Hugging Face's logo

narcolepticchicken
/
agent-cost-optimizer

ml-intern
Model card Files
xet
 Community
narcolepticchicken commited on
Commit
5defc5f
·
verified ·
1 Parent(s): 3816c65

Upload v2_verification_results.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. v2_verification_results.json +180 -0
v2_verification_results.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tier_router": {
3
+ "v1": {
4
+ "accuracy": 0.7007936507936507,
5
+ "f1_macro": 0.6703028725656281,
6
+ "threshold": null,
7
+ "per_class": {
8
+ "0": {
9
+ "precision": 0.6872536136662286,
10
+ "recall": 0.8819561551433389,
11
+ "f1": 0.7725258493353028,
12
+ "support": 593
13
+ },
14
+ "1": {
15
+ "precision": 0.6103896103896104,
16
+ "recall": 0.39275766016713093,
17
+ "f1": 0.47796610169491527,
18
+ "support": 359
19
+ },
20
+ "2": {
21
+ "precision": 0.8171641791044776,
22
+ "recall": 0.711038961038961,
23
+ "f1": 0.7604166666666666,
24
+ "support": 308
25
+ }
26
+ },
27
+ "collapsed": false,
28
+ "class_dist": {
29
+ "1": 359,
30
+ "0": 593,
31
+ "2": 308
32
+ }
33
+ },
34
+ "v2": {
35
+ "accuracy": 0.692063492063492,
36
+ "f1_macro": 0.6770126173682273,
37
+ "threshold": null,
38
+ "per_class": {
39
+ "0": {
40
+ "precision": 0.7383177570093458,
41
+ "recall": 0.7993254637436762,
42
+ "f1": 0.7676113360323886,
43
+ "support": 593
44
+ },
45
+ "1": {
46
+ "precision": 0.5335120643431636,
47
+ "recall": 0.5543175487465181,
48
+ "f1": 0.5437158469945356,
49
+ "support": 359
50
+ },
51
+ "2": {
52
+ "precision": 0.8122448979591836,
53
+ "recall": 0.6461038961038961,
54
+ "f1": 0.7197106690777577,
55
+ "support": 308
56
+ }
57
+ },
58
+ "collapsed": false,
59
+ "class_dist": {
60
+ "1": 359,
61
+ "0": 593,
62
+ "2": 308
63
+ }
64
+ },
65
+ "delta_f1": 0.006709744802599116,
66
+ "delta_acc": -0.0087301587301587
67
+ },
68
+ "tool_gater": {
69
+ "v1": {
70
+ "accuracy": 0.9823008849557522,
71
+ "f1_macro": 0.9195431761221236,
72
+ "accuracy_default": 0.9823008849557522,
73
+ "f1_default": 0.9195431761221236,
74
+ "threshold": 0.5,
75
+ "per_class": {
76
+ "neg": {
77
+ "precision": 0.988125,
78
+ "recall": 0.9930904522613065,
79
+ "f1": 0.9906015037593985,
80
+ "support": 1592
81
+ },
82
+ "pos": {
83
+ "precision": 0.8842105263157894,
84
+ "recall": 0.8155339805825242,
85
+ "f1": 0.8484848484848485,
86
+ "support": 103
87
+ }
88
+ },
89
+ "collapsed": false,
90
+ "class_dist": {
91
+ "0": 1592,
92
+ "1": 103
93
+ }
94
+ },
95
+ "v2": {
96
+ "accuracy": 0.9174041297935103,
97
+ "f1_macro": 0.7238976850688336,
98
+ "accuracy_default": 0.9174041297935103,
99
+ "f1_default": 0.7238976850688336,
100
+ "threshold": 0.5000000000000001,
101
+ "per_class": {
102
+ "neg": {
103
+ "precision": 0.9770039421813403,
104
+ "recall": 0.9340452261306532,
105
+ "f1": 0.9550417469492614,
106
+ "support": 1592
107
+ },
108
+ "pos": {
109
+ "precision": 0.3930635838150289,
110
+ "recall": 0.6601941747572816,
111
+ "f1": 0.4927536231884058,
112
+ "support": 103
113
+ }
114
+ },
115
+ "collapsed": false,
116
+ "class_dist": {
117
+ "0": 1592,
118
+ "1": 103
119
+ }
120
+ },
121
+ "delta_f1": -0.19564549105329,
122
+ "delta_acc": -0.06489675516224191
123
+ },
124
+ "verifier_gater": {
125
+ "v1": {
126
+ "accuracy": 0.6546929316338355,
127
+ "f1_macro": 0.6539117843377904,
128
+ "accuracy_default": 0.6546929316338355,
129
+ "f1_default": 0.6539117843377904,
130
+ "threshold": 0.5,
131
+ "per_class": {
132
+ "neg": {
133
+ "precision": 0.7112676056338029,
134
+ "recall": 0.6338912133891214,
135
+ "f1": 0.6703539823008849,
136
+ "support": 478
137
+ },
138
+ "pos": {
139
+ "precision": 0.5995423340961098,
140
+ "recall": 0.6805194805194805,
141
+ "f1": 0.6374695863746959,
142
+ "support": 385
143
+ }
144
+ },
145
+ "collapsed": false,
146
+ "class_dist": {
147
+ "1": 385,
148
+ "0": 478
149
+ }
150
+ },
151
+ "v2": {
152
+ "accuracy": 0.6674391657010429,
153
+ "f1_macro": 0.6666496187778009,
154
+ "accuracy_default": 0.6685979142526072,
155
+ "f1_default": 0.6676943872989887,
156
+ "threshold": 0.5200000000000001,
157
+ "per_class": {
158
+ "neg": {
159
+ "precision": 0.7784256559766763,
160
+ "recall": 0.5585774058577406,
161
+ "f1": 0.6504263093788063,
162
+ "support": 478
163
+ },
164
+ "pos": {
165
+ "precision": 0.5942307692307692,
166
+ "recall": 0.8025974025974026,
167
+ "f1": 0.6828729281767956,
168
+ "support": 385
169
+ }
170
+ },
171
+ "collapsed": false,
172
+ "class_dist": {
173
+ "1": 385,
174
+ "0": 478
175
+ }
176
+ },
177
+ "delta_f1": 0.012737834440010531,
178
+ "delta_acc": 0.01274623406720743
179
+ }
180
+ }