Upload 8 files
Browse files- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +261 -5
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 23093424
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:529b74d808e7406775eb8e3196fe594af28c4ea71ec9f5ae5dba2ee6bc7b58b9
|
| 3 |
size 23093424
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 46298682
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:058caa8e6c0fc57c07b779f33b25636610ecf2cf367654b5843fc8dc63021f1f
|
| 3 |
size 46298682
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c792e52c193f0f16c8ed09ef3cbc20ef01c97daab2c1902596f6e68ba633485b
|
| 3 |
size 14244
|
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:d2053d27afacc6bc6dded4d38ad7a85f2c6d88921977580cd78f5c5f7e27ff9a
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 3 |
-
"best_model_checkpoint": "outputs-6_7/checkpoint-
|
| 4 |
-
"epoch": 2.
|
| 5 |
"eval_steps": 4000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -775,6 +775,262 @@
|
|
| 775 |
"eval_samples_per_second": 14.272,
|
| 776 |
"eval_steps_per_second": 3.568,
|
| 777 |
"step": 48000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 778 |
}
|
| 779 |
],
|
| 780 |
"logging_steps": 500,
|
|
@@ -794,7 +1050,7 @@
|
|
| 794 |
"attributes": {}
|
| 795 |
}
|
| 796 |
},
|
| 797 |
-
"total_flos":
|
| 798 |
"train_batch_size": 4,
|
| 799 |
"trial_name": null,
|
| 800 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.8960378170013428,
|
| 3 |
+
"best_model_checkpoint": "outputs-6_7/checkpoint-64000",
|
| 4 |
+
"epoch": 2.7480548923964756,
|
| 5 |
"eval_steps": 4000,
|
| 6 |
+
"global_step": 64000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 775 |
"eval_samples_per_second": 14.272,
|
| 776 |
"eval_steps_per_second": 3.568,
|
| 777 |
"step": 48000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.082510348144204,
|
| 781 |
+
"grad_norm": 0.7904226183891296,
|
| 782 |
+
"learning_rate": 0.00028752952290977794,
|
| 783 |
+
"loss": 2.2271,
|
| 784 |
+
"step": 48500
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.1039795269910515,
|
| 788 |
+
"grad_norm": 0.8151206374168396,
|
| 789 |
+
"learning_rate": 0.0002874006956671104,
|
| 790 |
+
"loss": 2.2104,
|
| 791 |
+
"step": 49000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.1254487058378992,
|
| 795 |
+
"grad_norm": 0.6942662596702576,
|
| 796 |
+
"learning_rate": 0.0002872718684244428,
|
| 797 |
+
"loss": 2.2197,
|
| 798 |
+
"step": 49500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.1469178846847465,
|
| 802 |
+
"grad_norm": 0.6846303939819336,
|
| 803 |
+
"learning_rate": 0.0002871430411817752,
|
| 804 |
+
"loss": 2.2286,
|
| 805 |
+
"step": 50000
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 2.1683870635315943,
|
| 809 |
+
"grad_norm": 0.8961315155029297,
|
| 810 |
+
"learning_rate": 0.0002870142139391076,
|
| 811 |
+
"loss": 2.2329,
|
| 812 |
+
"step": 50500
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.1898562423784416,
|
| 816 |
+
"grad_norm": 0.5635807514190674,
|
| 817 |
+
"learning_rate": 0.0002868853866964401,
|
| 818 |
+
"loss": 2.2216,
|
| 819 |
+
"step": 51000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.211325421225289,
|
| 823 |
+
"grad_norm": 0.6454870700836182,
|
| 824 |
+
"learning_rate": 0.00028675655945377247,
|
| 825 |
+
"loss": 2.2119,
|
| 826 |
+
"step": 51500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.2327946000721366,
|
| 830 |
+
