Add index-free MiniCPM scout, local QLoRA training, and measured evaluation
Tests / core (push) Canceled after 0s
Tests / core (push) Canceled after 0s
This commit is contained in:
@@ -0,0 +1,749 @@
|
||||
{
|
||||
"scope": "Diagnostic: target body covered by any successful read during search. Not final returned evidence; combined reads have a larger aggregate source budget.",
|
||||
"variants": {
|
||||
"ollama_q4": {
|
||||
"tasks": 30,
|
||||
"read_target_hits": 1,
|
||||
"per_task": [
|
||||
{
|
||||
"id": "requests-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 17
|
||||
},
|
||||
{
|
||||
"id": "requests-06",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 28
|
||||
},
|
||||
{
|
||||
"id": "requests-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 120
|
||||
},
|
||||
{
|
||||
"id": "requests-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-10",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 19
|
||||
},
|
||||
{
|
||||
"id": "flask-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 30
|
||||
},
|
||||
{
|
||||
"id": "flask-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 61
|
||||
},
|
||||
{
|
||||
"id": "flask-06",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 1
|
||||
},
|
||||
{
|
||||
"id": "flask-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 29
|
||||
},
|
||||
{
|
||||
"id": "flask-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 8
|
||||
},
|
||||
{
|
||||
"id": "flask-10",
|
||||
"read_target": true,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 100
|
||||
},
|
||||
{
|
||||
"id": "click-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 2,
|
||||
"unique_read_lines": 3
|
||||
},
|
||||
{
|
||||
"id": "click-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 3,
|
||||
"unique_read_lines": 3
|
||||
},
|
||||
{
|
||||
"id": "click-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 120
|
||||
},
|
||||
{
|
||||
"id": "click-06",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 16
|
||||
},
|
||||
{
|
||||
"id": "click-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 1
|
||||
},
|
||||
{
|
||||
"id": "click-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 120
|
||||
},
|
||||
{
|
||||
"id": "click-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 12
|
||||
},
|
||||
{
|
||||
"id": "click-10",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 11
|
||||
}
|
||||
]
|
||||
},
|
||||
"transformers_nf4": {
|
||||
"tasks": 30,
|
||||
"read_target_hits": 0,
|
||||
"per_task": [
|
||||
{
|
||||
"id": "requests-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 1
|
||||
},
|
||||
{
|
||||
"id": "requests-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-06",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 65
|
||||
},
|
||||
{
|
||||
"id": "requests-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 2
|
||||
},
|
||||
{
|
||||
"id": "requests-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-10",
|
||||
"read_target": false,
|
||||
"successful_reads": 3,
|
||||
"unique_read_lines": 23
|
||||
},
|
||||
{
|
||||
"id": "flask-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 1
|
||||
},
|
||||
{
|
||||
"id": "flask-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 77
|
||||
},
|
||||
{
|
||||
"id": "flask-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-06",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 1
|
||||
},
|
||||
{
|
||||
"id": "flask-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 15
|
||||
},
|
||||
{
|
||||
"id": "flask-10",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 3
|
||||
},
|
||||
{
|
||||
"id": "click-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 4,
|
||||
"unique_read_lines": 4
|
||||
},
|
||||
{
|
||||
"id": "click-06",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 1
|
||||
},
|
||||
{
|
||||
"id": "click-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 6
|
||||
},
|
||||
{
|
||||
"id": "click-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 4
|
||||
},
|
||||
{
|
||||
"id": "click-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 1
|
||||
},
|
||||
{
|
||||
"id": "click-10",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
}
|
||||
]
|
||||
},
|
||||
"adapter_v1": {
|
||||
"tasks": 30,
|
||||
"read_target_hits": 0,
|
||||
"per_task": [
|
||||
{
|
||||
"id": "requests-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 40
|
||||
},
|
||||
{
|
||||
"id": "requests-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 35
|
||||
},
|
||||
{
|
||||
"id": "requests-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 1
|
||||
},
|
||||
{
|
||||
"id": "requests-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 84
|
||||
},
|
||||
{
|
||||
"id": "requests-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-06",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 66
|
||||
},
|
||||
{
|
||||
"id": "requests-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 78
|
||||
},
|
||||
{
|
||||
"id": "requests-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 1
|
||||
},
|
||||
{
|
||||
"id": "requests-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-10",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 2
|
||||
},
|
||||
{
|
||||
"id": "flask-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 118
|
||||
},
|
||||
{
|
||||
"id": "flask-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 23
|
||||
},
|
||||
{
|
||||
"id": "flask-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 33
|
||||
},
|
||||
{
|
||||
"id": "flask-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 37
|
||||
},
|
||||
{
|
||||
"id": "flask-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 53
|
||||
},
|
||||
{
|
||||
"id": "flask-06",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 17
|
||||
},
|
||||
{
|
||||
"id": "flask-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 37
|
||||
},
|
||||
{
|
||||
"id": "flask-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 31
|
||||
},
|
||||
{
|
||||
"id": "flask-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 21
|
||||
},
|
||||
{
|
||||
"id": "flask-10",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 111
|
||||
},
|
||||
{
|
||||
"id": "click-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 89
|
||||
},
|
||||
{
|
||||
"id": "click-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 21
|
||||
},
|
||||
{
|
||||
"id": "click-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 3
|
||||
},
|
||||
{
|
||||
"id": "click-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 75
|
||||
},
|
||||
{
|
||||
"id": "click-06",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 87
|
||||
},
|
||||
{
|
||||
"id": "click-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 56
|
||||
},
|
||||
{
|
||||
"id": "click-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 14
|
||||
},
|
||||
{
|
||||
"id": "click-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 21
|
||||
},
|
||||
{
|
||||
"id": "click-10",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 48
|
||||
}
|
||||
]
|
||||
},
|
||||
"adapter_v2": {
|
||||
"tasks": 30,
|
||||
"read_target_hits": 1,
|
||||
"per_task": [
|
||||
{
|
||||
"id": "requests-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 81
|
||||
},
|
||||
{
|
||||
"id": "requests-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 101
|
||||
},
|
||||
{
|
||||
"id": "requests-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-06",
|
||||
"read_target": true,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 90
|
||||
},
|
||||
{
|
||||
"id": "requests-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 101
|
||||
},
|
||||
{
|
||||
"id": "requests-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "requests-10",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-06",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "flask-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 74
|
||||
},
|
||||
{
|
||||
"id": "flask-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 101
|
||||
},
|
||||
{
|
||||
"id": "flask-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 101
|
||||
},
|
||||
{
|
||||
"id": "flask-10",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-01",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-02",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-03",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-04",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-05",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-06",
|
||||
"read_target": false,
|
||||
"successful_reads": 1,
|
||||
"unique_read_lines": 118
|
||||
},
|
||||
{
|
||||
"id": "click-07",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-08",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-09",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
},
|
||||
{
|
||||
"id": "click-10",
|
||||
"read_target": false,
|
||||
"successful_reads": 0,
|
||||
"unique_read_lines": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user