MMMMoK9922 commited on
Commit
626888c
·
verified ·
1 Parent(s): 5a91f79

Upload candidate_value_qslow_active model and summary

Browse files
candidate_value/qslow_active_ensemble/head_seed260814/candidate_value_head.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69bb45e95dded44d9dbc279e75252b897365c673cf4359ae2369f72098255ca7
3
+ size 3725550
candidate_value/qslow_active_ensemble/head_seed260815/candidate_value_head.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21d07d3e494b5d4874fecbdb5bd476be3a325ee4ec8e114a528ed1a20f9220cf
3
+ size 3725230
candidate_value/qslow_active_ensemble/head_seed260816/candidate_value_head.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abbc42b2bf06cd641fb27b88d83d5f61282d10ffc212aafb5a4b65323232ae82
3
+ size 3725486
candidate_value/qslow_active_ensemble/head_seed260817/candidate_value_head.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a866e96d77bf2ea5a0b3e66843e7eecb130b139561f3d96783b8cbfa858a2f2
3
+ size 3725678
candidate_value/qslow_active_ensemble/head_seed260818/candidate_value_head.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80ef4e6e5c3ce691b6cb97387e741e1a610bf6543d5a6936c739226c3bf13ef
3
+ size 3725294
candidate_value/qslow_active_ensemble/head_seed260819/candidate_value_head.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b73481a9a725813dc6e2a9135cd5f8db989d547c3c605f95ef0751b584cd967e
3
+ size 3726894
candidate_value/qslow_active_ensemble/head_seed260820/candidate_value_head.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a80262c7d2d27fddc0bf69a44fe2f49d424c6b04afcae4f9dff541ac20b0e69e
3
+ size 3724910
candidate_value/qslow_active_ensemble/head_seed260821/candidate_value_head.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef301e49d5e41866e56ac0e2f324970d14bfeb5e89dd50f6b3b1edad22b060e9
3
+ size 3725678
candidate_value/qslow_active_ensemble/summary.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "collection": {
3
+ "input_files": 61,
4
+ "complete_groups": 1116,
5
+ "class_counts": {
6
+ "all_fail": 13,
7
+ "all_success": 867,
8
+ "normal_needed": 103,
9
+ "other": 92,
10
+ "slow_needed": 41
11
+ },
12
+ "selected_groups": 449,
13
+ "selected_class_counts": {
14
+ "all_fail": 13,
15
+ "all_success": 200,
16
+ "normal_needed": 103,
17
+ "other": 92,
18
+ "slow_needed": 41
19
+ },
20
+ "targets": {
21
+ "retained_groups": 400,
22
+ "max_all_success": 200
23
+ },
24
+ "targets_met": true,
25
+ "records_output": "/kairos_vepfs_volc/data/manlichen/MetaRoboBench/candidate_value/p05ff500c30_qslow_active_g8_20260813/selected_records.jsonl"
26
+ },
27
+ "heads": 8,
28
+ "test": [
29
+ {
30
+ "groups": 72,
31
+ "selected_successes": 49,
32
+ "slow_successes": 65,
33
+ "oracle_successes": 72,
34
+ "preferred_accuracy": 0.5555555555555556,
35
+ "success_accuracy": 0.6574074074074074,
36
+ "selected_speed_counts": {
37
+ "fast": 56,
38
+ "normal": 12,
39
+ "slow": 4
40
+ }
41
+ },
42
+ {
43
+ "groups": 72,
44
+ "selected_successes": 50,
45
+ "slow_successes": 65,
46
+ "oracle_successes": 72,
47
+ "preferred_accuracy": 0.5694444444444444,
48
+ "success_accuracy": 0.6481481481481481,
49
+ "selected_speed_counts": {
50
+ "fast": 51,
51
+ "normal": 14,
52
+ "slow": 7
53
+ }
54
+ },
55
+ {
56
+ "groups": 72,
57
+ "selected_successes": 47,
58
+ "slow_successes": 65,
59
+ "oracle_successes": 72,
60
+ "preferred_accuracy": 0.5555555555555556,
61
+ "success_accuracy": 0.6435185185185185,
62
+ "selected_speed_counts": {
63
+ "fast": 55,
64
+ "normal": 15,
65
+ "slow": 2
66
+ }
67
+ },
68
+ {
69
+ "groups": 72,
70
+ "selected_successes": 47,
71
+ "slow_successes": 65,
72
+ "oracle_successes": 72,
73
+ "preferred_accuracy": 0.5555555555555556,
74
+ "success_accuracy": 0.6712962962962963,
75
+ "selected_speed_counts": {
76
+ "fast": 60,
77
+ "normal": 10,
78
+ "slow": 2
79
+ }
80
+ },
81
+ {
82
+ "groups": 72,
83
+ "selected_successes": 44,
84
+ "slow_successes": 65,
85
+ "oracle_successes": 72,
86
+ "preferred_accuracy": 0.5,
87
+ "success_accuracy": 0.6712962962962963,
88
+ "selected_speed_counts": {
89
+ "fast": 56,
90
+ "normal": 15,
91
+ "slow": 1
92
+ }
93
+ },
94
+ {
95
+ "groups": 72,
96
+ "selected_successes": 49,
97
+ "slow_successes": 65,
98
+ "oracle_successes": 72,
99
+ "preferred_accuracy": 0.5,
100
+ "success_accuracy": 0.6527777777777778,
101
+ "selected_speed_counts": {
102
+ "fast": 50,
103
+ "normal": 11,
104
+ "slow": 11
105
+ }
106
+ },
107
+ {
108
+ "groups": 72,
109
+ "selected_successes": 49,
110
+ "slow_successes": 65,
111
+ "oracle_successes": 72,
112
+ "preferred_accuracy": 0.5416666666666666,
113
+ "success_accuracy": 0.6851851851851852,
114
+ "selected_speed_counts": {
115
+ "fast": 55,
116
+ "normal": 13,
117
+ "slow": 4
118
+ }
119
+ },
120
+ {
121
+ "groups": 72,
122
+ "selected_successes": 50,
123
+ "slow_successes": 65,
124
+ "oracle_successes": 72,
125
+ "preferred_accuracy": 0.5416666666666666,
126
+ "success_accuracy": 0.6435185185185185,
127
+ "selected_speed_counts": {
128
+ "fast": 49,
129
+ "normal": 18,
130
+ "slow": 5
131
+ }
132
+ }
133
+ ],
134
+ "selection": "argmax_value_no_threshold",
135
+ "label_semantics": "Q^Slow: success first; among successful candidate chunks choose the lowest final episode frame count, followed by Slow continuation"
136
+ }