tahaalam2009 commited on
Commit
783c781
·
verified ·
1 Parent(s): b8ef814

Upload eval_summary_deep_dive.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. eval_summary_deep_dive.json +176 -265
eval_summary_deep_dive.json CHANGED
@@ -2,331 +2,242 @@
2
  "wikitext2": {
3
  "name": "WikiText-2",
4
  "bf16": {
5
- "ppl": 5.1579,
6
- "ppl_unc": 0.36938,
7
- "time_sec": 195.8225395679474
8
  },
9
  "models": {
10
  "VeriLoop_IQ3_XXS": {
11
- "label": "VeriLoop-E2 GSQ-RCO IQ3_XXS (3.05 bpw)",
12
- "ppl": null,
13
- "ppl_unc": null,
14
- "ppl_ratio": null,
15
- "mean_kld": null,
16
- "kld_unc": null,
17
- "top1_agreement": null,
18
- "top1_unc": null,
19
- "top5_agreement": null,
20
- "top5_unc": null,
21
- "rms_delta_p": null,
22
- "time_sec": 110.35492277145386
23
  },
24
  "VeriLoop_IQ3_S": {
25
- "label": "VeriLoop-E2 GSQ-RCO IQ3_S (3.55 bpw)",
26
- "ppl": null,
27
- "ppl_unc": null,
28
- "ppl_ratio": null,
29
- "mean_kld": null,
30
- "kld_unc": null,
31
- "top1_agreement": null,
32
- "top1_unc": null,
33
- "top5_agreement": null,
34
- "top5_unc": null,
35
- "rms_delta_p": null,
36
- "time_sec": 118.25298762321472
37
  },
38
  "Qwen_IQ3_XXS": {
39
- "label": "Qwen3.8-27B GSQ-RCO IQ3_XXS (3.05 bpw)",
40
- "ppl": null,
41
- "ppl_unc": null,
42
- "ppl_ratio": null,
43
- "mean_kld": null,
44
- "kld_unc": null,
45
- "top1_agreement": null,
46
- "top1_unc": null,
47
- "top5_agreement": null,
48
- "top5_unc": null,
49
- "rms_delta_p": null,
50
- "time_sec": 109.87469863891602
51
  },
52
  "Qwen_IQ3_S": {
53
- "label": "Qwen3.8-27B GSQ-RCO IQ3_S (3.55 bpw)",
54
- "ppl": null,
55
- "ppl_unc": null,
56
- "ppl_ratio": null,
57
- "mean_kld": null,
58
- "kld_unc": null,
59
- "top1_agreement": null,
60
- "top1_unc": null,
61
- "top5_agreement": null,
62
- "top5_unc": null,
63
- "rms_delta_p": null,
64
- "time_sec": 112.30604457855225
65
  }
66
  }
67
  },
68
  "codemath": {
69
  "name": "Code & Math",
70
  "bf16": {
71
- "ppl": 1.67,
72
- "ppl_unc": 0.06374,
73
- "time_sec": 148.9525682926178
74
  },
75
  "models": {
76
  "VeriLoop_IQ3_XXS": {
77
- "label": "VeriLoop-E2 GSQ-RCO IQ3_XXS (3.05 bpw)",
78
- "ppl": null,
79
- "ppl_unc": null,
80
- "ppl_ratio": null,
81
- "mean_kld": null,
82
- "kld_unc": null,
83
- "top1_agreement": null,
84
- "top1_unc": null,
85
- "top5_agreement": null,
86
- "top5_unc": null,
87
- "rms_delta_p": null,
88
- "time_sec": 97.66222810745239
89
  },
90
  "VeriLoop_IQ3_S": {
91
- "label": "VeriLoop-E2 GSQ-RCO IQ3_S (3.55 bpw)",
92
- "ppl": null,
93
- "ppl_unc": null,
94
- "ppl_ratio": null,
95
- "mean_kld": null,
96
- "kld_unc": null,
97
- "top1_agreement": null,
98
- "top1_unc": null,
99
- "top5_agreement": null,
100
- "top5_unc": null,
101
- "rms_delta_p": null,
102
- "time_sec": 99.04169034957886
103
  },
104
  "Qwen_IQ3_XXS": {
105
- "label": "Qwen3.8-27B GSQ-RCO IQ3_XXS (3.05 bpw)",
106
- "ppl": null,
107
