Training in progress, step 17500
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +153 -3
- pytorch_model.bin +1 -1
- runs/Jan03_01-47-25_21bb7eba274c/events.out.tfevents.1672710460.21bb7eba274c.23.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1115513717
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f389a14bfd58c27a83a27a7df40ecea82e8ea9846f9a754fe15ef3baf218cda
|
3 |
size 1115513717
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557969145
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ac15d1c531a2537f2ed5a5ca9b2c15212a32f681269a48c059475929253d03c
|
3 |
size 557969145
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d1f1f98d1a485fc2aa7583bef37396f966ba1263ca57a87f7bb243165c4d1d2
|
3 |
+
size 15459
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ddc9e3439f89ace0e8635bf051f23ef8d0f8b0f8a1af21d876b1c7c16844d24
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -906,11 +906,161 @@
|
|
906 |
"learning_rate": 3.2635774788241163e-06,
|
907 |
"loss": 0.625,
|
908 |
"step": 15000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
909 |
}
|
910 |
],
|
911 |
"max_steps": 32112,
|
912 |
"num_train_epochs": 2,
|
913 |
-
"total_flos":
|
914 |
"trial_name": null,
|
915 |
"trial_params": null
|
916 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9809417040358744,
|
5 |
+
"global_step": 17500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
906 |
"learning_rate": 3.2635774788241163e-06,
|
907 |
"loss": 0.625,
|
908 |
"step": 15000
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 0.85,
|
912 |
+
"learning_rate": 2.952167414050822e-06,
|
913 |
+
"loss": 0.8014,
|
914 |
+
"step": 15100
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.85,
|
918 |
+
"learning_rate": 2.6407573492775286e-06,
|
919 |
+
"loss": 0.7089,
|
920 |
+
"step": 15200
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.86,
|
924 |
+
"learning_rate": 2.329347284504235e-06,
|
925 |
+
"loss": 0.74,
|
926 |
+
"step": 15300
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.86,
|
930 |
+
"learning_rate": 2.0179372197309418e-06,
|
931 |
+
"loss": 0.7056,
|
932 |
+
"step": 15400
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 0.87,
|
936 |
+
"learning_rate": 1.7065271549576482e-06,
|
937 |
+
"loss": 0.7139,
|
938 |
+
"step": 15500
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.87,
|
942 |
+
"learning_rate": 1.395117090184355e-06,
|
943 |
+
"loss": 0.7094,
|
944 |
+
"step": 15600
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 0.88,
|
948 |
+
"learning_rate": 1.0837070254110613e-06,
|
949 |
+
"loss": 0.7352,
|
950 |
+
"step": 15700
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 0.89,
|
954 |
+
"learning_rate": 7.722969606377678e-07,
|
955 |
+
"loss": 0.6215,
|
956 |
+
"step": 15800
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.89,
|
960 |
+
"learning_rate": 4.608868958644744e-07,
|
961 |
+
"loss": 0.72,
|
962 |
+
"step": 15900
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.9,
|
966 |
+
"learning_rate": 1.4947683109118088e-07,
|
967 |
+
"loss": 0.844,
|
968 |
+
"step": 16000
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.9,
|
972 |
+
"learning_rate": 0.0,
|
973 |
+
"loss": 0.7329,
|
974 |
+
"step": 16100
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 0.91,
|
978 |
+
"learning_rate": 0.0,
|
979 |
+
"loss": 0.7173,
|
980 |
+
"step": 16200
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 0.91,
|
984 |
+
"learning_rate": 0.0,
|
985 |
+
"loss": 0.7362,
|
986 |
+
"step": 16300
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.92,
|
990 |
+
"learning_rate": 0.0,
|
991 |
+
"loss": 0.7832,
|
992 |
+
"step": 16400
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 0.92,
|
996 |
+
"learning_rate": 0.0,
|
997 |
+
"loss": 0.6208,
|
998 |
+
"step": 16500
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.93,
|
1002 |
+
"learning_rate": 0.0,
|
1003 |
+
"loss": 0.7005,
|
1004 |
+
"step": 16600
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.94,
|
1008 |
+
"learning_rate": 0.0,
|
1009 |
+
"loss": 0.6966,
|
1010 |
+
"step": 16700
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.94,
|
1014 |
+
"learning_rate": 0.0,
|
1015 |
+
"loss": 0.7328,
|
1016 |
+
"step": 16800
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 0.95,
|
1020 |
+
"learning_rate": 0.0,
|
1021 |
+
"loss": 0.7344,
|
1022 |
+
"step": 16900
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 0.95,
|
1026 |
+
"learning_rate": 0.0,
|
1027 |
+
"loss": 0.6683,
|
1028 |
+
"step": 17000
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.96,
|
1032 |
+
"learning_rate": 0.0,
|
1033 |
+
"loss": 0.7593,
|
1034 |
+
"step": 17100
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.96,
|
1038 |
+
"learning_rate": 0.0,
|
1039 |
+
"loss": 0.6735,
|
1040 |
+
"step": 17200
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.97,
|
1044 |
+
"learning_rate": 0.0,
|
1045 |
+
"loss": 0.6199,
|
1046 |
+
"step": 17300
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.98,
|
1050 |
+
"learning_rate": 0.0,
|
1051 |
+
"loss": 0.7717,
|
1052 |
+
"step": 17400
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.98,
|
1056 |
+
"learning_rate": 0.0,
|
1057 |
+
"loss": 0.7252,
|
1058 |
+
"step": 17500
|
1059 |
}
|
1060 |
],
|
1061 |
"max_steps": 32112,
|
1062 |
"num_train_epochs": 2,
|
1063 |
+
"total_flos": 8.078058692960256e+16,
|
1064 |
"trial_name": null,
|
1065 |
"trial_params": null
|
1066 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557969145
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ac15d1c531a2537f2ed5a5ca9b2c15212a32f681269a48c059475929253d03c
|
3 |
size 557969145
|
runs/Jan03_01-47-25_21bb7eba274c/events.out.tfevents.1672710460.21bb7eba274c.23.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0059104b5702024e249689bb568e96d0d4a72ee12fe8dd97c0dd035660f85968
|
3 |
+
size 37150
|