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 sha256:0125fae33628261199324924a24f838fdbb7b540c7e6bcb62bff601a40d01eef
|
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:a503e0cdf4afe06fa0b5404fcc5fb7f21103be4724082a3d4c6dd290c86facea
|
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 sha256:2a24c5bc3512830da9cba3ca397cf514b0ae6fb60b88be6e65aae6a572a12053
|
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 sha256:39251726090e58caa7ef55a9fbb1ddc467df67351a23913a9eb1c3ebc7739b81
|
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 sha256:29ff30ec67c5b5ac1208a9979704e6e232e35dedcab4abced828a442950a7093
|
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 sha256:50eb839ce465b37b75f897e9233f1a1830375c8f405f9dbcc069d2f8400758cf
|
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 sha256:24e97fbc1b9328bf1c041a7d181cae3773cd724fd7f12ae937f7c5a533519e0f
|
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:d779281e0360c039c87535346b845f871006563229a89df72c8c0c5a1f47a3f3
|
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": 0.00012951302233048365,
|
1507 |
"loss": 0.3475,
|
1508 |
"step": 125000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1509 |
}
|
1510 |
],
|
1511 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.212764146688113,
|
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": 0.00012951302233048365,
|
1507 |
"loss": 0.3475,
|
1508 |
"step": 125000
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 2.14,
|
1512 |
+
"learning_rate": 0.00012935732620630798,
|
1513 |
+
"loss": 0.3473,
|
1514 |
+
"step": 125500
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 2.14,
|
1518 |
+
"learning_rate": 0.00012920145579691002,
|
1519 |
+
"loss": 0.3473,
|
1520 |
+
"step": 126000
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 2.15,
|
1524 |
+
"learning_rate": 0.00012904478791008278,
|
1525 |
+
"loss": 0.3476,
|
1526 |
+
"step": 126500
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 2.16,
|
1530 |
+
"learning_rate": 0.00012888763597099904,
|
1531 |
+
"loss": 0.3474,
|
1532 |
+
"step": 127000
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 2.17,
|
1536 |
+
"learning_rate": 0.000128730001530685,
|
1537 |
+
"loss": 0.3473,
|
1538 |
+
"step": 127500
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 2.18,
|
1542 |
+
"learning_rate": 0.00012857188614492896,
|
1543 |
+
"loss": 0.3471,
|
1544 |
+
"step": 128000
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 2.19,
|
1548 |
+
"learning_rate": 0.0001284136090411938,
|
1549 |
+
"loss": 0.3471,
|
1550 |
+
"step": 128500
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 2.2,
|
1554 |
+
"learning_rate": 0.00012825453740496415,
|
1555 |
+
"loss": 0.3467,
|
1556 |
+
"step": 129000
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 2.2,
|
1560 |
+
"learning_rate": 0.00012809498951593147,
|
1561 |
+
"loss": 0.3467,
|
1562 |
+
"step": 129500
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 2.21,
|
1566 |
+
"learning_rate": 0.000127934966948769,
|
1567 |
+
"loss": 0.3466,
|
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:a503e0cdf4afe06fa0b5404fcc5fb7f21103be4724082a3d4c6dd290c86facea
|
3 |
size 201355195
|