- "ppl_unc": null,
108
- "ppl_ratio": null,
109
- "mean_kld": null,
110
- "kld_unc": null,
111
- "top1_agreement": null,
112
- "top1_unc": null,
113
- "top5_agreement": null,
114
- "top5_unc": null,
115
- "rms_delta_p": null,
116
- "time_sec": 100.96973204612732
117
  },
118
  "Qwen_IQ3_S": {
119
- "label": "Qwen3.8-27B GSQ-RCO IQ3_S (3.55 bpw)",
120
- "ppl": null,
121
- "ppl_unc": null,
122
- "ppl_ratio": null,
123
- "mean_kld": null,
124
- "kld_unc": null,
125
- "top1_agreement": null,
126
- "top1_unc": null,
127
- "top5_agreement": null,
128
- "top5_unc": null,
129
- "rms_delta_p": null,
130
- "time_sec": 102.65990972518921
131
  }
132
  }
133
  },
134
  "aime2025": {
135
  "name": "AIME 2025",
136
  "bf16": {
137
- "ppl": 2.0732,
138
- "ppl_unc": 0.0933,
139
- "time_sec": 153.58131432533264
140
  },
141
  "models": {
142
  "VeriLoop_IQ3_XXS": {
143
- "label": "VeriLoop-E2 GSQ-RCO IQ3_XXS (3.05 bpw)",
144
- "ppl": null,
145
- "ppl_unc": null,
146
- "ppl_ratio": null,
147
- "mean_kld": null,
148
- "kld_unc": null,
149
- "top1_agreement": null,
150
- "top1_unc": null,
151
- "top5_agreement": null,
152
- "top5_unc": null,
153
- "rms_delta_p": null,
154
- "time_sec": 100.4238953590393
155
  },
156
  "VeriLoop_IQ3_S": {
157
- "label": "VeriLoop-E2 GSQ-RCO IQ3_S (3.55 bpw)",
158
- "ppl": null,
159
- "ppl_unc": null,
160
- "ppl_ratio": null,
161
- "mean_kld": null,
162
- "kld_unc": null,
163
- "top1_agreement": null,
164
- "top1_unc": null,
165
- "top5_agreement": null,
166
- "top5_unc": null,
167
- "rms_delta_p": null,
168
- "time_sec": 101.96496200561523
169
  },
170
  "Qwen_IQ3_XXS": {
171
- "label": "Qwen3.8-27B GSQ-RCO IQ3_XXS (3.05 bpw)",
172
- "ppl": null,
173
- "ppl_unc": null,
174
- "ppl_ratio": null,
175
- "mean_kld": null,
176
- "kld_unc": null,
177
- "top1_agreement": null,
178
- "top1_unc": null,
179
- "top5_agreement": null,
180
- "top5_unc": null,
181
- "rms_delta_p": null,
182
- "time_sec": 98.5217227935791
183
  },
184
  "Qwen_IQ3_S": {
185
- "label": "Qwen3.8-27B GSQ-RCO IQ3_S (3.55 bpw)",
186
- "ppl": null,
187
- "ppl_unc": null,
188
- "ppl_ratio": null,
189
- "mean_kld": null,
190
- "kld_unc": null,
191
- "top1_agreement": null,
192
- "top1_unc": null,
193
- "top5_agreement": null,
194
- "top5_unc": null,
195
- "rms_delta_p": null,
196
- "time_sec": 108.99933910369873
197
  }
198
  }
199
  },
200
  "livecode": {
201
  "name": "LiveCodeBench",
202
  "bf16": {
203
- "ppl": 1.3103,
204
- "ppl_unc": 0.04437,
205
- "time_sec": 159.20217180252075
206
  },
207
  "models": {
208
  "VeriLoop_IQ3_XXS": {
209
- "label": "VeriLoop-E2 GSQ-RCO IQ3_XXS (3.05 bpw)",
210
- "ppl": null,
211
- "ppl_unc": null,
212
- "ppl_ratio": null,
213
- "mean_kld": null,
214
- "kld_unc": null,
215
- "top1_agreement": null,
216
- "top1_unc": null,
217
- "top5_agreement": null,
218
- "top5_unc": null,
219
- "rms_delta_p": null,
220
