Training in progress, step 85000
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/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0d344d9b79f704248c95f3fa8652a156ea62b33f60692d8d4b71ecf3d5358b1
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f05b62e4eb23834754aec3fe5902b4aece37bd95fd2dbb32c63e7a6311478a76
|
3 |
size 201355195
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6acd59d1802a584e8ad9e5d66dd0e1ea0bba8b3c65f21d2d1063acfd58623864
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11d90f1e0216fcdb615d50b50ceceaef250225eda00651593c2c6bac1fb5b7e5
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0adaef0a10327c5c1b663b2940a505b8b30455a2296ac7a9ec600ded77f47ca7
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5498bf9f7a6ee2aca1727faaa786cbe5ae5f000a23a8d13a73d59f68491578f2
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90e9fa6e58fb0dc4cb9a414dd41c920ab8f0c1ab2dc0cc194c3ce05ab3818d98
|
3 |
size 559
|
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 sha256:23b00d690352c4e19af274781a0e224e3486bf62ebcd43fefdef22aa01a31e8c
|
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": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -966,6 +966,66 @@
|
|
966 |
"learning_rate": 0.00014134782310325824,
|
967 |
"loss": 0.3545,
|
968 |
"step": 80000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
969 |
}
|
970 |
],
|
971 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.4468085106382977,
|
5 |
+
"global_step": 85000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
966 |
"learning_rate": 0.00014134782310325824,
|
967 |
"loss": 0.3545,
|
968 |
"step": 80000
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 1.37,
|
972 |
+
"learning_rate": 0.0001412418267213298,
|
973 |
+
"loss": 0.3547,
|
974 |
+
"step": 80500
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 1.38,
|
978 |
+
"learning_rate": 0.0001411350140948281,
|
979 |
+
"loss": 0.3547,
|
980 |
+
"step": 81000
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 1.39,
|
984 |
+
"learning_rate": 0.0001410275980904185,
|
985 |
+
"loss": 0.354,
|
986 |
+
"step": 81500
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 1.4,
|
990 |
+
"learning_rate": 0.0001409195797682536,
|
991 |
+
"loss": 0.3539,
|
992 |
+
"step": 82000
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 1.4,
|
996 |
+
"learning_rate": 0.00014081096019443061,
|
997 |
+
"loss": 0.3538,
|
998 |
+
"step": 82500
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 1.41,
|
1002 |
+
"learning_rate": 0.00014070174044098087,
|
1003 |
+
"loss": 0.3537,
|
1004 |
+
"step": 83000
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 1.42,
|
1008 |
+
"learning_rate": 0.00014059192158585924,
|
1009 |
+
"loss": 0.3534,
|
1010 |
+
"step": 83500
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 1.43,
|
1014 |
+
"learning_rate": 0.00014048150471293355,
|
1015 |
+
"loss": 0.3539,
|
1016 |
+
"step": 84000
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 1.44,
|
1020 |
+
"learning_rate": 0.00014037049091197368,
|
1021 |
+
"loss": 0.3532,
|
1022 |
+
"step": 84500
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 1.45,
|
1026 |
+
"learning_rate": 0.00014025888127864108,
|
1027 |
+
"loss": 0.3531,
|
1028 |
+
"step": 85000
|
1029 |
}
|
1030 |
],
|
1031 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f05b62e4eb23834754aec3fe5902b4aece37bd95fd2dbb32c63e7a6311478a76
|
3 |
size 201355195
|