Training in progress, step 43000, 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 sha256:3e472aa71c0bbcf7414fdf78eb35678e4d7f14aaadbf7918df34ea4652685a2b
|
| 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 sha256:29a7917c3e15e53145e8af6a97cd92e27e857ac54af72012dd85f2d0eb1081f1
|
| 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 sha256:002fcceb837e35ad0286b2e53e51596b46f1c5fb3a394693cfa1d4217734bbf5
|
| 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 sha256:2b2fd93bc7be1bea8db846b99724f24354c313e216c8e605acbf0553b5cf7bbe
|
| 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 sha256:95d3b87bea0041465cfcfc42b3360ab7ae12574769e94f070bd3670e72f35265
|
| 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:b2aa9dd63f7c0335f8a7a3673499d73cbdede80fcaa770aeaf3e472e8afd2064
|
| 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 sha256:5826b5a5d200e1498d14ab4d55e0411eaadcedbdfecbd73b3dc7c48d0447c718
|
| 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,
|
|
@@ -14708,6 +14708,356 @@
|
|
| 14708 |
"learning_rate": 0.0004865086109646348,
|
| 14709 |
"loss": 17.292,
|
| 14710 |
"step": 42000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14711 |
}
|
| 14712 |
],
|
| 14713 |
"logging_steps": 20,
|
|
@@ -14727,7 +15077,7 @@
|
|
| 14727 |
"attributes": {}
|
| 14728 |
}
|
| 14729 |
},
|
| 14730 |
-
"total_flos": 3.
|
| 14731 |
"train_batch_size": 48,
|
| 14732 |
"trial_name": null,
|
| 14733 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.08384885755931576,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 43000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14708 |
"learning_rate": 0.0004865086109646348,
|
| 14709 |
"loss": 17.292,
|
| 14710 |
"step": 42000
|
| 14711 |
+
},
|
| 14712 |
+
{
|
| 14713 |
+
"epoch": 0.081937883596336,
|
| 14714 |
+
"grad_norm": 7.0625,
|
| 14715 |
+
"learning_rate": 0.00048650210893372547,
|
| 14716 |
+
"loss": 17.3624,
|
| 14717 |
+
"step": 42020
|
| 14718 |
+
},
|
| 14719 |
+
{
|
| 14720 |
+
"epoch": 0.08197688306496824,
|
| 14721 |
+
"grad_norm": 7.25,
|
| 14722 |
+
"learning_rate": 0.00048649560690281607,
|
| 14723 |
+
"loss": 17.2483,
|
| 14724 |
+
"step": 42040
|
| 14725 |
+
},
|
| 14726 |
+
{
|
| 14727 |
+
"epoch": 0.08201588253360048,
|
| 14728 |
+
"grad_norm": 7.15625,
|
| 14729 |
+
"learning_rate": 0.00048648910487190673,
|
| 14730 |
+
"loss": 17.2416,
|
| 14731 |
+
"step": 42060
|
| 14732 |
+
},
|
| 14733 |
+
{
|
| 14734 |
+
"epoch": 0.08205488200223272,
|
| 14735 |
+
"grad_norm": 7.9375,
|
| 14736 |
+
"learning_rate": 0.0004864826028409974,
|
| 14737 |
+
"loss": 17.3319,
|
| 14738 |
+
"step": 42080
|
| 14739 |
+
},
|
| 14740 |
