Training in progress, step 8000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1153648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e11c2a216b88de55916ed3daefd736b5d02ae44eb3aff9205fff663a359a69dd
|
| 3 |
size 1153648
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2334411
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dec9e90ec6317d56e8e5c7c326640545430fee9702b8965f21ab07e19706f55b
|
| 3 |
size 2334411
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5bd7db10c0e542a6e15f1ab8dc43834d225b0872bb56f7417828ec308fe5b55
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28de945f8e58539f742a954625e39b68e0e34e082c955a3ad8182afe99f0b046
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be017f27bf180c965c2836b9491b668480ab6284c868efb5ab23b789c4d091f8
|
| 3 |
size 1465
|
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,
|
|
@@ -848,6 +848,286 @@
|
|
| 848 |
"learning_rate": 0.0009632172947186774,
|
| 849 |
"loss": 5.129850463867188,
|
| 850 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 851 |
}
|
| 852 |
],
|
| 853 |
"logging_steps": 50,
|
|
@@ -867,7 +1147,7 @@
|
|
| 867 |
"attributes": {}
|
| 868 |
}
|
| 869 |
},
|
| 870 |
-
"total_flos":
|
| 871 |
"train_batch_size": 16,
|
| 872 |
"trial_name": null,
|
| 873 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.1638370640398124,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 848 |
"learning_rate": 0.0009632172947186774,
|
| 849 |
"loss": 5.129850463867188,
|
| 850 |
"step": 6000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.12390177968010813,
|
| 854 |
+
"grad_norm": 0.45102745294570923,
|
| 855 |
+
"learning_rate": 0.0009626093823779802,
|
| 856 |
+
"loss": 5.130498657226562,
|
| 857 |
+
"step": 6050
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.12492576133035696,
|
| 861 |
+
"grad_norm": 0.6717409491539001,
|
| 862 |
+
"learning_rate": 0.0009619966826544757,
|
| 863 |
+
"loss": 5.112809143066406,
|
| 864 |
+
"step": 6100
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.1259497429806058,
|
| 868 |
+
"grad_norm": 0.6257486343383789,
|
| 869 |
+
"learning_rate": 0.0009613792018887792,
|
| 870 |
+
"loss": 5.129651489257813,
|
| 871 |
+
"step": 6150
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.12697372463085463,
|
| 875 |
+
"grad_norm": 0.6519837975502014,
|
| 876 |
+
"learning_rate": 0.0009607569464709833,
|
| 877 |
+
"loss": 5.13470458984375,
|
| 878 |
+
"step": 6200
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.12799770628110343,
|
| 882 |
+
"grad_norm": 0.4877980351448059,
|
| 883 |
+
"learning_rate": 0.0009601299228405917,
|
| 884 |
+
"loss": 5.120645751953125,
|
| 885 |
+
"step": 6250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.12902168793135227,
|
| 889 |
+
"grad_norm": 1.537527084350586,
|
| 890 |
+
"learning_rate": 0.0009594981374864532,
|
| 891 |
+
"loss": 5.148428955078125,
|
| 892 |
+
"step": 6300
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.1300456695816011,
|
| 896 |
+
"grad_norm": 0.9234127402305603,
|
| 897 |
+
"learning_rate": 0.0009588615969466931,
|
| 898 |
+
"loss": 5.141029663085938,
|
| 899 |
+
"step": 6350
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.13106965123184994,
|
| 903 |
+
"grad_norm": 0.4927079975605011,
|
| 904 |
+
"learning_rate": 0.0009582203078086476,
|
| 905 |
+
"loss": 5.1216796875,
|
| 906 |
+
"step": 6400
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.13209363288209874,
|
| 910 |
+
"grad_norm": 0.8232192397117615,
|
| 911 |
+
"learning_rate": 0.0009575742767087931,
|
| 912 |
+
"loss": 5.120458984375,
|
| 913 |
+
"step": 6450
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.13311761453234758,
|
| 917 |
+
"grad_norm": 0.5774878859519958,
|
| 918 |
+
