss": 1.1049,
|
| 14828 |
+
"step": 2117
|
| 14829 |
+
},
|
| 14830 |
+
{
|
| 14831 |
+
"epoch": 1.9831460674157304,
|
| 14832 |
+
"grad_norm": 0.0,
|
| 14833 |
+
"learning_rate": 7.76698649228136e-09,
|
| 14834 |
+
"loss": 1.1635,
|
| 14835 |
+
"step": 2118
|
| 14836 |
+
},
|
| 14837 |
+
{
|
| 14838 |
+
"epoch": 1.9840823970037453,
|
| 14839 |
+
"grad_norm": 0.0,
|
| 14840 |
+
"learning_rate": 6.928008617077542e-09,
|
| 14841 |
+
"loss": 1.1132,
|
| 14842 |
+
"step": 2119
|
| 14843 |
+
},
|
| 14844 |
+
{
|
| 14845 |
+
"epoch": 1.9850187265917603,
|
| 14846 |
+
"grad_norm": 0.0,
|
| 14847 |
+
"learning_rate": 6.136961587852597e-09,
|
| 14848 |
+
"loss": 1.1769,
|
| 14849 |
+
"step": 2120
|
| 14850 |
+
},
|
| 14851 |
+
{
|
| 14852 |
+
"epoch": 1.9859550561797752,
|
| 14853 |
+
"grad_norm": 0.0,
|
| 14854 |
+
"learning_rate": 5.393847301042865e-09,
|
| 14855 |
+
"loss": 1.1298,
|
| 14856 |
+
"step": 2121
|
| 14857 |
+
},
|
| 14858 |
+
{
|
| 14859 |
+
"epoch": 1.9868913857677901,
|
| 14860 |
+
"grad_norm": 0.0,
|
| 14861 |
+
"learning_rate": 4.698667538169943e-09,
|
| 14862 |
+
"loss": 1.1547,
|
| 14863 |
+
"step": 2122
|
| 14864 |
+
},
|
| 14865 |
+
{
|
| 14866 |
+
"epoch": 1.9878277153558053,
|
| 14867 |
+
"grad_norm": 0.0,
|
| 14868 |
+
"learning_rate": 4.051423965838464e-09,
|
| 14869 |
+
"loss": 1.1608,
|
| 14870 |
+
"step": 2123
|
| 14871 |
+
},
|
| 14872 |
+
{
|
| 14873 |
+
"epoch": 1.9887640449438202,
|
| 14874 |
+
"grad_norm": 0.0,
|
| 14875 |
+
"learning_rate": 3.4521181357316523e-09,
|
| 14876 |
+
"loss": 1.1669,
|
| 14877 |
+
"step": 2124
|
| 14878 |
+
},
|
| 14879 |
+
{
|
| 14880 |
+
"epoch": 1.9897003745318353,
|
| 14881 |
+
"grad_norm": 0.0,
|
| 14882 |
+
"learning_rate": 2.9007514846113304e-09,
|
| 14883 |
+
"loss": 1.167,
|
| 14884 |
+
"step": 2125
|
| 14885 |
+
},
|
| 14886 |
+
{
|
| 14887 |
+
"epoch": 1.9906367041198503,
|
| 14888 |
+
"grad_norm": 0.0,
|
| 14889 |
+
"learning_rate": 2.397325334309031e-09,
|
| 14890 |
+
"loss": 1.1729,
|
| 14891 |
+
"step": 2126
|
| 14892 |
+
},
|
| 14893 |
+
{
|
| 14894 |
+
"epoch": 1.9915730337078652,
|
| 14895 |
+
"grad_norm": 0.0,
|
| 14896 |
+
"learning_rate": 1.941840891721558e-09,
|
| 14897 |
+
"loss": 1.1634,
|
| 14898 |
+
"step": 2127
|
| 14899 |
+
},
|
| 14900 |
+
{
|
| 14901 |
+
"epoch": 1.9925093632958801,