+
{
|
| 14741 |
+
"epoch": 0.08209388147086497,
|
| 14742 |
+
"grad_norm": 8.125,
|
| 14743 |
+
"learning_rate": 0.00048647610081008804,
|
| 14744 |
+
"loss": 17.2649,
|
| 14745 |
+
"step": 42100
|
| 14746 |
+
},
|
| 14747 |
+
{
|
| 14748 |
+
"epoch": 0.0821328809394972,
|
| 14749 |
+
"grad_norm": 7.0,
|
| 14750 |
+
"learning_rate": 0.0004864695987791787,
|
| 14751 |
+
"loss": 17.2337,
|
| 14752 |
+
"step": 42120
|
| 14753 |
+
},
|
| 14754 |
+
{
|
| 14755 |
+
"epoch": 0.08217188040812944,
|
| 14756 |
+
"grad_norm": 8.6875,
|
| 14757 |
+
"learning_rate": 0.0004864630967482693,
|
| 14758 |
+
"loss": 17.1953,
|
| 14759 |
+
"step": 42140
|
| 14760 |
+
},
|
| 14761 |
+
{
|
| 14762 |
+
"epoch": 0.08221087987676168,
|
| 14763 |
+
"grad_norm": 7.59375,
|
| 14764 |
+
"learning_rate": 0.00048645659471735996,
|
| 14765 |
+
"loss": 17.2625,
|
| 14766 |
+
"step": 42160
|
| 14767 |
+
},
|
| 14768 |
+
{
|
| 14769 |
+
"epoch": 0.08224987934539392,
|
| 14770 |
+
"grad_norm": 7.1875,
|
| 14771 |
+
"learning_rate": 0.0004864500926864506,
|
| 14772 |
+
"loss": 17.3246,
|
| 14773 |
+
"step": 42180
|
| 14774 |
+
},
|
| 14775 |
+
{
|
| 14776 |
+
"epoch": 0.08228887881402616,
|
| 14777 |
+
"grad_norm": 7.75,
|
| 14778 |
+
"learning_rate": 0.0004864435906555413,
|
| 14779 |
+
"loss": 17.2691,
|
| 14780 |
+
"step": 42200
|
| 14781 |
+
},
|
| 14782 |
+
{
|
| 14783 |
+
"epoch": 0.0823278782826584,
|
| 14784 |
+
"grad_norm": 7.0,
|
| 14785 |
+
"learning_rate": 0.00048643708862463193,
|
| 14786 |
+
"loss": 17.3746,
|
| 14787 |
+
"step": 42220
|
| 14788 |
+
},
|
| 14789 |
+
{
|
| 14790 |
+
"epoch": 0.08236687775129063,
|
| 14791 |
+
"grad_norm": 7.03125,
|
| 14792 |
+
"learning_rate": 0.0004864305865937226,
|
| 14793 |
+
"loss": 17.3057,
|
| 14794 |
+
"step": 42240
|
| 14795 |
+
},
|
| 14796 |
+
{
|
| 14797 |
+
"epoch": 0.08240587721992287,
|
| 14798 |
+
"grad_norm": 7.40625,
|
| 14799 |
+
"learning_rate": 0.00048642408456281324,
|
| 14800 |
+
"loss": 17.3146,
|
| 14801 |
+
"step": 42260
|
| 14802 |
+
},
|
| 14803 |
+
{
|
| 14804 |
+
"epoch": 0.08244487668855512,
|
| 14805 |
+
"grad_norm": 7.125,
|
| 14806 |
+
"learning_rate": 0.00048641758253190385,
|
| 14807 |
+
"loss": 17.3207,
|
| 14808 |
+
"step": 42280
|
| 14809 |
+
},
|
| 14810 |
+
{
|
| 14811 |
+
"epoch": 0.08248387615718736,
|
| 14812 |
+
"grad_norm": 7.4375,
|
| 14813 |
+
"learning_rate": 0.00048641108050099445,
|
| 14814 |
+
"loss": 17.3296,
|
| 14815 |
+
"step": 42300
|
| 14816 |
+
},
|
| 14817 |
+
{
|
| 14818 |
+
"epoch": 0.0825228756258196,
|
| 14819 |
+
"grad_norm": 7.375,
|
| 14820 |
+
"learning_rate": 0.0004864045784700851,
|
| 14821 |
+
"loss": 17.2988,
|
| 14822 |
