Training in progress, step 136000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +51 -3
- pytorch_model.bin +1 -1
- runs/May16_05-26-38_740b6dbf3e56/events.out.tfevents.1684216250.740b6dbf3e56.4449.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3871544599
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2f48d508ece7df760eb555c017887dbe66d0cba6c7cfec5e6d05c94a3f8988e
|
3 |
size 3871544599
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2a9024dd8a689e9ae503a3b92563cbd3856dd8ddb0b64a278d1035564872316
|
3 |
size 1944201353
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:586b3dca1089776e32d357296b4040f36f7c66e484c78b70291b9bf859f0da7d
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9be7d27f5adca25da92af93035570ac65d76bd8fd5301a951f17e1a456e8d376
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19bd67e3926298d10573f580a7616d969cad0d6d8378e7cf425b0e24b2dc768a
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1590,11 +1590,59 @@
|
|
1590 |
"learning_rate": 4.893511776430863e-06,
|
1591 |
"loss": 1.6672,
|
1592 |
"step": 132000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1593 |
}
|
1594 |
],
|
1595 |
"max_steps": 1415120,
|
1596 |
"num_train_epochs": 10,
|
1597 |
-
"total_flos":
|
1598 |
"trial_name": null,
|
1599 |
"trial_params": null
|
1600 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9610492396404545,
|
5 |
+
"global_step": 136000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1590 |
"learning_rate": 4.893511776430863e-06,
|
1591 |
"loss": 1.6672,
|
1592 |
"step": 132000
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 0.94,
|
1596 |
+
"learning_rate": 4.892709015746761e-06,
|
1597 |
+
"loss": 1.6937,
|
1598 |
+
"step": 132500
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.94,
|
1602 |
+
"learning_rate": 4.89190492131604e-06,
|
1603 |
+
"loss": 1.676,
|
1604 |
+
"step": 133000
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 0.94,
|
1608 |
+
"learning_rate": 4.891096271306403e-06,
|
1609 |
+
"loss": 1.6808,
|
1610 |
+
"step": 133500
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 0.95,
|
1614 |
+
"learning_rate": 4.890284675178114e-06,
|
1615 |
+
"loss": 1.6601,
|
1616 |
+
"step": 134000
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 0.95,
|
1620 |
+
"learning_rate": 4.8894701339311555e-06,
|
1621 |
+
"loss": 1.6762,
|
1622 |
+
"step": 134500
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 0.95,
|
1626 |
+
"learning_rate": 4.888654286477422e-06,
|
1627 |
+
"loss": 1.6826,
|
1628 |
+
"step": 135000
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 0.96,
|
1632 |
+
"learning_rate": 4.8878338638927996e-06,
|
1633 |
+
"loss": 1.649,
|
1634 |
+
"step": 135500
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 0.96,
|
1638 |
+
"learning_rate": 4.887010499209203e-06,
|
1639 |
+
"loss": 1.677,
|
1640 |
+
"step": 136000
|
1641 |
}
|
1642 |
],
|
1643 |
"max_steps": 1415120,
|
1644 |
"num_train_epochs": 10,
|
1645 |
+
"total_flos": 6.00884944380887e+16,
|
1646 |
"trial_name": null,
|
1647 |
"trial_params": null
|
1648 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2a9024dd8a689e9ae503a3b92563cbd3856dd8ddb0b64a278d1035564872316
|
3 |
size 1944201353
|
runs/May16_05-26-38_740b6dbf3e56/events.out.tfevents.1684216250.740b6dbf3e56.4449.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53a86a89599e9513699a13d646354a3c7e3196e861192b3d15d0bfb827290eb6
|
3 |
+
size 14703
|