Training in progress, step 110000
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 sha256:899c5ba5cbd3aff242d9f786cf6db2b9166f22f05cfa7c167959ec2c4e7a0c95
|
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 sha256:26c2965e27dc9f7f07f8c74b91e970a98ba98f322e9d56f9832b76c22bfa9820
|
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:cb9870672cac38aeccce618b5e6eff6d62fdc9756ea6adffd0a43be4e2f1eed4
|
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 sha256:7bb7dbae5864ea164e0bf14a98a3a6aeacc7239f2a411504824e2b58b0a83dd2
|
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 sha256:2a4aa193514380574b62c500436c00fb71391ff454cf08ade5ade2ddd786a474
|
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 sha256:35a055118bc8fad25dc395b9d6525b760671904441bdd88ae86f46e521d5d9d0
|
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:a58cc7c4378f55401187646c56ccb483dba5cd3ed96098739e6a9940706ddedb
|
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:a651111659a74286a8024267f35d853681d66f9821a35280fcf83de3c206da34
|
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,
|
@@ -1266,6 +1266,66 @@
|
|
1266 |
"learning_rate": 0.00013532324880356615,
|
1267 |
"loss": 0.3507,
|
1268 |
"step": 105000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1269 |
}
|
1270 |
],
|
1271 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.8723330014212645,
|
5 |
+
"global_step": 110000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1266 |
"learning_rate": 0.00013532324880356615,
|
1267 |
"loss": 0.3507,
|
1268 |
"step": 105000
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 1.8,
|
1272 |
+
"learning_rate": 0.0001351882409434157,
|
1273 |
+
"loss": 0.3504,
|
1274 |
+
"step": 105500
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 1.8,
|
1278 |
+
"learning_rate": 0.00013505268839760753,
|
1279 |
+
"loss": 0.3501,
|
1280 |
+
"step": 106000
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 1.81,
|
1284 |
+
"learning_rate": 0.00013491659250399054,
|
1285 |
+
"loss": 0.3503,
|
1286 |
+
"step": 106500
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 1.82,
|
1290 |
+
"learning_rate": 0.00013477995460577628,
|
1291 |
+
"loss": 0.3505,
|
1292 |
+
"step": 107000
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 1.83,
|
1296 |
+
"learning_rate": 0.00013464277605152562,
|
1297 |
+
"loss": 0.3502,
|
1298 |
+
"step": 107500
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 1.84,
|
1302 |
+
"learning_rate": 0.0001345050581951355,
|
1303 |
+
"loss": 0.3503,
|
1304 |
+
"step": 108000
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 1.85,
|
1308 |
+
"learning_rate": 0.00013436680239582559,
|
1309 |
+
"loss": 0.35,
|
1310 |
+
"step": 108500
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 1.86,
|
1314 |
+
"learning_rate": 0.00013422801001812477,
|
1315 |
+
"loss": 0.3506,
|
1316 |
+
"step": 109000
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 1.86,
|
1320 |
+
"learning_rate": 0.00013408868243185783,
|
1321 |
+
"loss": 0.3504,
|
1322 |
+
"step": 109500
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 1.87,
|
1326 |
+
"learning_rate": 0.00013394882101213176,
|
1327 |
+
"loss": 0.3497,
|
1328 |
+
"step": 110000
|
1329 |
}
|
1330 |
],
|
1331 |
"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 sha256:26c2965e27dc9f7f07f8c74b91e970a98ba98f322e9d56f9832b76c22bfa9820
|
3 |
size 201355195
|