"learning_rate": 0.0009569235103326801,
|
| 919 |
+
"loss": 5.126387329101562,
|
| 920 |
+
"step": 6500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.1341415961825964,
|
| 924 |
+
"grad_norm": 0.6650785207748413,
|
| 925 |
+
"learning_rate": 0.0009562680154148622,
|
| 926 |
+
"loss": 5.114985961914062,
|
| 927 |
+
"step": 6550
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.13516557783284525,
|
| 931 |
+
"grad_norm": 0.6255061030387878,
|
| 932 |
+
"learning_rate": 0.0009556077987388274,
|
| 933 |
+
"loss": 5.120186767578125,
|
| 934 |
+
"step": 6600
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.13618955948309405,
|
| 938 |
+
"grad_norm": 0.7133514881134033,
|
| 939 |
+
"learning_rate": 0.0009549428671369271,
|
| 940 |
+
"loss": 5.121702270507813,
|
| 941 |
+
"step": 6650
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.1372135411333429,
|
| 945 |
+
"grad_norm": 0.6055569648742676,
|
| 946 |
+
"learning_rate": 0.0009542732274903063,
|
| 947 |
+
"loss": 5.14235107421875,
|
| 948 |
+
"step": 6700
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.13823752278359172,
|
| 952 |
+
"grad_norm": 0.7576662302017212,
|
| 953 |
+
"learning_rate": 0.0009535988867288315,
|
| 954 |
+
"loss": 5.119496765136719,
|
| 955 |
+
"step": 6750
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.13926150443384055,
|
| 959 |
+
"grad_norm": 0.6630811095237732,
|
| 960 |
+
"learning_rate": 0.0009529198518310193,
|
| 961 |
+
"loss": 5.148829345703125,
|
| 962 |
+
"step": 6800
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.14028548608408936,
|
| 966 |
+
"grad_norm": 0.5539138317108154,
|
| 967 |
+
"learning_rate": 0.0009522361298239649,
|
| 968 |
+
"loss": 5.130253295898438,
|
| 969 |
+
"step": 6850
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.1413094677343382,
|
| 973 |
+
"grad_norm": 0.7363731861114502,
|
| 974 |
+
"learning_rate": 0.0009515477277832683,
|
| 975 |
+
"loss": 5.123260498046875,
|
| 976 |
+
"step": 6900
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.14233344938458703,
|
| 980 |
+
"grad_norm": 0.6448495388031006,
|
| 981 |
+
"learning_rate": 0.0009508546528329613,
|
| 982 |
+
"loss": 5.115362854003906,
|
| 983 |
+
"step": 6950
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.14335743103483586,
|
| 987 |
+
"grad_norm": 0.7072167992591858,
|
| 988 |
+
"learning_rate": 0.0009501569121454348,
|
| 989 |
+
"loss": 5.12288818359375,
|
| 990 |
+
"step": 7000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.14438141268508467,
|
| 994 |
+
"grad_norm": 0.6230286955833435,
|
| 995 |
+
"learning_rate": 0.000949454512941363,
|
| 996 |
+
"loss": 5.113099365234375,
|
| 997 |
+
"step": 7050
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.1454053943353335,
|
| 1001 |
+
"grad_norm": 0.5957027077674866,
|
| 1002 |
+
"learning_rate": 0.0009487474624896297,
|
| 1003 |
+
"loss": 5.0959320068359375,
|
| 1004 |
+
"step": 7100
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.14642937598558234,
|
| 1008 |
+
"grad_norm": 0.6588881015777588,
|
| 1009 |
+
"learning_rate": 0.0009480357681072532,
|
| 1010 |
+
"loss": 5.100380859375,
|
| 1011 |
+
"step": 7150
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.14745335763583117,
|
| 1015 |
+
"grad_norm": 0.9760961532592773,
|
| 1016 |
+
"learning_rate": 0.0009473194371593097,
|
| 1017 |
+
"loss": 5.12734130859375,
|
| 1018 |
+
"step": 7200
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.14847733928608,
|
| 1022 |
+
"grad_norm": 0.6699064373970032,
|
| 1023 |
+
"learning_rate": 0.0009465984770588578,
|
| 1024 |
+
"loss": 5.093500366210938,
|
| 1025 |
+
"step": 7250
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.1495013209363288,
|
| 1029 |
+
"grad_norm": 0.6809692978858948,
