Training in progress, step 90000
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 sha256:7ec6dc111e6167617249a4034f667ff8c1dac4e0508b2d117f87c2a48b53f992
|
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:fd1a954286945255af2c2f6a9caa52188dcc39909af1998372c65c068243f847
|
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:fd75299155a785e038cc2034bc0ffae9f55e960c94bd0d7eeb1f0123fe91a7b9
|
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 sha256:1a9f62023cae76e82d48aee2a952f4c6d76c642cc4db4f90dd6af1d183efff25
|
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 sha256:6fb5901ddeb1cfbe18f3314a87d55dbe2efa71565718ac2ab36838d79b0ca129
|
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 sha256:143c38b79821877e7c44d516c39a7e7355c53315c2e2279c91582047957f2c7c
|
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 sha256:03c7bc8447e7ec329f5ebcdbdba23f6503dd9b1599722a7f3d541e97e65b905e
|
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 sha256:88745b2213b88b884ae47af09195b94e85097099ce2e5b5e82db98c713a418d9
|
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,
|
@@ -1026,6 +1026,66 @@
|
|
1026 |
"learning_rate": 0.00014025955271103284,
|
1027 |
"loss": 0.3529,
|
1028 |
"step": 85000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1029 |
}
|
1030 |
],
|
1031 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.5319103667202834,
|
5 |
+
"global_step": 90000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1026 |
"learning_rate": 0.00014025955271103284,
|
1027 |
"loss": 0.3529,
|
1028 |
"step": 85000
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 1.46,
|
1032 |
+
"learning_rate": 0.00014014735191195807,
|
1033 |
+
"loss": 0.3528,
|
1034 |
+
"step": 85500
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 1.46,
|
1038 |
+
"learning_rate": 0.00014003478366336457,
|
1039 |
+
"loss": 0.3527,
|
1040 |
+
"step": 86000
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 1.47,
|
1044 |
+
"learning_rate": 0.00013992253468820287,
|
1045 |
+
"loss": 0.3559,
|
1046 |
+
"step": 86500
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 1.48,
|
1050 |
+
"learning_rate": 0.00013980856343455598,
|
1051 |
+
"loss": 0.3566,
|
1052 |
+
"step": 87000
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 1.49,
|
1056 |
+
"learning_rate": 0.0001396940018945337,
|
1057 |
+
"loss": 0.3554,
|
1058 |
+
"step": 87500
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 1.5,
|
1062 |
+
"learning_rate": 0.00013957885119881218,
|
1063 |
+
"loss": 0.3552,
|
1064 |
+
"step": 88000
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 1.51,
|
1068 |
+
"learning_rate": 0.00013946311248388228,
|
1069 |
+
"loss": 0.3548,
|
1070 |
+
"step": 88500
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 1.51,
|
1074 |
+
"learning_rate": 0.00013934678689203836,
|
1075 |
+
"loss": 0.3547,
|
1076 |
+
"step": 89000
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 1.52,
|
1080 |
+
"learning_rate": 0.0001392298755713671,
|
1081 |
+
"loss": 0.3547,
|
1082 |
+
"step": 89500
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 1.53,
|
1086 |
+
"learning_rate": 0.00013911237967573605,
|
1087 |
+
"loss": 0.3541,
|
1088 |
+
"step": 90000
|
1089 |
}
|
1090 |
],
|
1091 |
"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:fd1a954286945255af2c2f6a9caa52188dcc39909af1998372c65c068243f847
|
3 |
size 201355195
|