Commit
•
b30d1b7
1
Parent(s):
aa67652
Training in progress, step 6012
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 +9 -3
- pytorch_model.bin +1 -1
- runs/Jun03_18-44-11_bb544bc9a418/events.out.tfevents.1685817877.bb544bc9a418.167.4 +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 6319689
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d36bec87e133299bf06a2de01115a95f6704969e864625d2a3645081c83181e9
|
3 |
size 6319689
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1121737121
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19d118b64c2ed4e3c9d552b6ce440479989ebf1cf97152bebf33768cce74110a
|
3 |
size 1121737121
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ab40fee09963eda338d12e747f08ae95d8c60239b13bda5252fb46b0fd31856
|
3 |
size 14639
|
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:b00a7b8f259c1a03fd8357cfbf7a99e86f8e8743033407c5af8d7cbd79ec3de1
|
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 sha256:2e1a1b30192fbfe833caaccec63966294961a0228011293ae50846c9421f40d1
|
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,
|
@@ -48,11 +48,17 @@
|
|
48 |
"learning_rate": 1.8843237360932635e-05,
|
49 |
"loss": 1.603,
|
50 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
}
|
52 |
],
|
53 |
"max_steps": 86379,
|
54 |
"num_train_epochs": 1,
|
55 |
-
"total_flos":
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.06960025006077866,
|
5 |
+
"global_step": 6012,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
48 |
"learning_rate": 1.8843237360932635e-05,
|
49 |
"loss": 1.603,
|
50 |
"step": 5000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.07,
|
54 |
+
"learning_rate": 1.8611699602912747e-05,
|
55 |
+
"loss": 1.5877,
|
56 |
+
"step": 6000
|
57 |
}
|
58 |
],
|
59 |
"max_steps": 86379,
|
60 |
"num_train_epochs": 1,
|
61 |
+
"total_flos": 1.1195821810778112e+16,
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1121737121
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19d118b64c2ed4e3c9d552b6ce440479989ebf1cf97152bebf33768cce74110a
|
3 |
size 1121737121
|
runs/Jun03_18-44-11_bb544bc9a418/events.out.tfevents.1685817877.bb544bc9a418.167.4
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:cdec86a48022656d252f801817eee250dd7f5cd327595c1d2c1bfa0184692885
|
3 |
+
size 5131
|