|
| 1030 |
+
"learning_rate": 0.0009458728952668616,
|
| 1031 |
+
"loss": 5.11171630859375,
|
| 1032 |
+
"step": 7300
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.15052530258657765,
|
| 1036 |
+
"grad_norm": 0.686957061290741,
|
| 1037 |
+
"learning_rate": 0.0009451426992921135,
|
| 1038 |
+
"loss": 5.096458129882812,
|
| 1039 |
+
"step": 7350
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.15154928423682648,
|
| 1043 |
+
"grad_norm": 0.560275673866272,
|
| 1044 |
+
"learning_rate": 0.0009444078966911564,
|
| 1045 |
+
"loss": 5.110729370117188,
|
| 1046 |
+
"step": 7400
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.15257326588707532,
|
| 1050 |
+
"grad_norm": 0.651648998260498,
|
| 1051 |
+
"learning_rate": 0.0009436684950682058,
|
| 1052 |
+
"loss": 5.120025634765625,
|
| 1053 |
+
"step": 7450
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.15359724753732412,
|
| 1057 |
+
"grad_norm": 0.6866291761398315,
|
| 1058 |
+
"learning_rate": 0.0009429245020750703,
|
| 1059 |
+
"loss": 5.098842163085937,
|
| 1060 |
+
"step": 7500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.15462122918757296,
|
| 1064 |
+
"grad_norm": 0.513738214969635,
|
| 1065 |
+
"learning_rate": 0.0009421759254110736,
|
| 1066 |
+
"loss": 5.087961730957031,
|
| 1067 |
+
"step": 7550
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.1556452108378218,
|
| 1071 |
+
"grad_norm": 0.7265562415122986,
|
| 1072 |
+
"learning_rate": 0.0009414227728229737,
|
| 1073 |
+
"loss": 5.108470764160156,
|
| 1074 |
+
"step": 7600
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.15666919248807062,
|
| 1078 |
+
"grad_norm": 0.756854772567749,
|
| 1079 |
+
"learning_rate": 0.0009406650521048838,
|
| 1080 |
+
"loss": 5.114437866210937,
|
| 1081 |
+
"step": 7650
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.15769317413831943,
|
| 1085 |
+
"grad_norm": 0.6479256749153137,
|
| 1086 |
+
"learning_rate": 0.0009399027710981906,
|
| 1087 |
+
"loss": 5.109376525878906,
|
| 1088 |
+
"step": 7700
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.15871715578856826,
|
| 1092 |
+
"grad_norm": 0.5385767817497253,
|
| 1093 |
+
"learning_rate": 0.0009391359376914739,
|
| 1094 |
+
"loss": 5.101813049316406,
|
| 1095 |
+
"step": 7750
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.1597411374388171,
|
| 1099 |
+
"grad_norm": 0.6479353904724121,
|
| 1100 |
+
"learning_rate": 0.0009383645598204244,
|
| 1101 |
+
"loss": 5.090848999023438,
|
| 1102 |
+
"step": 7800
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.16076511908906593,
|
| 1106 |
+
"grad_norm": 1.1998552083969116,
|
| 1107 |
+
"learning_rate": 0.0009375886454677622,
|
| 1108 |
+
"loss": 5.098601684570313,
|
| 1109 |
+
"step": 7850
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.16178910073931474,
|
| 1113 |
+
"grad_norm": 0.5866249799728394,
|
| 1114 |
+
"learning_rate": 0.000936808202663154,
|
| 1115 |
+
"loss": 5.117637939453125,
|
| 1116 |
+
"step": 7900
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.16281308238956357,
|
| 1120 |
+
"grad_norm": 0.6267330050468445,
|
| 1121 |
+
"learning_rate": 0.0009360232394831292,
|
| 1122 |
+
"loss": 5.103722839355469,
|
| 1123 |
+
"step": 7950
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.1638370640398124,
|
| 1127 |
+
"grad_norm": 0.6675161719322205,
|
| 1128 |
+
"learning_rate": 0.0009352337640509974,
|
| 1129 |
+
"loss": 5.09795166015625,
|
| 1130 |
+
"step": 8000
|
| 1131 |
}
|
| 1132 |
],
|
| 1133 |
"logging_steps": 50,
|
|
|
|
| 1147 |
"attributes": {}
|
| 1148 |
}
|
| 1149 |
},
|
| 1150 |
+
"total_flos": 104262008832000.0,
|
| 1151 |
"train_batch_size": 16,
|
| 1152 |
"trial_name": null,
|
| 1153 |
"trial_params": null
|