Training in progress, step 500
Browse files- all_results.json +4 -4
- pytorch_model.bin +1 -1
- runs/Apr19_19-55-11_brutasse/1650398117.7451944/events.out.tfevents.1650398117.brutasse.28216.1 +3 -0
- runs/Apr19_19-55-11_brutasse/events.out.tfevents.1650398117.brutasse.28216.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +5 -5
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples_per_second": 32.
|
6 |
-
"train_steps_per_second": 2.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
+
"train_loss": 1.7289850234985351,
|
4 |
+
"train_runtime": 259.8277,
|
5 |
+
"train_samples_per_second": 32.714,
|
6 |
+
"train_steps_per_second": 2.078
|
7 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14963873
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96aed9ef584388c13518e28240841b9607f4e9f9f7c6b0340b477127ae15f863
|
3 |
size 14963873
|
runs/Apr19_19-55-11_brutasse/1650398117.7451944/events.out.tfevents.1650398117.brutasse.28216.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f49830604102e4ff63490c463e041865b800b845a1f2ab2e05de71d2ef2bf44
|
3 |
+
size 5023
|
runs/Apr19_19-55-11_brutasse/events.out.tfevents.1650398117.brutasse.28216.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0896f52258723e5381a1023488a1825b87127b9e08906488618d4822fd9fd276
|
3 |
+
size 5938
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples_per_second": 32.
|
6 |
-
"train_steps_per_second": 2.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
+
"train_loss": 1.7289850234985351,
|
4 |
+
"train_runtime": 259.8277,
|
5 |
+
"train_samples_per_second": 32.714,
|
6 |
+
"train_steps_per_second": 2.078
|
7 |
}
|
trainer_state.json
CHANGED
@@ -10,17 +10,17 @@
|
|
10 |
{
|
11 |
"epoch": 9.26,
|
12 |
"learning_rate": 3.7037037037037037e-06,
|
13 |
-
"loss": 1.
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
"epoch": 10.0,
|
18 |
"step": 540,
|
19 |
"total_flos": 1.49327778152448e+17,
|
20 |
-
"train_loss": 1.
|
21 |
-
"train_runtime":
|
22 |
-
"train_samples_per_second": 32.
|
23 |
-
"train_steps_per_second": 2.
|
24 |
}
|
25 |
],
|
26 |
"max_steps": 540,
|
|
|
10 |
{
|
11 |
"epoch": 9.26,
|
12 |
"learning_rate": 3.7037037037037037e-06,
|
13 |
+
"loss": 1.7612,
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
"epoch": 10.0,
|
18 |
"step": 540,
|
19 |
"total_flos": 1.49327778152448e+17,
|
20 |
+
"train_loss": 1.7289850234985351,
|
21 |
+
"train_runtime": 259.8277,
|
22 |
+
"train_samples_per_second": 32.714,
|
23 |
+
"train_steps_per_second": 2.078
|
24 |
}
|
25 |
],
|
26 |
"max_steps": 540,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3183
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db018bf8ec0b63a4e2f3caf7dde94171a5c80d17706a2f2e30cd644ec64ca701
|
3 |
size 3183
|