+
"step": 42320
|
| 14823 |
+
},
|
| 14824 |
+
{
|
| 14825 |
+
"epoch": 0.08256187509445184,
|
| 14826 |
+
"grad_norm": 7.6875,
|
| 14827 |
+
"learning_rate": 0.00048639807643917576,
|
| 14828 |
+
"loss": 17.2477,
|
| 14829 |
+
"step": 42340
|
| 14830 |
+
},
|
| 14831 |
+
{
|
| 14832 |
+
"epoch": 0.08260087456308408,
|
| 14833 |
+
"grad_norm": 7.65625,
|
| 14834 |
+
"learning_rate": 0.0004863915744082664,
|
| 14835 |
+
"loss": 17.3086,
|
| 14836 |
+
"step": 42360
|
| 14837 |
+
},
|
| 14838 |
+
{
|
| 14839 |
+
"epoch": 0.08263987403171631,
|
| 14840 |
+
"grad_norm": 7.4375,
|
| 14841 |
+
"learning_rate": 0.0004863850723773571,
|
| 14842 |
+
"loss": 17.2836,
|
| 14843 |
+
"step": 42380
|
| 14844 |
+
},
|
| 14845 |
+
{
|
| 14846 |
+
"epoch": 0.08267887350034855,
|
| 14847 |
+
"grad_norm": 7.03125,
|
| 14848 |
+
"learning_rate": 0.00048637857034644773,
|
| 14849 |
+
"loss": 17.2822,
|
| 14850 |
+
"step": 42400
|
| 14851 |
+
},
|
| 14852 |
+
{
|
| 14853 |
+
"epoch": 0.0827178729689808,
|
| 14854 |
+
"grad_norm": 7.125,
|
| 14855 |
+
"learning_rate": 0.0004863720683155384,
|
| 14856 |
+
"loss": 17.2869,
|
| 14857 |
+
"step": 42420
|
| 14858 |
+
},
|
| 14859 |
+
{
|
| 14860 |
+
"epoch": 0.08275687243761304,
|
| 14861 |
+
"grad_norm": 7.25,
|
| 14862 |
+
"learning_rate": 0.00048636556628462905,
|
| 14863 |
+
"loss": 17.2606,
|
| 14864 |
+
"step": 42440
|
| 14865 |
+
},
|
| 14866 |
+
{
|
| 14867 |
+
"epoch": 0.08279587190624528,
|
| 14868 |
+
"grad_norm": 6.71875,
|
| 14869 |
+
"learning_rate": 0.00048635906425371965,
|
| 14870 |
+
"loss": 17.2897,
|
| 14871 |
+
"step": 42460
|
| 14872 |
+
},
|
| 14873 |
+
{
|
| 14874 |
+
"epoch": 0.08283487137487752,
|
| 14875 |
+
"grad_norm": 7.375,
|
| 14876 |
+
"learning_rate": 0.0004863525622228103,
|
| 14877 |
+
"loss": 17.3211,
|
| 14878 |
+
"step": 42480
|
| 14879 |
+
},
|
| 14880 |
+
{
|
| 14881 |
+
"epoch": 0.08287387084350975,
|
| 14882 |
+
"grad_norm": 6.8125,
|
| 14883 |
+
"learning_rate": 0.00048634606019190096,
|
| 14884 |
+
"loss": 17.2688,
|
| 14885 |
+
"step": 42500
|
| 14886 |
+
},
|
| 14887 |
+
{
|
| 14888 |
+
"epoch": 0.08291287031214199,
|
| 14889 |
+
"grad_norm": 8.3125,
|
| 14890 |
+
"learning_rate": 0.00048633955816099157,
|
| 14891 |
+
"loss": 17.3131,
|
| 14892 |
+
"step": 42520
|
| 14893 |
+
},
|
| 14894 |
+
{
|
| 14895 |
+
"epoch": 0.08295186978077423,
|
| 14896 |
+
"grad_norm": 6.9375,
|
| 14897 |
+
"learning_rate": 0.0004863330561300822,
|
| 14898 |
+
"loss": 17.2749,
|
| 14899 |
+
"step": 42540
|
| 14900 |
+
},
|
| 14901 |
+
{
|
| 14902 |
+
"epoch": 0.08299086924940648,
|
| 14903 |
+
"grad_norm": 7.0625,
|
| 14904 |
+
"learning_rate": 0.0004863265540991729,
