Training in progress, step 621000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +39 -3
- pytorch_model.bin +1 -1
- runs/Jun02_06-43-44_462ae3634d0f/events.out.tfevents.1685689892.462ae3634d0f.537.0 +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 sha256:806be1299dc9f397b015bf45e4e9491d4765b5be56231fa086b220f80466e124
|
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 sha256:4467c2e695dbb515cc354d8e7385cc956efa20f7924c326db2a4ecdc2455acee
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce33c87ee60e5c5f09d3f93624e4aea152d072fa3e8cb2a51f34ae26cdbcf071
|
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:aef3ed6db2003a0d35336f0e4da89c5bcb53719a88d56afdb76ca509399bfcd3
|
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 sha256:4d821665fd46cc125e074beaa5297a592c3b1a69d3f8eda9777d00bef746240d
|
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": 16.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -7422,11 +7422,47 @@
|
|
7422 |
"learning_rate": 4.3366854581669033e-07,
|
7423 |
"loss": 1.0156,
|
7424 |
"step": 618000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7425 |
}
|
7426 |
],
|
7427 |
"max_steps": 762960,
|
7428 |
"num_train_epochs": 20,
|
7429 |
-
"total_flos": 7.
|
7430 |
"trial_name": null,
|
7431 |
"trial_params": null
|
7432 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 16.278690587285443,
|
5 |
+
"global_step": 621000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7422 |
"learning_rate": 4.3366854581669033e-07,
|
7423 |
"loss": 1.0156,
|
7424 |
"step": 618000
|
7425 |
+
},
|
7426 |
+
{
|
7427 |
+
"epoch": 16.21,
|
7428 |
+
"learning_rate": 4.307757117746536e-07,
|
7429 |
+
"loss": 1.0203,
|
7430 |
+
"step": 618500
|
7431 |
+
},
|
7432 |
+
{
|
7433 |
+
"epoch": 16.23,
|
7434 |
+
"learning_rate": 4.278974079867265e-07,
|
7435 |
+
"loss": 1.0212,
|
7436 |
+
"step": 619000
|
7437 |
+
},
|
7438 |
+
{
|
7439 |
+
"epoch": 16.24,
|
7440 |
+
"learning_rate": 4.2502211036962613e-07,
|
7441 |
+
"loss": 1.0281,
|
7442 |
+
"step": 619500
|
7443 |
+
},
|
7444 |
+
{
|
7445 |
+
"epoch": 16.25,
|
7446 |
+
"learning_rate": 4.2215560802978895e-07,
|
7447 |
+
"loss": 1.0204,
|
7448 |
+
"step": 620000
|
7449 |
+
},
|
7450 |
+
{
|
7451 |
+
"epoch": 16.27,
|
7452 |
+
"learning_rate": 4.1929791311755256e-07,
|
7453 |
+
"loss": 1.0117,
|
7454 |
+
"step": 620500
|
7455 |
+
},
|
7456 |
+
{
|
7457 |
+
"epoch": 16.28,
|
7458 |
+
"learning_rate": 4.1644903774592405e-07,
|
7459 |
+
"loss": 1.024,
|
7460 |
+
"step": 621000
|
7461 |
}
|
7462 |
],
|
7463 |
"max_steps": 762960,
|
7464 |
"num_train_epochs": 20,
|
7465 |
+
"total_flos": 7.400442013835674e+17,
|
7466 |
"trial_name": null,
|
7467 |
"trial_params": null
|
7468 |
}
|
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 sha256:4467c2e695dbb515cc354d8e7385cc956efa20f7924c326db2a4ecdc2455acee
|
3 |
size 1944201353
|
runs/Jun02_06-43-44_462ae3634d0f/events.out.tfevents.1685689892.462ae3634d0f.537.0
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 sha256:6bf0201424bc705d483ce8d79fd3c5ea059fa9c2831940cf15877da9e6a36860
|
3 |
+
size 10221
|