End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.99958686221855,
|
3 |
+
"total_flos": 9.925024630549355e+19,
|
4 |
+
"train_loss": 1.502550286699811,
|
5 |
+
"train_runtime": 81421.0241,
|
6 |
+
"train_samples_per_second": 11.891,
|
7 |
+
"train_steps_per_second": 0.743
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.99958686221855,
|
3 |
+
"total_flos": 9.925024630549355e+19,
|
4 |
+
"train_loss": 1.502550286699811,
|
5 |
+
"train_runtime": 81421.0241,
|
6 |
+
"train_samples_per_second": 11.891,
|
7 |
+
"train_steps_per_second": 0.743
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|