Training in progress, step 120000
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 sha256:3c6fd9b355a0e1992610991a161343d23d4ff462cc3fcb6f8a31448b1c2375a2
|
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:f0e16b838fd7316c9c7a7392bf436c40c402518f2606e42e2993ec4865334552
|
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:d04071bd50c8ee493a8e62efb4f1ec18a47cebca0e90b017a310caaab5269ad7
|
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 sha256:14cf1d60ffd5a02986d01d3dffd29f5d1e5ecd11b19ecba44b2e67e765006270
|
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:f65c2278fa0afd9fc8e7e02777b9c1a886997704058cbcff31d2481acd673b5e
|
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 sha256:6b061b62ac3781b52f15d7ce095b2f330ca06ae5b50b54ec5e4a023b9c6e8b36
|
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 sha256:801cf09f8bef43d067c8cb4d5577fa9390122f24214dd6aef5a5f7d6410354b0
|
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 sha256:34d21e7407b27fb0fa7a5c7e6cc6c43957d6960c332159dc447194c7f8b52452
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1386,6 +1386,66 @@
|
|
1386 |
"learning_rate": 0.0001325211522476785,
|
1387 |
"loss": 0.3487,
|
1388 |
"step": 115000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1389 |
}
|
1390 |
],
|
1391 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0425528293376227,
|
5 |
+
"global_step": 120000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1386 |
"learning_rate": 0.0001325211522476785,
|
1387 |
"loss": 0.3487,
|
1388 |
"step": 115000
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 1.97,
|
1392 |
+
"learning_rate": 0.00013237551091401257,
|
1393 |
+
"loss": 0.349,
|
1394 |
+
"step": 115500
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 1.97,
|
1398 |
+
"learning_rate": 0.0001322299383160388,
|
1399 |
+
"loss": 0.3494,
|
1400 |
+
"step": 116000
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 1.98,
|
1404 |
+
"learning_rate": 0.0001320832666336504,
|
1405 |
+
"loss": 0.3493,
|
1406 |
+
"step": 116500
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 1.99,
|
1410 |
+
"learning_rate": 0.00013193637579394162,
|
1411 |
+
"loss": 0.3491,
|
1412 |
+
"step": 117000
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 2.0,
|
1416 |
+
"learning_rate": 0.00013178867850631044,
|
1417 |
+
"loss": 0.3497,
|
1418 |
+
"step": 117500
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 2.01,
|
1422 |
+
"learning_rate": 0.00013164047008533037,
|
1423 |
+
"loss": 0.3489,
|
1424 |
+
"step": 118000
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 2.02,
|
1428 |
+
"learning_rate": 0.00013149175199375862,
|
1429 |
+
"loss": 0.3489,
|
1430 |
+
"step": 118500
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 2.03,
|
1434 |
+
"learning_rate": 0.00013134252569938276,
|
1435 |
+
"loss": 0.3479,
|
1436 |
+
"step": 119000
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 2.03,
|
1440 |
+
"learning_rate": 0.0001311927926750061,
|
1441 |
+
"loss": 0.3482,
|
1442 |
+
"step": 119500
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 2.04,
|
1446 |
+
"learning_rate": 0.00013104255439843306,
|
1447 |
+
"loss": 0.3479,
|
1448 |
+
"step": 120000
|
1449 |
}
|
1450 |
],
|
1451 |
"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:f0e16b838fd7316c9c7a7392bf436c40c402518f2606e42e2993ec4865334552
|
3 |
size 201355195
|