Training in progress, step 80000
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 sha256:47a6eb20fa5db1212a142ed952b33da36c38b1399764d8616f7e7b7fe81ccdfc
|
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 sha256:3953213e9173efface2259271c6df5ae3522f2c37a8bf53fe78820c4d4caae35
|
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 sha256:2ff236134280a08f32326a23ab233d3e49b41c02304ad8a7e5177b1c841d8789
|
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:f3e73079d7973e30b8179d372c26f2d6ec60be100ee7ea4bb85b88bc12e420c9
|
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:cc7ada0f43a3c328c9c7ec937be58de27c9e9a59fc7358b130b82e88fb9cf458
|
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 sha256:0bfbfe97276930c0b48cc0462761cca35cdc8f7792c5e02c87ab4e43a5212dc3
|
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:d750382fa1a25e2ca3c297de17b0a3f1b2f9743b1a5601c3d30eaaf271a7c337
|
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 sha256:0f321003648c79fc1f925ff85743abf01dcfe1007c95b3b1b5a3f5d886765821
|
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,
|
@@ -906,6 +906,66 @@
|
|
906 |
"learning_rate": 0.00014237584703282328,
|
907 |
"loss": 0.3557,
|
908 |
"step": 75000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
909 |
}
|
910 |
],
|
911 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.3617021276595744,
|
5 |
+
"global_step": 80000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
906 |
"learning_rate": 0.00014237584703282328,
|
907 |
"loss": 0.3557,
|
908 |
"step": 75000
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 1.29,
|
912 |
+
"learning_rate": 0.0001422757349017764,
|
913 |
+
"loss": 0.3554,
|
914 |
+
"step": 75500
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 1.29,
|
918 |
+
"learning_rate": 0.00014217500813436775,
|
919 |
+
"loss": 0.3554,
|
920 |
+
"step": 76000
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 1.3,
|
924 |
+
"learning_rate": 0.0001420736677247299,
|
925 |
+
"loss": 0.3551,
|
926 |
+
"step": 76500
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 1.31,
|
930 |
+
"learning_rate": 0.00014197191918990406,
|
931 |
+
"loss": 0.3551,
|
932 |
+
"step": 77000
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 1.32,
|
936 |
+
"learning_rate": 0.00014186935572468444,
|
937 |
+
"loss": 0.3547,
|
938 |
+
"step": 77500
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 1.33,
|
942 |
+
"learning_rate": 0.00014176618163390153,
|
943 |
+
"loss": 0.3545,
|
944 |
+
"step": 78000
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 1.34,
|
948 |
+
"learning_rate": 0.00014166239793584186,
|
949 |
+
"loss": 0.3548,
|
950 |
+
"step": 78500
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 1.34,
|
954 |
+
"learning_rate": 0.0001415580056548087,
|
955 |
+
"loss": 0.3546,
|
956 |
+
"step": 79000
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 1.35,
|
960 |
+
"learning_rate": 0.00014145321642642885,
|
961 |
+
"loss": 0.3544,
|
962 |
+
"step": 79500
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 1.36,
|
966 |
+
"learning_rate": 0.00014134782310325824,
|
967 |
+
"loss": 0.3545,
|
968 |
+
"step": 80000
|
969 |
}
|
970 |
],
|
971 |
"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 sha256:3953213e9173efface2259271c6df5ae3522f2c37a8bf53fe78820c4d4caae35
|
3 |
size 201355195
|