Upload post_eval.json with huggingface_hub
Browse files- post_eval.json +21 -21
post_eval.json
CHANGED
|
@@ -3,43 +3,43 @@
|
|
| 3 |
{
|
| 4 |
"prompt": "Write a 200-word blog post about the benefits of remote work.",
|
| 5 |
"score": {
|
| 6 |
-
"len":
|
| 7 |
-
"ppl":
|
| 8 |
-
"burst": 0.
|
| 9 |
-
"fdgpt": 0.
|
| 10 |
-
"nppl":
|
| 11 |
-
"stylo": 0.
|
| 12 |
-
"ensemble": 0.
|
| 13 |
-
"class": "
|
| 14 |
}
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"prompt": "Explain quantum computing in simple terms, around 150 words.",
|
| 18 |
"score": {
|
| 19 |
-
"len":
|
| 20 |
-
"ppl":
|
| 21 |
-
"burst": 0.
|
| 22 |
-
"fdgpt": 0.
|
| 23 |
-
"nppl":
|
| 24 |
"stylo": 0.275,
|
| 25 |
-
"ensemble": 0.
|
| 26 |
"class": "Human"
|
| 27 |
}
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"prompt": "Write a professional email declining a job offer, about 100 words.",
|
| 31 |
"score": {
|
| 32 |
-
"len":
|
| 33 |
-
"ppl":
|
| 34 |
-
"burst": 0.
|
| 35 |
-
"fdgpt": 0.
|
| 36 |
-
"nppl": 12.
|
| 37 |
"stylo": 0.275,
|
| 38 |
"ensemble": 0.4418,
|
| 39 |
"class": "Uncertain"
|
| 40 |
}
|
| 41 |
}
|
| 42 |
],
|
| 43 |
-
"mean": 0.
|
| 44 |
-
"improvement": -0.
|
| 45 |
}
|
|
|
|
| 3 |
{
|
| 4 |
"prompt": "Write a 200-word blog post about the benefits of remote work.",
|
| 5 |
"score": {
|
| 6 |
+
"len": 187,
|
| 7 |
+
"ppl": 17.1,
|
| 8 |
+
"burst": 0.6005,
|
| 9 |
+
"fdgpt": 0.0002,
|
| 10 |
+
"nppl": 22.2,
|
| 11 |
+
"stylo": 0.375,
|
| 12 |
+
"ensemble": 0.4071,
|
| 13 |
+
"class": "Uncertain"
|
| 14 |
}
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"prompt": "Explain quantum computing in simple terms, around 150 words.",
|
| 18 |
"score": {
|
| 19 |
+
"len": 139,
|
| 20 |
+
"ppl": 19.5,
|
| 21 |
+
"burst": 0.505,
|
| 22 |
+
"fdgpt": 0.0001,
|
| 23 |
+
"nppl": 28.6,
|
| 24 |
"stylo": 0.275,
|
| 25 |
+
"ensemble": 0.2984,
|
| 26 |
"class": "Human"
|
| 27 |
}
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"prompt": "Write a professional email declining a job offer, about 100 words.",
|
| 31 |
"score": {
|
| 32 |
+
"len": 100,
|
| 33 |
+
"ppl": 9.0,
|
| 34 |
+
"burst": 0.3377,
|
| 35 |
+
"fdgpt": 0.0014,
|
| 36 |
+
"nppl": 12.6,
|
| 37 |
"stylo": 0.275,
|
| 38 |
"ensemble": 0.4418,
|
| 39 |
"class": "Uncertain"
|
| 40 |
}
|
| 41 |
}
|
| 42 |
],
|
| 43 |
+
"mean": 0.3824,
|
| 44 |
+
"improvement": -0.0241
|
| 45 |
}
|