hevok commited on
Commit
b61868f
·
verified ·
1 Parent(s): 078ead7

Upload folder using huggingface_hub

Browse files
lm_eval/RWKV-x060-World-1B6-v2.1-20240328-ctx4096/pad_11/0.4.8_2025-03-17T00-03-49.169695_xnli.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/models/RWKV-x060-World-1B6-v2.1-20240328-ctx4096",
3
+ "tasks": [
4
+ "xnli"
5
+ ],
6
+ "num_fewshot": 0,
7
+ "lm_eval_version": "0.4.8",
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "custom_prefix_token_id": 11,
11
+ "pad_token_ids": [
12
+ 11
13
+ ],
14
+ "stop_token_ids": [
15
+ 11,
16
+ 261
17
+ ],
18
+ "results": {
19
+ "xnli": {
20
+ "acc,none": 0.41370816599732263,
21
+ "acc_stderr,none": 0.0025309792751254667,
22
+ "alias": "xnli"
23
+ },
24
+ "xnli_ar": {
25
+ "alias": " - xnli_ar",
26
+ "acc,none": 0.3429718875502008,
27
+ "acc_stderr,none": 0.00951499993403346
28
+ },
29
+ "xnli_bg": {
30
+ "alias": " - xnli_bg",
31
+ "acc,none": 0.42610441767068274,
32
+ "acc_stderr,none": 0.009912016377459065
33
+ },
34
+ "xnli_de": {
35
+ "alias": " - xnli_de",
36
+ "acc,none": 0.4759036144578313,
37
+ "acc_stderr,none": 0.010010427753210675
38
+ },
39
+ "xnli_el": {
40
+ "alias": " - xnli_el",
41
+ "acc,none": 0.3783132530120482,
42
+ "acc_stderr,none": 0.009720735678557153
43
+ },
44
+ "xnli_en": {
45
+ "alias": " - xnli_en",
46
+ "acc,none": 0.5413654618473895,
47
+ "acc_stderr,none": 0.009987716412406583
48
+ },
49
+ "xnli_es": {
50
+ "alias": " - xnli_es",
51
+ "acc,none": 0.46626506024096387,
52
+ "acc_stderr,none": 0.009999235684721615
53
+ },
54
+ "xnli_fr": {
55
+ "alias": " - xnli_fr",
56
+ "acc,none": 0.4815261044176707,
57
+ "acc_stderr,none": 0.01001522976835699
58
+ },
59
+ "xnli_hi": {
60
+ "alias": " - xnli_hi",
61
+ "acc,none": 0.3891566265060241,
62
+ "acc_stderr,none": 0.009772702993836016
63
+ },
64
+ "xnli_ru": {
65
+ "alias": " - xnli_ru",
66
+ "acc,none": 0.4497991967871486,
67
+ "acc_stderr,none": 0.00997143125556017
68
+ },
69
+ "xnli_sw": {
70
+ "alias": " - xnli_sw",
71
+ "acc,none": 0.3465863453815261,
72
+ "acc_stderr,none": 0.009538660220458997
73
+ },
74
+ "xnli_th": {
75
+ "alias": " - xnli_th",
76
+ "acc,none": 0.41004016064257026,
77
+ "acc_stderr,none": 0.009858525713807856
78
+ },
79
+ "xnli_tr": {
80
+ "alias": " - xnli_tr",
81
+ "acc,none": 0.3823293172690763,
82
+ "acc_stderr,none": 0.009740580649033707
83
+ },
84
+ "xnli_ur": {
85
+ "alias": " - xnli_ur",
86
+ "acc,none": 0.3465863453815261,
87
+ "acc_stderr,none": 0.009538660220458992
88
+ },
89
+ "xnli_vi": {
90
+ "alias": " - xnli_vi",
91
+ "acc,none": 0.4248995983935743,
92
+ "acc_stderr,none": 0.0099083775681982
93
+ },
94
+ "xnli_zh": {
95
+ "alias": " - xnli_zh",
96
+ "acc,none": 0.3437751004016064,
97
+ "acc_stderr,none": 0.009520310502882937
98
+ }
99
+ }
100
+ }
lm_eval/RWKV-x060-World-1B6-v2.1-20240328-ctx4096/pad_11/0.4.8_2025-03-17T01-28-38.097947_xstorycloze.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/models/RWKV-x060-World-1B6-v2.1-20240328-ctx4096",
