Commit
•
ce8c3d8
1
Parent(s):
4cd6e77
Training in progress, step 2000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +23 -3
- pytorch_model.bin +1 -1
- runs/Mar24_13-56-57_9891ffea5fdc/events.out.tfevents.1679666221.9891ffea5fdc.675.0 +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 2847145157
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7098abf80dcc4efe9fe1060e6a60b6513b742b95075629fb0643e2c6ccf54168
|
3 |
size 2847145157
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c901c3fbc15d3575284f2e5fd521563888566b5e135882a2ce394205bf25d10d
|
3 |
size 1524261149
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fe857f1e69c23f614e1fdda9e28583b7e3ffdf1b8d255d77f9e2bd92913534a
|
3 |
size 14575
|
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:a32a25264c00904ee87e9a06cdd056f1bcfef3a4060539bab5b821516db4eb96
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -26,11 +26,31 @@
|
|
26 |
"eval_samples_per_second": 15.677,
|
27 |
"eval_steps_per_second": 2.614,
|
28 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
}
|
30 |
],
|
31 |
"max_steps": 9995,
|
32 |
"num_train_epochs": 5,
|
33 |
-
"total_flos":
|
34 |
"trial_name": null,
|
35 |
"trial_params": null
|
36 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0005002501250626,
|
5 |
+
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
26 |
"eval_samples_per_second": 15.677,
|
27 |
"eval_steps_per_second": 2.614,
|
28 |
"step": 1000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.75,
|
32 |
+
"learning_rate": 1.6998499249624815e-05,
|
33 |
+
"loss": 3.1872,
|
34 |
+
"step": 1500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 1.0,
|
38 |
+
"learning_rate": 1.599799899949975e-05,
|
39 |
+
"loss": 3.1659,
|
40 |
+
"step": 2000
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 1.0,
|
44 |
+
"eval_loss": 3.1159095764160156,
|
45 |
+
"eval_runtime": 134.9774,
|
46 |
+
"eval_samples_per_second": 15.684,
|
47 |
+
"eval_steps_per_second": 2.615,
|
48 |
+
"step": 2000
|
49 |
}
|
50 |
],
|
51 |
"max_steps": 9995,
|
52 |
"num_train_epochs": 5,
|
53 |
+
"total_flos": 5659269857280000.0,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|
56 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c901c3fbc15d3575284f2e5fd521563888566b5e135882a2ce394205bf25d10d
|
3 |
size 1524261149
|
runs/Mar24_13-56-57_9891ffea5fdc/events.out.tfevents.1679666221.9891ffea5fdc.675.0
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:e2fa327cc7886676c087d1f05a5167bd4f52ab8fd161e78308e37d866216b66d
|
3 |
+
size 5325
|