|
| 14902 |
+
"grad_norm": 0.0,
|
| 14903 |
+
"learning_rate": 1.53429924881765e-09,
|
| 14904 |
+
"loss": 1.1068,
|
| 14905 |
+
"step": 2128
|
| 14906 |
+
},
|
| 14907 |
+
{
|
| 14908 |
+
"epoch": 1.993445692883895,
|
| 14909 |
+
"grad_norm": 0.0,
|
| 14910 |
+
"learning_rate": 1.174701382626875e-09,
|
| 14911 |
+
"loss": 1.1238,
|
| 14912 |
+
"step": 2129
|
| 14913 |
+
},
|
| 14914 |
+
{
|
| 14915 |
+
"epoch": 1.99438202247191,
|
| 14916 |
+
"grad_norm": 0.0,
|
| 14917 |
+
"learning_rate": 8.63048155235191e-10,
|
| 14918 |
+
"loss": 1.113,
|
| 14919 |
+
"step": 2130
|
| 14920 |
+
},
|
| 14921 |
+
{
|
| 14922 |
+
"epoch": 1.9953183520599251,
|
| 14923 |
+
"grad_norm": 0.0,
|
| 14924 |
+
"learning_rate": 5.99340313798269e-10,
|
| 14925 |
+
"loss": 1.1078,
|
| 14926 |
+
"step": 2131
|
| 14927 |
+
},
|
| 14928 |
+
{
|
| 14929 |
+
"epoch": 1.99625468164794,
|
| 14930 |
+
"grad_norm": 0.0,
|
| 14931 |
+
"learning_rate": 3.8357849051484655e-10,
|
| 14932 |
+
"loss": 1.102,
|
| 14933 |
+
"step": 2132
|
| 14934 |
+
},
|
| 14935 |
+
{
|
| 14936 |
+
"epoch": 1.9971910112359552,
|
| 14937 |
+
"grad_norm": 0.0,
|
| 14938 |
+
"learning_rate": 2.1576320265337403e-10,
|
| 14939 |
+
"loss": 1.0998,
|
| 14940 |
+
"step": 2133
|
| 14941 |
+
},
|
| 14942 |
+
{
|
| 14943 |
+
"epoch": 1.9981273408239701,
|
| 14944 |
+
"grad_norm": 0.0,
|
| 14945 |
+
"learning_rate": 9.58948525253689e-11,
|
| 14946 |
+
"loss": 1.1516,
|
| 14947 |
+
"step": 2134
|
| 14948 |
+
},
|
| 14949 |
+
{
|
| 14950 |
+
"epoch": 1.999063670411985,
|
| 14951 |
+
"grad_norm": 0.0,
|
| 14952 |
+
"learning_rate": 2.3973727498738387e-11,
|
| 14953 |
+
"loss": 1.1345,
|
| 14954 |
+
"step": 2135
|
| 14955 |
+
},
|
| 14956 |
+
{
|
| 14957 |
+
"epoch": 2.0,
|
| 14958 |
+
"grad_norm": 0.0,
|
| 14959 |
+
"learning_rate": 0.0,
|
| 14960 |
+
"loss": 1.2175,
|
| 14961 |
+
"step": 2136
|
| 14962 |
}
|
| 14963 |
],
|
| 14964 |
"logging_steps": 1,
|
|
|
|
| 14973 |
"should_evaluate": false,
|
| 14974 |
"should_log": false,
|
| 14975 |
"should_save": true,
|
| 14976 |
+
"should_training_stop": true
|
| 14977 |
},
|
| 14978 |
"attributes": {}
|
| 14979 |
}
|
| 14980 |
},
|
| 14981 |
+
"total_flos": 6.987483782320226e+18,
|
| 14982 |
"train_batch_size": 8,
|
| 14983 |
"trial_name": null,
|
| 14984 |
"trial_params": null
|