End of training
Browse files- all_results.json +2 -2
- train_results.json +2 -2
- trainer_state.json +2 -2
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -2,8 +2,8 @@
|
|
2 |
"epoch": 40.0,
|
3 |
"total_flos": 4.167371548576973e+18,
|
4 |
"train_loss": 1.28,
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 2698,
|
7 |
-
"train_samples_per_second": 132.
|
8 |
"train_steps_per_second": 0.491
|
9 |
}
|
|
|
2 |
"epoch": 40.0,
|
3 |
"total_flos": 4.167371548576973e+18,
|
4 |
"train_loss": 1.28,
|
5 |
+
"train_runtime": 814.2643,
|
6 |
"train_samples": 2698,
|
7 |
+
"train_samples_per_second": 132.537,
|
8 |
"train_steps_per_second": 0.491
|
9 |
}
|
train_results.json
CHANGED
@@ -2,8 +2,8 @@
|
|
2 |
"epoch": 40.0,
|
3 |
"total_flos": 4.167371548576973e+18,
|
4 |
"train_loss": 1.28,
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 2698,
|
7 |
-
"train_samples_per_second": 132.
|
8 |
"train_steps_per_second": 0.491
|
9 |
}
|
|
|
2 |
"epoch": 40.0,
|
3 |
"total_flos": 4.167371548576973e+18,
|
4 |
"train_loss": 1.28,
|
5 |
+
"train_runtime": 814.2643,
|
6 |
"train_samples": 2698,
|
7 |
+
"train_samples_per_second": 132.537,
|
8 |
"train_steps_per_second": 0.491
|
9 |
}
|
trainer_state.json
CHANGED
@@ -13,8 +13,8 @@
|
|
13 |
"step": 400,
|
14 |
"total_flos": 4.167371548576973e+18,
|
15 |
"train_loss": 1.28,
|
16 |
-
"train_runtime":
|
17 |
-
"train_samples_per_second": 132.
|
18 |
"train_steps_per_second": 0.491
|
19 |
}
|
20 |
],
|
|
|
13 |
"step": 400,
|
14 |
"total_flos": 4.167371548576973e+18,
|
15 |
"train_loss": 1.28,
|
16 |
+
"train_runtime": 814.2643,
|
17 |
+
"train_samples_per_second": 132.537,
|
18 |
"train_steps_per_second": 0.491
|
19 |
}
|
20 |
],
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8824
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfd08f66fdfb30ee1d264d881de4c25929edb8d5f342f45449e62265c6938783
|
3 |
size 8824
|