|
| 14905 |
+
"loss": 17.2178,
|
| 14906 |
+
"step": 42560
|
| 14907 |
+
},
|
| 14908 |
+
{
|
| 14909 |
+
"epoch": 0.08302986871803872,
|
| 14910 |
+
"grad_norm": 7.375,
|
| 14911 |
+
"learning_rate": 0.00048632005206826354,
|
| 14912 |
+
"loss": 17.2386,
|
| 14913 |
+
"step": 42580
|
| 14914 |
+
},
|
| 14915 |
+
{
|
| 14916 |
+
"epoch": 0.08306886818667096,
|
| 14917 |
+
"grad_norm": 6.71875,
|
| 14918 |
+
"learning_rate": 0.0004863135500373542,
|
| 14919 |
+
"loss": 17.2432,
|
| 14920 |
+
"step": 42600
|
| 14921 |
+
},
|
| 14922 |
+
{
|
| 14923 |
+
"epoch": 0.0831078676553032,
|
| 14924 |
+
"grad_norm": 7.6875,
|
| 14925 |
+
"learning_rate": 0.0004863070480064448,
|
| 14926 |
+
"loss": 17.2513,
|
| 14927 |
+
"step": 42620
|
| 14928 |
+
},
|
| 14929 |
+
{
|
| 14930 |
+
"epoch": 0.08314686712393543,
|
| 14931 |
+
"grad_norm": 7.15625,
|
| 14932 |
+
"learning_rate": 0.00048630054597553546,
|
| 14933 |
+
"loss": 17.3046,
|
| 14934 |
+
"step": 42640
|
| 14935 |
+
},
|
| 14936 |
+
{
|
| 14937 |
+
"epoch": 0.08318586659256767,
|
| 14938 |
+
"grad_norm": 7.78125,
|
| 14939 |
+
"learning_rate": 0.0004862940439446261,
|
| 14940 |
+
"loss": 17.2278,
|
| 14941 |
+
"step": 42660
|
| 14942 |
+
},
|
| 14943 |
+
{
|
| 14944 |
+
"epoch": 0.08322486606119991,
|
| 14945 |
+
"grad_norm": 8.0,
|
| 14946 |
+
"learning_rate": 0.00048628754191371677,
|
| 14947 |
+
"loss": 17.2885,
|
| 14948 |
+
"step": 42680
|
| 14949 |
+
},
|
| 14950 |
+
{
|
| 14951 |
+
"epoch": 0.08326386552983216,
|
| 14952 |
+
"grad_norm": 7.1875,
|
| 14953 |
+
"learning_rate": 0.0004862810398828074,
|
| 14954 |
+
"loss": 17.268,
|
| 14955 |
+
"step": 42700
|
| 14956 |
+
},
|
| 14957 |
+
{
|
| 14958 |
+
"epoch": 0.0833028649984644,
|
| 14959 |
+
"grad_norm": 7.9375,
|
| 14960 |
+
"learning_rate": 0.0004862745378518981,
|
| 14961 |
+
"loss": 17.3266,
|
| 14962 |
+
"step": 42720
|
| 14963 |
+
},
|
| 14964 |
+
{
|
| 14965 |
+
"epoch": 0.08334186446709664,
|
| 14966 |
+
"grad_norm": 7.5,
|
| 14967 |
+
"learning_rate": 0.00048626803582098874,
|
| 14968 |
+
"loss": 17.331,
|
| 14969 |
+
"step": 42740
|
| 14970 |
+
},
|
| 14971 |
+
{
|
| 14972 |
+
"epoch": 0.08338086393572887,
|
| 14973 |
+
"grad_norm": 8.4375,
|
| 14974 |
+
"learning_rate": 0.00048626153379007934,
|
| 14975 |
+
"loss": 17.326,
|
| 14976 |
+
"step": 42760
|
| 14977 |
+
},
|
| 14978 |
+
{
|
| 14979 |
+
"epoch": 0.08341986340436111,
|
| 14980 |
+
"grad_norm": 7.03125,
|
| 14981 |
+
"learning_rate": 0.00048625503175916995,
|
| 14982 |
+
"loss": 17.2474,
|
| 14983 |
+
"step": 42780
|
| 14984 |
+
},
|
| 14985 |
+
{
|
| 14986 |
+
"epoch": 0.08345886287299335,
|
| 14987 |
+
"grad_norm": 8.0,