"grad_norm": 0.5770113468170166,
|
| 831 |
+
"learning_rate": 0.00028662773221110486,
|
| 832 |
+
"loss": 2.2216,
|
| 833 |
+
"step": 52000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 2.2327946000721366,
|
| 837 |
+
"eval_loss": 2.9131178855895996,
|
| 838 |
+
"eval_runtime": 170.3262,
|
| 839 |
+
"eval_samples_per_second": 14.678,
|
| 840 |
+
"eval_steps_per_second": 3.669,
|
| 841 |
+
"step": 52000
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 2.254263778918984,
|
| 845 |
+
"grad_norm": 0.6589009165763855,
|
| 846 |
+
"learning_rate": 0.0002864989049684373,
|
| 847 |
+
"loss": 2.2237,
|
| 848 |
+
"step": 52500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.2757329577658316,
|
| 852 |
+
"grad_norm": 0.6595714688301086,
|
| 853 |
+
"learning_rate": 0.0002863700777257697,
|
| 854 |
+
"loss": 2.2331,
|
| 855 |
+
"step": 53000
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.297202136612679,
|
| 859 |
+
"grad_norm": 0.5528385639190674,
|
| 860 |
+
"learning_rate": 0.0002862412504831021,
|
| 861 |
+
"loss": 2.2316,
|
| 862 |
+
"step": 53500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 2.318671315459526,
|
| 866 |
+
"grad_norm": 0.6706179976463318,
|
| 867 |
+
"learning_rate": 0.00028611242324043455,
|
| 868 |
+
"loss": 2.2312,
|
| 869 |
+
"step": 54000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 2.340140494306374,
|
| 873 |
+
"grad_norm": 0.6599323153495789,
|
| 874 |
+
"learning_rate": 0.000285983595997767,
|
| 875 |
+
"loss": 2.2228,
|
| 876 |
+
"step": 54500
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 2.3616096731532212,
|
| 880 |
+
"grad_norm": 0.7218915820121765,
|
| 881 |
+
"learning_rate": 0.0002858547687550994,
|
| 882 |
+
"loss": 2.2269,
|
| 883 |
+
"step": 55000
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 2.3830788520000685,
|
| 887 |
+
"grad_norm": 0.6501777768135071,
|
| 888 |
+
"learning_rate": 0.0002857259415124318,
|
| 889 |
+
"loss": 2.225,
|
| 890 |
+
"step": 55500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.4045480308469163,
|
| 894 |
+
"grad_norm": 0.6774255037307739,
|
| 895 |
+
"learning_rate": 0.00028559711426976423,
|
| 896 |
+
"loss": 2.2193,
|
| 897 |
+
"step": 56000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 2.4045480308469163,
|
| 901 |
+
"eval_loss": 2.90551495552063,
|
| 902 |
+
"eval_runtime": 173.4554,
|
| 903 |
+
"eval_samples_per_second": 14.413,
|
| 904 |
+
"eval_steps_per_second": 3.603,
|
| 905 |
+
"step": 56000
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.4260172096937636,
|
| 909 |
+
"grad_norm": 0.667073130607605,
|
| 910 |
+
"learning_rate": 0.00028546828702709663,
|
| 911 |
+
"loss": 2.2228,
|
| 912 |
+
"step": 56500
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.4474863885406113,
|
| 916 |
+
"grad_norm": 0.776077389717102,
|
| 917 |
+
"learning_rate": 0.000285339459784429,
|
| 918 |
+
"loss": 2.226,
|
| 919 |
+
"step": 57000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.4689555673874586,
|
| 923 |
+
"grad_norm": 0.7873576879501343,
|
| 924 |
+
"learning_rate": 0.00028521063254176147,
|
| 925 |
+
"loss": 2.2219,
|
| 926 |
+
"step": 57500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.490424746234306,
|
| 930 |
+
"grad_norm": 0.7621210813522339,
|
| 931 |
+
"learning_rate": 0.0002850818052990939,
|
| 932 |
+
"loss": 2.2226,
|
| 933 |
+
"step": 58000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.5118939250811536,
|
