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:e51fe3d77cc9e74a03015a679bf9c6e5b20948a91fec3a0a678f7ab3d632266b
|
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:c035316a6d8fc5afe7f4bf5263646f9d28003e5dc92f6d7d8ca0dfcd6793a547
|
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 sha256:366fcf2af7e77643d8ba291b8a66dfb537d4ef759595fd9e7a945bd15b02507a
|
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:d3ec4b721b64709a3029a0a2cb04e18d166896dfa34d7fdfc8143f8d8565fa60
|
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 sha256:4fb92796b14e92fd63e400d0d94dcf933348fe7696852142cff135a6ac92eff3
|
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 sha256:58ff7b8548b63f48264cef8154875e50044ff9178a1ba8dad705f9e679474825
|
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 sha256:42b6574b57c2570000c9af4e77bbf53b450e6d4b62d98188361ee6a5f2aaa995
|
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 sha256:345b6e5a884c94f439eac86a159284d4991183aeed3398174ad1ad011c4a43d7
|
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": 0.00014134803491572606,
|
967 |
"loss": 0.3542,
|
968 |
"step": 80000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
969 |
}
|
970 |
],
|
971 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.446804708045038,
|
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": 0.00014134803491572606,
|
967 |
"loss": 0.3542,
|
968 |
"step": 80000
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 1.37,
|
972 |
+
"learning_rate": 0.00014124203974129223,
|
973 |
+
"loss": 0.3539,
|
974 |
+
"step": 80500
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 1.38,
|
978 |
+
"learning_rate": 0.00014113522832260466,
|
979 |
+
"loss": 0.3541,
|
980 |
+
"step": 81000
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 1.39,
|
984 |
+
"learning_rate": 0.00014102781352389485,
|
985 |
+
"loss": 0.3537,
|
986 |
+
"step": 81500
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 1.4,
|
990 |
+
"learning_rate": 0.00014091979640530345,
|
991 |
+
"loss": 0.3535,
|
992 |
+
"step": 82000
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 1.4,
|
996 |
+
"learning_rate": 0.00014081139586900036,
|
997 |
+
"loss": 0.3533,
|
998 |
+
"step": 82500
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 1.41,
|
1002 |
+
"learning_rate": 0.0001407021785141258,
|
1003 |
+
"loss": 0.3535,
|
1004 |
+
"step": 83000
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 1.42,
|
1008 |
+
"learning_rate": 0.00014059236205325574,
|
1009 |
+
"loss": 0.3536,
|
1010 |
+
"step": 83500
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 1.43,
|
1014 |
+
"learning_rate": 0.00014048194757023435,
|
1015 |
+
"loss": 0.353,
|
1016 |
+
"step": 84000
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 1.44,
|
1020 |
+
"learning_rate": 0.00014037115877265014,
|
1021 |
+
"loss": 0.353,
|
1022 |
+
"step": 84500
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 1.45,
|
1026 |
+
"learning_rate": 0.00014025955271103284,
|
1027 |
+
"loss": 0.3529,
|
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:c035316a6d8fc5afe7f4bf5263646f9d28003e5dc92f6d7d8ca0dfcd6793a547
|
3 |
size 201355195
|