End of training
Browse files
all_results.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime":
|
6 |
"eval_samples": 24055,
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second":
|
9 |
-
"perplexity":
|
10 |
-
"train_loss":
|
11 |
-
"train_runtime":
|
12 |
"train_samples": 24910,
|
13 |
-
"train_samples_per_second":
|
14 |
-
"train_steps_per_second": 0.
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 89.58,
|
3 |
+
"eval_accuracy": 0.5148013040185571,
|
4 |
+
"eval_loss": 2.73911714553833,
|
5 |
+
"eval_runtime": 145.896,
|
6 |
"eval_samples": 24055,
|
7 |
+
"eval_samples_per_second": 164.878,
|
8 |
+
"eval_steps_per_second": 5.154,
|
9 |
+
"perplexity": 15.47331837619993,
|
10 |
+
"train_loss": 3.7431876293448516,
|
11 |
+
"train_runtime": 42244.2763,
|
12 |
"train_samples": 24910,
|
13 |
+
"train_samples_per_second": 58.967,
|
14 |
+
"train_steps_per_second": 0.114
|
15 |
}
|
eval_results.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime":
|
6 |
"eval_samples": 24055,
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second":
|
9 |
-
"perplexity":
|
10 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 89.58,
|
3 |
+
"eval_accuracy": 0.5148013040185571,
|
4 |
+
"eval_loss": 2.73911714553833,
|
5 |
+
"eval_runtime": 145.896,
|
6 |
"eval_samples": 24055,
|
7 |
+
"eval_samples_per_second": 164.878,
|
8 |
+
"eval_steps_per_second": 5.154,
|
9 |
+
"perplexity": 15.47331837619993
|
10 |
}
|
runs/Feb14_00-12-10_monica.sm.unibocconi.it/events.out.tfevents.1676372443.monica.sm.unibocconi.it.4164817.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26625321fb87508e6806a980245d911e5f14945900233a180200a73b51d5fcc8
|
3 |
+
size 363
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 24910,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 89.58,
|
3 |
+
"train_loss": 3.7431876293448516,
|
4 |
+
"train_runtime": 42244.2763,
|
5 |
"train_samples": 24910,
|
6 |
+
"train_samples_per_second": 58.967,
|
7 |
+
"train_steps_per_second": 0.114
|
8 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|