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 sha256:740df9904223b962174f4e91ff0afa57cfe1097a467cce9c8782ed26466fc7ec
|
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 sha256:827d673d56f251aaa2346c1e0f1c4e6c28b1d969fa17606a94b7895558120017
|
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:fd82d33f7cb064bef83b890cfa1d1c55aad7a13f1dc845a226270e4976b18dd3
|
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:c49b5ebc44c117e805046ae9d6210c1c55a4fe3fe7283e9e44477ea89bc4d635
|
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:f27e9a67b2517c3e1bea7ffae2e191e434a73c922930b0ce4e985b99d925d6dc
|
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 sha256:03c54fb70bfb6e96af25ce04f81dd618fa7b81ed167e7c858f613f0e4a7efbe3
|
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 sha256:79db1af5de353c3fa097eee6c84b7ce443e15764a9af1536c6243026933cf1fa
|
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 sha256:8754c1fe7bb01622671683307fb7fbf395a57411685a73cf91fe7cbce8c44fd5
|
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": 0.00014025888127864108,
|
1027 |
"loss": 0.3531,
|
1028 |
"step": 85000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1029 |
}
|
1030 |
],
|
1031 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.5319148936170213,
|
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": 0.00014025888127864108,
|
1027 |
"loss": 0.3531,
|
1028 |
"step": 85000
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 1.46,
|
1032 |
+
"learning_rate": 0.00014014667691447777,
|
1033 |
+
"loss": 0.3532,
|
1034 |
+
"step": 85500
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 1.46,
|
1038 |
+
"learning_rate": 0.00014003387892689548,
|
1039 |
+
"loss": 0.3529,
|
1040 |
+
"step": 86000
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 1.47,
|
1044 |
+
"learning_rate": 0.00013992048842916485,
|
1045 |
+
"loss": 0.3529,
|
1046 |
+
"step": 86500
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 1.48,
|
1050 |
+
"learning_rate": 0.00013980673509364334,
|
1051 |
+
"loss": 0.3525,
|
1052 |
+
"step": 87000
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 1.49,
|
1056 |
+
"learning_rate": 0.00013969216411821367,
|
1057 |
+
"loss": 0.3526,
|
1058 |
+
"step": 87500
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 1.5,
|
1062 |
+
"learning_rate": 0.00013957700400522283,
|
1063 |
+
"loss": 0.3528,
|
1064 |
+
"step": 88000
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 1.51,
|
1068 |
+
"learning_rate": 0.0001394612558912547,
|
1069 |
+
"loss": 0.3523,
|
1070 |
+
"step": 88500
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 1.51,
|
1074 |
+
"learning_rate": 0.00013934515417356422,
|
1075 |
+
"loss": 0.3525,
|
1076 |
+
"step": 89000
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 1.52,
|
1080 |
+
"learning_rate": 0.00013922823466086605,
|
1081 |
+
"loss": 0.3521,
|
1082 |
+
"step": 89500
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 1.53,
|
1086 |
+
"learning_rate": 0.0001391107305894032,
|
1087 |
+
"loss": 0.352,
|
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 sha256:827d673d56f251aaa2346c1e0f1c4e6c28b1d969fa17606a94b7895558120017
|
3 |
size 201355195
|