Training in progress, step 627000
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 +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 sha256:30cd8050cb6404088c5716079148dd0da70144e4be8ff9a3d8b384acf70755c2
|
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 sha256:05ee9a7da46e1a224189b23b0c2c4d8a9bfe97d804c74a078fe32f5d0875aad1
|
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 sha256:76cbb628e04923671f85d7d99e49cf45496fe34ffb57a5111e03658d124a7d16
|
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 sha256:6143b27eaf96690bbe891751f24c600c4892dab7823d8c13fb59f1cc963b65c0
|
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 sha256:58e6a28fc1607a90c71dc0e11a421f4fc6f6121d48134da179bd1cba7f5481db
|
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,
|
@@ -7494,11 +7494,47 @@
|
|
7494 |
"learning_rate": 3.995472520106156e-07,
|
7495 |
"loss": 1.0092,
|
7496 |
"step": 624000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7497 |
}
|
7498 |
],
|
7499 |
"max_steps": 762960,
|
7500 |
"num_train_epochs": 20,
|
7501 |
-
"total_flos": 7.
|
7502 |
"trial_name": null,
|
7503 |
"trial_params": null
|
7504 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 16.435971102326704,
|
5 |
+
"global_step": 627000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7494 |
"learning_rate": 3.995472520106156e-07,
|
7495 |
"loss": 1.0092,
|
7496 |
"step": 624000
|
7497 |
+
},
|
7498 |
+
{
|
7499 |
+
"epoch": 16.37,
|
7500 |
+
"learning_rate": 3.9676599636984005e-07,
|
7501 |
+
"loss": 1.0272,
|
7502 |
+
"step": 624500
|
7503 |
+
},
|
7504 |
+
{
|
7505 |
+
"epoch": 16.38,
|
7506 |
+
"learning_rate": 3.939880732106663e-07,
|
7507 |
+
"loss": 1.029,
|
7508 |
+
"step": 625000
|
7509 |
+
},
|
7510 |
+
{
|
7511 |
+
"epoch": 16.4,
|
7512 |
+
"learning_rate": 3.9121907687375336e-07,
|
7513 |
+
"loss": 1.0189,
|
7514 |
+
"step": 625500
|
7515 |
+
},
|
7516 |
+
{
|
7517 |
+
"epoch": 16.41,
|
7518 |
+
"learning_rate": 3.884645302832277e-07,
|
7519 |
+
"loss": 1.0061,
|
7520 |
+
"step": 626000
|
7521 |
+
},
|
7522 |
+
{
|
7523 |
+
"epoch": 16.42,
|
7524 |
+
"learning_rate": 3.857134048518893e-07,
|
7525 |
+
"loss": 1.0061,
|
7526 |
+
"step": 626500
|
7527 |
+
},
|
7528 |
+
{
|
7529 |
+
"epoch": 16.44,
|
7530 |
+
"learning_rate": 3.8297124131692177e-07,
|
7531 |
+
"loss": 1.0129,
|
7532 |
+
"step": 627000
|
7533 |
}
|
7534 |
],
|
7535 |
"max_steps": 762960,
|
7536 |
"num_train_epochs": 20,
|
7537 |
+
"total_flos": 7.466521265780244e+17,
|
7538 |
"trial_name": null,
|
7539 |
"trial_params": null
|
7540 |
}
|
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 sha256:05ee9a7da46e1a224189b23b0c2c4d8a9bfe97d804c74a078fe32f5d0875aad1
|
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 sha256:66ce0e077eb7226d21856c3aa901ae59cffa1521766d1b609f24e1c4b48cd004
|
3 |
+
size 12141
|