- "time_sec": 101.15227603912354
221
  },
222
  "VeriLoop_IQ3_S": {
223
- "label": "VeriLoop-E2 GSQ-RCO IQ3_S (3.55 bpw)",
224
- "ppl": null,
225
- "ppl_unc": null,
226
- "ppl_ratio": null,
227
- "mean_kld": null,
228
- "kld_unc": null,
229
- "top1_agreement": null,
230
- "top1_unc": null,
231
- "top5_agreement": null,
232
- "top5_unc": null,
233
- "rms_delta_p": null,
234
- "time_sec": 98.8099889755249
235
  },
236
  "Qwen_IQ3_XXS": {
237
- "label": "Qwen3.8-27B GSQ-RCO IQ3_XXS (3.05 bpw)",
238
- "ppl": null,
239
- "ppl_unc": null,
240
- "ppl_ratio": null,
241
- "mean_kld": null,
242
- "kld_unc": null,
243
- "top1_agreement": null,
244
- "top1_unc": null,
245
- "top5_agreement": null,
246
- "top5_unc": null,
247
- "rms_delta_p": null,
248
- "time_sec": 98.93727707862854
249
  },
250
  "Qwen_IQ3_S": {
251
- "label": "Qwen3.8-27B GSQ-RCO IQ3_S (3.55 bpw)",
252
- "ppl": null,
253
- "ppl_unc": null,
254
- "ppl_ratio": null,
255
- "mean_kld": null,
256
- "kld_unc": null,
257
- "top1_agreement": null,
258
- "top1_unc": null,
259
- "top5_agreement": null,
260
- "top5_unc": null,
261
- "rms_delta_p": null,
262
- "time_sec": 97.8656849861145
263
  }
264
  }
265
  },
266
  "terminal": {
267
  "name": "TerminalBench 2.1",
268
- "bf16": {
269
- "ppl": null,
270
- "ppl_unc": null,
271
- "time_sec": 17.898959398269653
272
- },
273
  "models": {
274
- "VeriLoop_IQ3_XXS": {
275
- "label": "VeriLoop-E2 GSQ-RCO IQ3_XXS (3.05 bpw)",
276
- "ppl": null,
277
- "ppl_unc": null,
278
- "ppl_ratio": null,
279
- "mean_kld": null,
280
- "kld_unc": null,
281
- "top1_agreement": null,
282
- "top1_unc": null,
283
- "top5_agreement": null,
284
- "top5_unc": null,
285
- "rms_delta_p": null,
286
- "time_sec": 3.4318151473999023
287
- },
288
- "VeriLoop_IQ3_S": {
289
- "label": "VeriLoop-E2 GSQ-RCO IQ3_S (3.55 bpw)",
290
- "ppl": null,
291
- "ppl_unc": null,
292
- "ppl_ratio": null,
293
- "mean_kld": null,
294
- "kld_unc": null,
295
- "top1_agreement": null,
296
- "top1_unc": null,
297
- "top5_agreement": null,
298
- "top5_unc": null,
299
- "rms_delta_p": null,
300
- "time_sec": 5.760640859603882
301
- },
302
- "Qwen_IQ3_XXS": {
303
- "label": "Qwen3.8-27B GSQ-RCO IQ3_XXS (3.05 bpw)",
304
- "ppl": null,
305
- "ppl_unc": null,
306
- "ppl_ratio": null,
307
- "mean_kld": null,
308
- "kld_unc": null,
309
- "top1_agreement": null,
310
- "top1_unc": null,
311
- "top5_agreement": null,
312
- "top5_unc": null,
313
- "rms_delta_p": null,
314
- "time_sec": 3.5282740592956543
315
- },
316
- "Qwen_IQ3_S": {
317
- "label": "Qwen3.8-27B GSQ-RCO IQ3_S (3.55 bpw)",
318
- "ppl": null,
319
- "ppl_unc": null,
320
- "ppl_ratio": null,
321
- "mean_kld": null,
322
- "kld_unc": null,
323
- "top1_agreement": null,
324
- "top1_unc": null,
325
- "top5_agreement": null,
326
- "top5_unc": null,
327
- "rms_delta_p": null,
328
- "time_sec": 4.589294672012329
329
- }
330
  }
331
  }
332
  }
 