3
+ "tasks": [
4
+ "xstorycloze"
5
+ ],
6
+ "num_fewshot": 0,
7
+ "lm_eval_version": "0.4.8",
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "custom_prefix_token_id": 11,
11
+ "pad_token_ids": [
12
+ 11
13
+ ],
14
+ "stop_token_ids": [
15
+ 11,
16
+ 261
17
+ ],
18
+ "results": {
19
+ "xstorycloze": {
20
+ "acc,none": 0.5823957643944407,
21
+ "acc_stderr,none": 0.0037925764585649427,
22
+ "alias": "xstorycloze"
23
+ },
24
+ "xstorycloze_ar": {
25
+ "alias": " - xstorycloze_ar",
26
+ "acc,none": 0.5519523494374586,
27
+ "acc_stderr,none": 0.012797478885304733
28
+ },
29
+ "xstorycloze_en": {
30
+ "alias": " - xstorycloze_en",
31
+ "acc,none": 0.7352746525479815,
32
+ "acc_stderr,none": 0.01135361301038959
33
+ },
34
+ "xstorycloze_es": {
35
+ "alias": " - xstorycloze_es",
36
+ "acc,none": 0.6406353408338848,
37
+ "acc_stderr,none": 0.012347659802101674
38
+ },
39
+ "xstorycloze_eu": {
40
+ "alias": " - xstorycloze_eu",
41
+ "acc,none": 0.5334215751158173,
42
+ "acc_stderr,none": 0.012838347934731667
43
+ },
44
+ "xstorycloze_hi": {
45
+ "alias": " - xstorycloze_hi",
46
+ "acc,none": 0.5473196558570483,
47
+ "acc_stderr,none": 0.012809372866181954
48
+ },
49
+ "xstorycloze_id": {
50
+ "alias": " - xstorycloze_id",
51
+ "acc,none": 0.6101919258769027,
52
+ "acc_stderr,none": 0.012550764190647008
53
+ },
54
+ "xstorycloze_my": {
55
+ "alias": " - xstorycloze_my",
56
+ "acc,none": 0.49106551952349436,
57
+ "acc_stderr,none": 0.0128650709173208
58
+ },
59
+ "xstorycloze_ru": {
60
+ "alias": " - xstorycloze_ru",
61
+ "acc,none": 0.6201191264063534,
62
+ "acc_stderr,none": 0.012490298101718166
63
+ },
64
+ "xstorycloze_sw": {
65
+ "alias": " - xstorycloze_sw",
66
+ "acc,none": 0.5188616810059563,
67
+ "acc_stderr,none": 0.012857966762464994
68
+ },
69
+ "xstorycloze_te": {
70
+ "alias": " - xstorycloze_te",
71
+ "acc,none": 0.5526141628060887,
72
+ "acc_stderr,none": 0.012795688167385279
73
+ },
74
+ "xstorycloze_zh": {
75
+ "alias": " - xstorycloze_zh",
76
+ "acc,none": 0.6048974189278623,
77
+ "acc_stderr,none": 0.01258077297613326
78
+ }
79
+ }
80
+ }
lm_eval/RWKV-x060-World-1B6-v2.1-20240328-ctx4096/pad_11/0.4.8_2025-03-17T01-36-06.458772_xwinograd.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/models/RWKV-x060-World-1B6-v2.1-20240328-ctx4096",
3
+ "tasks": [
4
+ "xwinograd"
5
+ ],
6
+ "num_fewshot": 0,
7
+ "lm_eval_version": "0.4.8",
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "custom_prefix_token_id": 11,
11
+ "pad_token_ids": [
12
+ 11
13
+ ],
14
+ "stop_token_ids": [
15
+ 11,
16
+ 261
17
+ ],
18
+ "results": {
19
+ "xwinograd": {
20
+ "acc,none": 0.7651157563497415,
21
+ "acc_stderr,none": 0.006252314857589183,
22
+ "alias": "xwinograd"
23
+ },
24
+ "xwinograd_en": {
25
+ "alias": " - xwinograd_en",
26
+ "acc,none": 0.8344086021505376,
