Model save
Browse files- all_results.json +3 -3
- train_results.json +3 -3
- trainer_state.json +3 -3
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -11,7 +11,7 @@
|
|
11 |
"perplexity": 24.39002046460787,
|
12 |
"total_flos": 1.0587061010143642e+18,
|
13 |
"train_loss": 0.0,
|
14 |
-
"train_runtime": 0.
|
15 |
-
"train_samples_per_second":
|
16 |
-
"train_steps_per_second":
|
17 |
}
|
|
|
11 |
"perplexity": 24.39002046460787,
|
12 |
"total_flos": 1.0587061010143642e+18,
|
13 |
"train_loss": 0.0,
|
14 |
+
"train_runtime": 0.6897,
|
15 |
+
"train_samples_per_second": 826370.638,
|
16 |
+
"train_steps_per_second": 12918.158
|
17 |
}
|
train_results.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"epoch": 5.0,
|
3 |
"total_flos": 1.0587061010143642e+18,
|
4 |
"train_loss": 0.0,
|
5 |
-
"train_runtime": 0.
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
2 |
"epoch": 5.0,
|
3 |
"total_flos": 1.0587061010143642e+18,
|
4 |
"train_loss": 0.0,
|
5 |
+
"train_runtime": 0.6897,
|
6 |
+
"train_samples_per_second": 826370.638,
|
7 |
+
"train_steps_per_second": 12918.158
|
8 |
}
|
trainer_state.json
CHANGED
@@ -823,9 +823,9 @@
|
|
823 |
"step": 8910,
|
824 |
"total_flos": 1.0587061010143642e+18,
|
825 |
"train_loss": 0.0,
|
826 |
-
"train_runtime": 0.
|
827 |
-
"train_samples_per_second":
|
828 |
-
"train_steps_per_second":
|
829 |
}
|
830 |
],
|
831 |
"logging_steps": 100,
|
|
|
823 |
"step": 8910,
|
824 |
"total_flos": 1.0587061010143642e+18,
|
825 |
"train_loss": 0.0,
|
826 |
+
"train_runtime": 0.6897,
|
827 |
+
"train_samples_per_second": 826370.638,
|
828 |
+
"train_steps_per_second": 12918.158
|
829 |
}
|
830 |
],
|
831 |
"logging_steps": 100,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b64acc06a54753e3c90d36e5fc570d0909cca6d16e044cd9018ae585d3fb3c51
|
3 |
size 5560
|