| 937 |
+
"grad_norm": 0.774750828742981,
|
| 938 |
+
"learning_rate": 0.0002849529780564263,
|
| 939 |
+
"loss": 2.2328,
|
| 940 |
+
"step": 58500
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.533363103928001,
|
| 944 |
+
"grad_norm": 0.707665205001831,
|
| 945 |
+
"learning_rate": 0.0002848241508137587,
|
| 946 |
+
"loss": 2.2342,
|
| 947 |
+
"step": 59000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.554832282774848,
|
| 951 |
+
"grad_norm": 0.7524703741073608,
|
| 952 |
+
"learning_rate": 0.00028469532357109116,
|
| 953 |
+
"loss": 2.2296,
|
| 954 |
+
"step": 59500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.576301461621696,
|
| 958 |
+
"grad_norm": 0.6186488270759583,
|
| 959 |
+
"learning_rate": 0.00028456649632842355,
|
| 960 |
+
"loss": 2.2282,
|
| 961 |
+
"step": 60000
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.576301461621696,
|
| 965 |
+
"eval_loss": 2.907226085662842,
|
| 966 |
+
"eval_runtime": 176.429,
|
| 967 |
+
"eval_samples_per_second": 14.17,
|
| 968 |
+
"eval_steps_per_second": 3.543,
|
| 969 |
+
"step": 60000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.5977706404685432,
|
| 973 |
+
"grad_norm": 0.6811486482620239,
|
| 974 |
+
"learning_rate": 0.00028443766908575594,
|
| 975 |
+
"loss": 2.2357,
|
| 976 |
+
"step": 60500
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.619239819315391,
|
| 980 |
+
"grad_norm": 0.7401767373085022,
|
| 981 |
+
"learning_rate": 0.0002843088418430884,
|
| 982 |
+
"loss": 2.2264,
|
| 983 |
+
"step": 61000
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.6407089981622383,
|
| 987 |
+
"grad_norm": 0.6240813136100769,
|
| 988 |
+
"learning_rate": 0.00028418001460042084,
|
| 989 |
+
"loss": 2.2402,
|
| 990 |
+
"step": 61500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.6621781770090855,
|
| 994 |
+
"grad_norm": 0.6217384338378906,
|
| 995 |
+
"learning_rate": 0.00028405118735775324,
|
| 996 |
+
"loss": 2.2294,
|
| 997 |
+
"step": 62000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.6836473558559333,
|
| 1001 |
+
"grad_norm": 0.5563312768936157,
|
| 1002 |
+
"learning_rate": 0.00028392236011508563,
|
| 1003 |
+
"loss": 2.2344,
|
| 1004 |
+
"step": 62500
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.7051165347027806,
|
| 1008 |
+
"grad_norm": 0.7275550961494446,
|
| 1009 |
+
"learning_rate": 0.0002837935328724181,
|
| 1010 |
+
"loss": 2.2233,
|
| 1011 |
+
"step": 63000
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.7265857135496283,
|
| 1015 |
+
"grad_norm": 0.6657426953315735,
|
| 1016 |
+
"learning_rate": 0.00028366470562975047,
|
| 1017 |
+
"loss": 2.2269,
|
| 1018 |
+
"step": 63500
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.7480548923964756,
|
| 1022 |
+
"grad_norm": 0.5833483934402466,
|
| 1023 |
+
"learning_rate": 0.0002835358783870829,
|
| 1024 |
+
"loss": 2.2234,
|
| 1025 |
+
"step": 64000
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.7480548923964756,
|
| 1029 |
+
"eval_loss": 2.8960378170013428,
|
| 1030 |
+
"eval_runtime": 165.7901,
|
| 1031 |
+
"eval_samples_per_second": 15.079,
|
| 1032 |
+
"eval_steps_per_second": 3.77,
|
| 1033 |
+
"step": 64000
|
| 1034 |
}
|
| 1035 |
],
|
| 1036 |
"logging_steps": 500,
|
|
|
|
| 1050 |
"attributes": {}
|
| 1051 |
}
|
| 1052 |
},
|
| 1053 |
+
"total_flos": 7.740828282336215e+18,
|
| 1054 |
"train_batch_size": 4,
|
| 1055 |
"trial_name": null,
|
| 1056 |
"trial_params": null
|