Commit
•
41e154b
1
Parent(s):
ad88bbf
Training in progress, step 11022
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/Jun04_02-06-39_4367d7224c9f/events.out.tfevents.1685845095.4367d7224c9f.857.0 +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 6319689
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25428f46455f1fd06035695d3c658ede8a9f536835ba3323007f5a290a232333
|
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:f1abc19bf3a6b17b6c52f668a4484117af425b853bca8d40a0fe9bae0c5dd31d
|
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:da3aa24e748f9c7657710b0aa0586814e789fa2de1a50753f5d10a7797332557
|
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 sha256:9980c6ca8f2ae30bfe1a454ad1f29053c44e5b48c830b261146a97e01acbc299
|
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:b4a13c5d0a3a755a3d13c01c4ff6385d7ade7690614b070245b50ae328a7aadf
|
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,
|
@@ -78,11 +78,17 @@
|
|
78 |
"learning_rate": 1.768624318410725e-05,
|
79 |
"loss": 1.5727,
|
80 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
}
|
82 |
],
|
83 |
"max_steps": 86379,
|
84 |
"num_train_epochs": 1,
|
85 |
-
"total_flos":
|
86 |
"trial_name": null,
|
87 |
"trial_params": null
|
88 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.12760045844476087,
|
5 |
+
"global_step": 11022,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
78 |
"learning_rate": 1.768624318410725e-05,
|
79 |
"loss": 1.5727,
|
80 |
"step": 10000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.13,
|
84 |
+
"learning_rate": 1.7454705426087362e-05,
|
85 |
+
"loss": 1.552,
|
86 |
+
"step": 11000
|
87 |
}
|
88 |
],
|
89 |
"max_steps": 86379,
|
90 |
"num_train_epochs": 1,
|
91 |
+
"total_flos": 2.052567331975987e+16,
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|
94 |
}
|
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:f1abc19bf3a6b17b6c52f668a4484117af425b853bca8d40a0fe9bae0c5dd31d
|
3 |
size 1121737121
|
runs/Jun04_02-06-39_4367d7224c9f/events.out.tfevents.1685845095.4367d7224c9f.857.0
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 sha256:729f414609be36a9087638ecdf4d652cca1f08fa68b5b6171d6916a093ef6af2
|
3 |
+
size 4503
|