Commit
•
49aed88
1
Parent(s):
9e8b4c5
Training in progress, step 27054
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_13-23-35_1c0366a2fd20/events.out.tfevents.1685885434.1c0366a2fd20.848.0 +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:e6b668281cfaa0451cc98ba11615ec02e72d80de0ed7cc4789cf22c72392a790
|
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 sha256:74e86f4fca51e3894dd5548ad67c99c7e4e4d33d5c08180437565808ddaa7f51
|
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 sha256:165d14822acba753a1d8f0d787071d58fe69341c1047ef2f8c00f12403c09456
|
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:e6376e5308388d326e18f61a636fb3c4f55de4c1f3e204b466fb36671c1c0646
|
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:a2b9abf983dc60c25cd57c884b13f7f1dfc0b10cafb6629d6b55aadd31c13aa5
|
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,
|
@@ -174,11 +174,17 @@
|
|
174 |
"learning_rate": 1.3982796744579123e-05,
|
175 |
"loss": 1.5007,
|
176 |
"step": 26000
|
|
|
|
|
|
|
|
|
|
|
|
|
177 |
}
|
178 |
],
|
179 |
"max_steps": 86379,
|
180 |
"num_train_epochs": 1,
|
181 |
-
"total_flos":
|
182 |
"trial_name": null,
|
183 |
"trial_params": null
|
184 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.31320112527350397,
|
5 |
+
"global_step": 27054,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
174 |
"learning_rate": 1.3982796744579123e-05,
|
175 |
"loss": 1.5007,
|
176 |
"step": 26000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.31,
|
180 |
+
"learning_rate": 1.3751490524317255e-05,
|
181 |
+
"loss": 1.5128,
|
182 |
+
"step": 27000
|
183 |
}
|
184 |
],
|
185 |
"max_steps": 86379,
|
186 |
"num_train_epochs": 1,
|
187 |
+
"total_flos": 5.03811981485015e+16,
|
188 |
"trial_name": null,
|
189 |
"trial_params": null
|
190 |
}
|
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 sha256:74e86f4fca51e3894dd5548ad67c99c7e4e4d33d5c08180437565808ddaa7f51
|
3 |
size 1121737121
|
runs/Jun04_13-23-35_1c0366a2fd20/events.out.tfevents.1685885434.1c0366a2fd20.848.0
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 sha256:7193e752062c6faeec2c711b108a1481062b40f3fd617b2125dbde492cf35fbf
|
3 |
+
size 4829
|