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 +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +153 -3
- pytorch_model.bin +1 -1
- runs/Dec05_03-30-37_fbdce2302f52/events.out.tfevents.1670211053.fbdce2302f52.24.0 +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 sha256:70920a080f4832237ce7c6ba0b7f90a36204857a2597dfa2c6caf8d3a72f7e7f
|
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 sha256:3916aa768b3547ed097d45447da1e5f44df02e98af7f4c9081b40d19b99444c0
|
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 15523
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96d08c867edbcec7c00e24e146bf3d6892636f95bde24b387b90e00d4e61e819
|
3 |
size 15523
|
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:eab84ebacf80b8995a27a6b564c2dd8315f1d3f62ec0076da07f78d4762c61eb
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -914,11 +914,161 @@
|
|
914 |
"learning_rate": 8.225732450678378e-07,
|
915 |
"loss": 0.6941,
|
916 |
"step": 15000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
917 |
}
|
918 |
],
|
919 |
"max_steps": 30516,
|
920 |
"num_train_epochs": 2,
|
921 |
-
"total_flos":
|
922 |
"trial_name": null,
|
923 |
"trial_params": null
|
924 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.032265675691618,
|
5 |
+
"global_step": 17500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
914 |
"learning_rate": 8.225732450678378e-07,
|
915 |
"loss": 0.6941,
|
916 |
"step": 15000
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.89,
|
920 |
+
"learning_rate": 4.948548207380218e-07,
|
921 |
+
"loss": 0.7049,
|
922 |
+
"step": 15100
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.9,
|
926 |
+
"learning_rate": 1.6713639640820606e-07,
|
927 |
+
"loss": 0.6312,
|
928 |
+
"step": 15200
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.9,
|
932 |
+
"learning_rate": 0.0,
|
933 |
+
"loss": 0.6369,
|
934 |
+
"step": 15300
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.91,
|
938 |
+
"learning_rate": 0.0,
|
939 |
+
"loss": 0.6321,
|
940 |
+
"step": 15400
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.91,
|
944 |
+
"learning_rate": 0.0,
|
945 |
+
"loss": 0.7197,
|
946 |
+
"step": 15500
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 0.92,
|
950 |
+
"learning_rate": 0.0,
|
951 |
+
"loss": 0.6451,
|
952 |
+
"step": 15600
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 0.93,
|
956 |
+
"learning_rate": 0.0,
|
957 |
+
"loss": 0.6704,
|
958 |
+
"step": 15700
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 0.93,
|
962 |
+
"learning_rate": 0.0,
|
963 |
+
"loss": 0.6144,
|
964 |
+
"step": 15800
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 0.94,
|
968 |
+
"learning_rate": 0.0,
|
969 |
+
"loss": 0.6497,
|
970 |
+
"step": 15900
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.94,
|
974 |
+
"learning_rate": 0.0,
|
975 |
+
"loss": 0.7311,
|
976 |
+
"step": 16000
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.95,
|
980 |
+
"learning_rate": 0.0,
|
981 |
+
"loss": 0.6799,
|
982 |
+
"step": 16100
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.96,
|
986 |
+
"learning_rate": 0.0,
|
987 |
+
"loss": 0.6354,
|
988 |
+
"step": 16200
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 0.96,
|
992 |
+
"learning_rate": 0.0,
|
993 |
+
"loss": 0.6063,
|
994 |
+
"step": 16300
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 0.97,
|
998 |
+
"learning_rate": 0.0,
|
999 |
+
"loss": 0.6489,
|
1000 |
+
"step": 16400
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 0.97,
|
1004 |
+
"learning_rate": 0.0,
|
1005 |
+
"loss": 0.6334,
|
1006 |
+
"step": 16500
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 0.98,
|
1010 |
+
"learning_rate": 0.0,
|
1011 |
+
"loss": 0.689,
|
1012 |
+
"step": 16600
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 0.99,
|
1016 |
+
"learning_rate": 0.0,
|
1017 |
+
"loss": 0.6852,
|
1018 |
+
"step": 16700
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.99,
|
1022 |
+
"learning_rate": 0.0,
|
1023 |
+
"loss": 0.6481,
|
1024 |
+
"step": 16800
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 1.0,
|
1028 |
+
"learning_rate": 0.0,
|
1029 |
+
"loss": 0.7362,
|
1030 |
+
"step": 16900
|
1031 |
+
},
|
1032 |
+
{
|
1033 |
+
"epoch": 1.0,
|
1034 |
+
"learning_rate": 0.0,
|
1035 |
+
"loss": 0.7102,
|
1036 |
+
"step": 17000
|
1037 |
+
},
|
1038 |
+
{
|
1039 |
+
"epoch": 1.01,
|
1040 |
+
"learning_rate": 0.0,
|
1041 |
+
"loss": 0.6313,
|
1042 |
+
"step": 17100
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 1.01,
|
1046 |
+
"learning_rate": 0.0,
|
1047 |
+
"loss": 0.7327,
|
1048 |
+
"step": 17200
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 1.02,
|
1052 |
+
"learning_rate": 0.0,
|
1053 |
+
"loss": 0.624,
|
1054 |
+
"step": 17300
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 1.03,
|
1058 |
+
"learning_rate": 0.0,
|
1059 |
+
"loss": 0.6883,
|
1060 |
+
"step": 17400
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 1.03,
|
1064 |
+
"learning_rate": 0.0,
|
1065 |
+
"loss": 0.5119,
|
1066 |
+
"step": 17500
|
1067 |
}
|
1068 |
],
|
1069 |
"max_steps": 30516,
|
1070 |
"num_train_epochs": 2,
|
1071 |
+
"total_flos": 1.0676522063241216e+17,
|
1072 |
"trial_name": null,
|
1073 |
"trial_params": null
|
1074 |
}
|
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 sha256:3916aa768b3547ed097d45447da1e5f44df02e98af7f4c9081b40d19b99444c0
|
3 |
size 557969145
|
runs/Dec05_03-30-37_fbdce2302f52/events.out.tfevents.1670211053.fbdce2302f52.24.0
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 sha256:46d026c8117c697ed1221f4329f4a0e25d72fbf3cd5830657ac90bb96ef8f6fe
|
3 |
+
size 37185
|