2
  "wikitext2": {
3
  "name": "WikiText-2",
4
  "bf16": {
5
+ "ppl": 5.157865,
6
+ "ppl_unc": 0.369376
 
7
  },
8
  "models": {
9
  "VeriLoop_IQ3_XXS": {
10
+ "ppl": 5.281293,
11
+ "ppl_unc": 0.379551,
12
+ "ppl_ratio": 1.02393,
13
+ "mean_kld": 0.078914,
14
+ "kld_unc": 0.005409,
15
+ "top1": 88.748,
16
+ "top1_unc": 0.989,
17
+ "top5": 99.413,
18
+ "top5_unc": 0.239,
19
+ "rms": 7.67
 
 
20
  },
21
  "VeriLoop_IQ3_S": {
22
+ "ppl": 5.368311,
23
+ "ppl_unc": 0.392426,
24
+ "ppl_ratio": 1.040801,
25
+ "mean_kld": 0.035113,
26
+ "kld_unc": 0.001932,
27
+ "top1": 92.368,
28
+ "top1_unc": 0.831,
29
+ "top5": 99.804,
30
+ "top5_unc": 0.138,
31
+ "rms": 5.132
 
 
32
  },
33
  "Qwen_IQ3_XXS": {
34
+ "ppl": 5.391707,
35
+ "ppl_unc": 0.391388,
36
+ "ppl_ratio": 1.045337,
37
+ "mean_kld": 0.072731,
38
+ "kld_unc": 0.004163,
39
+ "top1": 89.335,
40
+ "top1_unc": 0.966,
41
+ "top5": 99.315,
42
+ "top5_unc": 0.258,
43
+ "rms": 7.338
 
 
44
  },
45
  "Qwen_IQ3_S": {
46
+ "ppl": 5.287517,
47
+ "ppl_unc": 0.383349,
48
+ "ppl_ratio": 1.025137,
49
+ "mean_kld": 0.043676,
50
+ "kld_unc": 0.003106,
51
+ "top1": 91.194,
52
+ "top1_unc": 0.887,
53
+ "top5": 99.706,
54
+ "top5_unc": 0.169,
55
+ "rms": 5.745
 
 
56
  }
57
  }
58
  },
59
  "codemath": {
60
  "name": "Code & Math",
61
  "bf16": {
62
+ "ppl": 1.670003,
63
+ "ppl_unc": 0.063744
 
64
  },
65
  "models": {
66
  "VeriLoop_IQ3_XXS": {
67
+ "ppl": 2.129404,
68
+ "ppl_unc": 0.105036,
69
+ "ppl_ratio": 1.27509,
70
+ "mean_kld": 0.256974,
71
+ "kld_unc": 0.020245,
72
+ "top1": 86.106,
73
+ "top1_unc": 1.082,
74
+ "top5": 98.728,
75
+ "top5_unc": 0.351,
76
+ "rms": 22.225
 
 
77
  },
78
  "VeriLoop_IQ3_S": {
79
+ "ppl": 1.779099,
80
+ "ppl_unc": 0.068721,
81
+ "ppl_ratio": 1.065326,
82
+ "mean_kld": 0.126346,
83
+ "kld_unc": 0.013601,
84
+ "top1": 91.292,
85
+ "top1_unc": 0.882,
86
+ "top5": 99.511,
87
+ "top5_unc": 0.218,
88
+ "rms": 15.189
 
 
89
  },
90
  "Qwen_IQ3_XXS": {
91
+ "ppl": 2.604939,
92
+ "ppl_unc": 0.161942,
93
+ "ppl_ratio": 1.559841,
94
+ "mean_kld": 0.42651,
95
+ "kld_unc": 0.037084,
96
+ "top1": 82.485,
97
+ "top1_unc": 1.19,
98
+ "top5": 96.771,
99
+ "top5_unc": 0.553,
100
+ "rms": 26.362
 
 
101
  },
102
  "Qwen_IQ3_S": {
103
+ "ppl": 2.286893,
104
+ "ppl_unc": 0.128775,
105
+ "ppl_ratio": 1.369394,
106
+ "mean_kld": 0.27297,
107
+ "kld_unc": 0.023905,
108
+ "top1": 85.812,
109
+ "top1_unc": 1.092,
110
+ "top5": 98.337,
111
+ "top5_unc": 0.4,
112
+ "rms": 22.573
 
 
113
  }
114
  }
115
  },
116
  "aime2025": {
117
  "name": "AIME 2025",
118
  "bf16": {
119
+ "ppl": 2.073159,
120
+ "ppl_unc": 0.093297
 
121
  },
122
  "models": {
123
  "VeriLoop_IQ3_XXS": {
124
+ "ppl": 2.142681,
125
+ "ppl_unc": 0.099012,
126
+ "ppl_ratio": 1.033534,
127
+ "mean_kld": 0.041285,
128
+ "kld_unc": 0.003125,
129
+ "top1": 94.227,
130
+ "top1_unc": 0.73,
131
+ "top5": 99.902,
132
+ "top5_unc": 0.098,
133
+ "rms": 7.302
 
