Training in progress, step 105000
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 sha256:48c174a6569e6ca59c20c6331485b1820a26010c89b97db9cee6c46a48618b30
|
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:dd1ad69cc709597d223f156d81a5f8943f311d2f91441a889c4d2e646ff34516
|
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:e0443217dfef07dd5c04074b68687083023d20032d9353f4a3273f8b828ba239
|
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 sha256:504731a1baf2cdb2201c6dea74d0d2f14c71a47654a3cd42a0affe434676d5ac
|
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 sha256:35368ffd36be1d2f5483520e51fff9a2331196300fcf74cf599874a51a714c50
|
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 sha256:89b062449922429fc77be531d8d39e0ca14c8760c57869e66cbb2cd9cabb1c18
|
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 sha256:6f9268bbb891cb8c58064617fc108f9131c7c8ed362ad4bb75b8e6cbd2d62457
|
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 sha256:39ba0f8c5461187c3b8706393ea80ec7feeb9cc910f1e06ed81d44de45f63cad
|
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,
|
@@ -1206,6 +1206,66 @@
|
|
1206 |
"learning_rate": 0.00013664178710672204,
|
1207 |
"loss": 0.3517,
|
1208 |
"step": 100000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1209 |
}
|
1210 |
],
|
1211 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.7872273427460192,
|
5 |
+
"global_step": 105000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1206 |
"learning_rate": 0.00013664178710672204,
|
1207 |
"loss": 0.3517,
|
1208 |
"step": 100000
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 1.71,
|
1212 |
+
"learning_rate": 0.00013651229291169033,
|
1213 |
+
"loss": 0.3516,
|
1214 |
+
"step": 100500
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 1.72,
|
1218 |
+
"learning_rate": 0.00013638250162282539,
|
1219 |
+
"loss": 0.3516,
|
1220 |
+
"step": 101000
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 1.73,
|
1224 |
+
"learning_rate": 0.00013625189431597695,
|
1225 |
+
"loss": 0.3515,
|
1226 |
+
"step": 101500
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 1.74,
|
1230 |
+
"learning_rate": 0.00013612073182564145,
|
1231 |
+
"loss": 0.3512,
|
1232 |
+
"step": 102000
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 1.74,
|
1236 |
+
"learning_rate": 0.00013599007137178395,
|
1237 |
+
"loss": 0.3527,
|
1238 |
+
"step": 102500
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 1.75,
|
1242 |
+
"learning_rate": 0.0001358578068190425,
|
1243 |
+
"loss": 0.352,
|
1244 |
+
"step": 103000
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 1.76,
|
1248 |
+
"learning_rate": 0.00013572499097229843,
|
1249 |
+
"loss": 0.3512,
|
1250 |
+
"step": 103500
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 1.77,
|
1254 |
+
"learning_rate": 0.00013559162514239058,
|
1255 |
+
"loss": 0.3509,
|
1256 |
+
"step": 104000
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 1.78,
|
1260 |
+
"learning_rate": 0.0001354577106455858,
|
1261 |
+
"loss": 0.3504,
|
1262 |
+
"step": 104500
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 1.79,
|
1266 |
+
"learning_rate": 0.00013532324880356615,
|
1267 |
+
"loss": 0.3507,
|
1268 |
+
"step": 105000
|
1269 |
}
|
1270 |
],
|
1271 |
"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:dd1ad69cc709597d223f156d81a5f8943f311d2f91441a889c4d2e646ff34516
|
3 |
size 201355195
|