tom813
commited on
Commit
•
7e8a666
1
Parent(s):
1c480f3
15000 update
Browse files- adapter_model.bin +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +21 -3
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 261189898
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58ff9f13fe4fd43916c511c4e7a58027c1ce30fb6b7744815a66a31aa378e9d7
|
3 |
size 261189898
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1044540346
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7318a7e6b468b1f60f77c2df735b4138a4972075a7f9d23b7cbbc3ea18158b34
|
3 |
size 1044540346
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:453bd6991fe36c7874b91d8fe044905b7822553a1079f2afd925646c3b124eb5
|
3 |
size 14244
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25d9b43d9967cc267ee69f422bfad8c170bd37836e9da711be203c8963d6971e
|
3 |
size 1064
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -18,11 +18,29 @@
|
|
18 |
"learning_rate": 0.0002,
|
19 |
"loss": 0.2937,
|
20 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
}
|
22 |
],
|
23 |
"max_steps": 30000,
|
24 |
"num_train_epochs": 30,
|
25 |
-
"total_flos":
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
28 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 14.634146341463415,
|
5 |
+
"global_step": 15000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
18 |
"learning_rate": 0.0002,
|
19 |
"loss": 0.2937,
|
20 |
"step": 6000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 8.78,
|
24 |
+
"learning_rate": 0.0002,
|
25 |
+
"loss": 1.5565,
|
26 |
+
"step": 9000
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 11.71,
|
30 |
+
"learning_rate": 0.0002,
|
31 |
+
"loss": 1.4597,
|
32 |
+
"step": 12000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 14.63,
|
36 |
+
"learning_rate": 0.0002,
|
37 |
+
"loss": 1.3908,
|
38 |
+
"step": 15000
|
39 |
}
|
40 |
],
|
41 |
"max_steps": 30000,
|
42 |
"num_train_epochs": 30,
|
43 |
+
"total_flos": 3.1738277265408e+18,
|
44 |
"trial_name": null,
|
45 |
"trial_params": null
|
46 |
}
|