Training in progress, step 2000
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1001681601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c316b653e881cbc7c550e18a0ad79bc5bdd2f924059fd0750822acd856f517a6
|
3 |
size 1001681601
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b435d85ea3892e6bd61756c08b68b4615f1a3a1380f3265dee55d45beceeb611
|
3 |
size 551185105
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd51c2fa4070296203cb870e417cf342a24d6f4daf52267069468a9392c81b1e
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:485f44e8f87bcdee528a0308324f16db0903799b33ad2ce15b2040e5bda76593
|
3 |
size 623
|
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,
|
@@ -24,11 +24,17 @@
|
|
24 |
"learning_rate": 9.658863636363636e-08,
|
25 |
"loss": 0.0296,
|
26 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
}
|
28 |
],
|
29 |
"max_steps": 44000,
|
30 |
"num_train_epochs": 1,
|
31 |
-
"total_flos":
|
32 |
"trial_name": null,
|
33 |
"trial_params": null
|
34 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.02713041590927589,
|
5 |
+
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
24 |
"learning_rate": 9.658863636363636e-08,
|
25 |
"loss": 0.0296,
|
26 |
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.03,
|
30 |
+
"learning_rate": 9.545227272727273e-08,
|
31 |
+
"loss": 0.0246,
|
32 |
+
"step": 2000
|
33 |
}
|
34 |
],
|
35 |
"max_steps": 44000,
|
36 |
"num_train_epochs": 1,
|
37 |
+
"total_flos": 2091746435530752.0,
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
40 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b435d85ea3892e6bd61756c08b68b4615f1a3a1380f3265dee55d45beceeb611
|
3 |
size 551185105
|
runs/Oct20_17-51-04_5425517b47a3/events.out.tfevents.1666288481.5425517b47a3.23.0
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 sha256:5f1db98e2114e80f6143fca94fbec46f03e7b50fd9d52f52839add4074c25b5b
|
3 |
+
size 46274
|