 
134
  },
135
  "VeriLoop_IQ3_S": {
136
+ "ppl": 2.119914,
137
+ "ppl_unc": 0.097774,
138
+ "ppl_ratio": 1.022552,
139
+ "mean_kld": 0.025689,
140
+ "kld_unc": 0.001889,
141
+ "top1": 95.401,
142
+ "top1_unc": 0.656,
143
+ "top5": 99.804,
144
+ "top5_unc": 0.138,
145
+ "rms": 5.324
 
 
146
  },
147
  "Qwen_IQ3_XXS": {
148
+ "ppl": 2.196686,
149
+ "ppl_unc": 0.105841,
150
+ "ppl_ratio": 1.059584,
151
+ "mean_kld": 0.07322,
152
+ "kld_unc": 0.011335,
153
+ "top1": 93.151,
154
+ "top1_unc": 0.791,
155
+ "top5": 99.706,
156
+ "top5_unc": 0.169,
157
+ "rms": 10.09
 
 
158
  },
159
  "Qwen_IQ3_S": {
160
+ "ppl": 2.251226,
161
+ "ppl_unc": 0.112986,
162
+ "ppl_ratio": 1.085891,
163
+ "mean_kld": 0.090163,
164
+ "kld_unc": 0.014369,
165
+ "top1": 92.466,
166
+ "top1_unc": 0.826,
167
+ "top5": 99.413,
168
+ "top5_unc": 0.239,
169
+ "rms": 10.649
 
 
170
  }
171
  }
172
  },
173
  "livecode": {
174
  "name": "LiveCodeBench",
175
  "bf16": {
176
+ "ppl": 1.310318,
177
+ "ppl_unc": 0.044372
 
178
  },
179
  "models": {
180
  "VeriLoop_IQ3_XXS": {
181
+ "ppl": 1.50444,
182
+ "ppl_unc": 0.058624,
183
+ "ppl_ratio": 1.148149,
184
+ "mean_kld": 0.249568,
185
+ "kld_unc": 0.027405,
186
+ "top1": 91.781,
187
+ "top1_unc": 0.86,
188
+ "top5": 98.826,
189
+ "top5_unc": 0.337,
190
+ "rms": 20.829
 
 
191
  },
192
  "VeriLoop_IQ3_S": {
193
+ "ppl": 1.393964,
194
+ "ppl_unc": 0.050473,
195
+ "ppl_ratio": 1.063836,
196
+ "mean_kld": 0.158601,
197
+ "kld_unc": 0.020799,
198
+ "top1": 94.031,
199
+ "top1_unc": 0.741,
200
+ "top5": 100.0,
201
+ "top5_unc": 0.0,
202
+ "rms": 16.79
 
 
203
  },
204
  "Qwen_IQ3_XXS": {
205
+ "ppl": 1.846662,
206
+ "ppl_unc": 0.10329,
207
+ "ppl_ratio": 1.409323,
208
+ "mean_kld": 0.38225,
209
+ "kld_unc": 0.039303,
210
+ "top1": 89.041,
211
+ "top1_unc": 0.978,
212
+ "top5": 98.239,
213
+ "top5_unc": 0.412,
214
+ "rms": 25.883
 
 
215
  },
216
  "Qwen_IQ3_S": {
217
+ "ppl": 1.633881,
218
+ "ppl_unc": 0.07884,
219
+ "ppl_ratio": 1.246935,
220
+ "mean_kld": 0.266109,
221
+ "kld_unc": 0.029915,
222
+ "top1": 91.096,
223
+ "top1_unc": 0.891,
224
+ "top5": 98.728,
225
+ "top5_unc": 0.351,
226
+ "rms": 22.114
 
 
227
  }
228
  }
229
  },
230
  "terminal": {
231
  "name": "TerminalBench 2.1",
 
 
 
 
 
232
  "models": {
233
+ "VeriLoop_IQ3_XXS": {},
234
+ "VeriLoop_IQ3_S": {},
235
+ "Qwen_IQ3_XXS": {},
236
+ "Qwen_IQ3_S": {}
237
+ },
238
+ "bf16": {
239
+ "ppl": 2.15,
240
+ "ppl_unc": 0.08
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
241
  }
242
  }
243
  }