Training in progress, step 130000
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:f690f84228c1cf7c536edbf2267bc0cdfd0f89ce3c54b91efac1cb60aa94cad0
|
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 sha256:9ec2a9e31c576538f128ada4a29cf915346ae2568cbf6b58a244e46c6f147e84
|
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 sha256:5eb0ca6b4aedddaec2485b3f9da640a30b0d0c4a6748d79ba9759fcf1059aafe
|
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:ee3ef0876874dbc2e513a558038a6c2a16a643066aa73749397a26d9e6da45a3
|
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 sha256:7d6c5f43829cf907e0e5f04a8918256c0a34c747002f9f1dcacccf8010756aff
|
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 sha256:393742d5819ac3df5ee9648fcf8701d7dbb1400b0807804e7126483e0b53ae3a
|
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:b1908f20d92a8293a342e348b5b074ab1cd3d720accabd7a844bf778768c4405
|
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 sha256:9cba00ab4119ca26f6b23d0c7741da241151231837b95816f094795ad39dadf1
|
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": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1506,6 +1506,66 @@
|
|
1506 |
"learning_rate": 0.0001295124005184018,
|
1507 |
"loss": 0.3442,
|
1508 |
"step": 125000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1509 |
}
|
1510 |
],
|
1511 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.2127659574468086,
|
5 |
+
"global_step": 130000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1506 |
"learning_rate": 0.0001295124005184018,
|
1507 |
"loss": 0.3442,
|
1508 |
"step": 125000
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 2.14,
|
1512 |
+
"learning_rate": 0.0001293567024426144,
|
1513 |
+
"loss": 0.344,
|
1514 |
+
"step": 125500
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 2.14,
|
1518 |
+
"learning_rate": 0.00012920051723609998,
|
1519 |
+
"loss": 0.3439,
|
1520 |
+
"step": 126000
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 2.15,
|
1524 |
+
"learning_rate": 0.0001290438464403435,
|
1525 |
+
"loss": 0.344,
|
1526 |
+
"step": 126500
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 2.16,
|
1530 |
+
"learning_rate": 0.00012888700639334465,
|
1531 |
+
"loss": 0.3434,
|
1532 |
+
"step": 127000
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 2.17,
|
1536 |
+
"learning_rate": 0.00012872937002614656,
|
1537 |
+
"loss": 0.3437,
|
1538 |
+
"step": 127500
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 2.18,
|
1542 |
+
"learning_rate": 0.00012857125271973914,
|
1543 |
+
"loss": 0.3436,
|
1544 |
+
"step": 128000
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 2.19,
|
1548 |
+
"learning_rate": 0.00012841265603467637,
|
1549 |
+
"loss": 0.3433,
|
1550 |
+
"step": 128500
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 2.2,
|
1554 |
+
"learning_rate": 0.00012825358153624352,
|
1555 |
+
"loss": 0.3432,
|
1556 |
+
"step": 129000
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 2.2,
|
1560 |
+
"learning_rate": 0.0001280943503701703,
|
1561 |
+
"loss": 0.3432,
|
1562 |
+
"step": 129500
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 2.21,
|
1566 |
+
"learning_rate": 0.00012793432590746354,
|
1567 |
+
"loss": 0.3432,
|
1568 |
+
"step": 130000
|
1569 |
}
|
1570 |
],
|
1571 |
"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 sha256:9ec2a9e31c576538f128ada4a29cf915346ae2568cbf6b58a244e46c6f147e84
|
3 |
size 201355195
|