|
| 14988 |
+
"learning_rate": 0.0004862485297282606,
|
| 14989 |
+
"loss": 17.2174,
|
| 14990 |
+
"step": 42800
|
| 14991 |
+
},
|
| 14992 |
+
{
|
| 14993 |
+
"epoch": 0.0834978623416256,
|
| 14994 |
+
"grad_norm": 7.4375,
|
| 14995 |
+
"learning_rate": 0.00048624202769735126,
|
| 14996 |
+
"loss": 17.2893,
|
| 14997 |
+
"step": 42820
|
| 14998 |
+
},
|
| 14999 |
+
{
|
| 15000 |
+
"epoch": 0.08353686181025784,
|
| 15001 |
+
"grad_norm": 6.71875,
|
| 15002 |
+
"learning_rate": 0.0004862355256664419,
|
| 15003 |
+
"loss": 17.2931,
|
| 15004 |
+
"step": 42840
|
| 15005 |
+
},
|
| 15006 |
+
{
|
| 15007 |
+
"epoch": 0.08357586127889008,
|
| 15008 |
+
"grad_norm": 8.8125,
|
| 15009 |
+
"learning_rate": 0.0004862290236355326,
|
| 15010 |
+
"loss": 17.2065,
|
| 15011 |
+
"step": 42860
|
| 15012 |
+
},
|
| 15013 |
+
{
|
| 15014 |
+
"epoch": 0.08361486074752232,
|
| 15015 |
+
"grad_norm": 7.46875,
|
| 15016 |
+
"learning_rate": 0.00048622252160462323,
|
| 15017 |
+
"loss": 17.3003,
|
| 15018 |
+
"step": 42880
|
| 15019 |
+
},
|
| 15020 |
+
{
|
| 15021 |
+
"epoch": 0.08365386021615455,
|
| 15022 |
+
"grad_norm": 6.71875,
|
| 15023 |
+
"learning_rate": 0.0004862160195737139,
|
| 15024 |
+
"loss": 17.2048,
|
| 15025 |
+
"step": 42900
|
| 15026 |
+
},
|
| 15027 |
+
{
|
| 15028 |
+
"epoch": 0.08369285968478679,
|
| 15029 |
+
"grad_norm": 7.3125,
|
| 15030 |
+
"learning_rate": 0.0004862095175428045,
|
| 15031 |
+
"loss": 17.2964,
|
| 15032 |
+
"step": 42920
|
| 15033 |
+
},
|
| 15034 |
+
{
|
| 15035 |
+
"epoch": 0.08373185915341903,
|
| 15036 |
+
"grad_norm": 7.3125,
|
| 15037 |
+
"learning_rate": 0.00048620301551189515,
|
| 15038 |
+
"loss": 17.2578,
|
| 15039 |
+
"step": 42940
|
| 15040 |
+
},
|
| 15041 |
+
{
|
| 15042 |
+
"epoch": 0.08377085862205128,
|
| 15043 |
+
"grad_norm": 7.0,
|
| 15044 |
+
"learning_rate": 0.0004861965134809858,
|
| 15045 |
+
"loss": 17.2819,
|
| 15046 |
+
"step": 42960
|
| 15047 |
+
},
|
| 15048 |
+
{
|
| 15049 |
+
"epoch": 0.08380985809068352,
|
| 15050 |
+
"grad_norm": 8.3125,
|
| 15051 |
+
"learning_rate": 0.00048619001145007646,
|
| 15052 |
+
"loss": 17.3285,
|
| 15053 |
+
"step": 42980
|
| 15054 |
+
},
|
| 15055 |
+
{
|
| 15056 |
+
"epoch": 0.08384885755931576,
|
| 15057 |
+
"grad_norm": 7.34375,
|
| 15058 |
+
"learning_rate": 0.0004861835094191671,
|
| 15059 |
+
"loss": 17.2176,
|
| 15060 |
+
"step": 43000
|
| 15061 |
}
|
| 15062 |
],
|
| 15063 |
"logging_steps": 20,
|
|
|
|
| 15077 |
"attributes": {}
|
| 15078 |
}
|
| 15079 |
},
|
| 15080 |
+
"total_flos": 3.1611854039032005e+19,
|
| 15081 |
"train_batch_size": 48,
|
| 15082 |
"trial_name": null,
|
| 15083 |
"trial_params": null
|