27
+ "acc_stderr,none": 0.00771063615962449
28
+ },
29
+ "xwinograd_fr": {
30
+ "alias": " - xwinograd_fr",
31
+ "acc,none": 0.6987951807228916,
32
+ "acc_stderr,none": 0.0506639425494172
33
+ },
34
+ "xwinograd_jp": {
35
+ "alias": " - xwinograd_jp",
36
+ "acc,none": 0.6673618352450469,
37
+ "acc_stderr,none": 0.015222429340088765
38
+ },
39
+ "xwinograd_pt": {
40
+ "alias": " - xwinograd_pt",
41
+ "acc,none": 0.6730038022813688,
42
+ "acc_stderr,none": 0.028982074243683254
43
+ },
44
+ "xwinograd_ru": {
45
+ "alias": " - xwinograd_ru",
46
+ "acc,none": 0.653968253968254,
47
+ "acc_stderr,none": 0.02684549902197288
48
+ },
49
+ "xwinograd_zh": {
50
+ "alias": " - xwinograd_zh",
51
+ "acc,none": 0.7599206349206349,
52
+ "acc_stderr,none": 0.019044849417856065
53
+ }
54
+ }
55
+ }
lm_eval/RWKV-x060-World-1B6-v2.1-20240328-ctx4096/pad_11/0.4.8_2025-03-17T11-13-00.537290_mmlu.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/models/RWKV-x060-World-1B6-v2.1-20240328-ctx4096",
3
+ "tasks": [
4
+ "mmlu"
5
+ ],
6
+ "num_fewshot": 5,
7
+ "lm_eval_version": "0.4.8",
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "custom_prefix_token_id": null,
11
+ "pad_token_ids": [
12
+ 11
13
+ ],
14
+ "stop_token_ids": [
15
+ 11,
16
+ 261
17
+ ],
18
+ "results": {
19
+ "mmlu": {
20
+ "acc,none": 0.2508901865831078,
21
+ "acc_stderr,none": 0.00365623049621683,
22
+ "alias": "mmlu"
23
+ },
24
+ "mmlu_humanities": {
25
+ "acc,none": 0.2452709883103082,
26
+ "acc_stderr,none": 0.006270950553728565,
27
+ "alias": " - humanities"
28
+ },
29
+ "mmlu_formal_logic": {
30
+ "alias": " - formal_logic",
31
+ "acc,none": 0.29365079365079366,
32
+ "acc_stderr,none": 0.04073524322147127
33
+ },
34
+ "mmlu_high_school_european_history": {
35
+ "alias": " - high_school_european_history",
36
+ "acc,none": 0.32727272727272727,
37
+ "acc_stderr,none": 0.03663974994391242
38
+ },
39
+ "mmlu_high_school_us_history": {
40
+ "alias": " - high_school_us_history",
41
+ "acc,none": 0.20098039215686275,
42
+ "acc_stderr,none": 0.028125972265654373
43
+ },
44
+ "mmlu_high_school_world_history": {
45
+ "alias": " - high_school_world_history",
46
+ "acc,none": 0.2742616033755274,
47
+ "acc_stderr,none": 0.029041333510598025
48
+ },
49
+ "mmlu_international_law": {
50
+ "alias": " - international_law",
51
+ "acc,none": 0.19834710743801653,
52
+ "acc_stderr,none": 0.03640118271990947
53
+ },
54
+ "mmlu_jurisprudence": {
55
+ "alias": " - jurisprudence",
56
+ "acc,none": 0.24074074074074073,
57
+ "acc_stderr,none": 0.041331194402438376
58
+ },
59
+ "mmlu_logical_fallacies": {
60
+ "alias": " - logical_fallacies",
61
+ "acc,none": 0.2822085889570552,
62
+ "acc_stderr,none": 0.03536117886664743
63
+ },
64
+ "mmlu_moral_disputes": {
65
+ "alias": " - moral_disputes",
66
+ "acc,none": 0.2398843930635838,
67
+ "acc_stderr,none": 0.02298959254312356
68
+ },
69
+ "mmlu_moral_scenarios": {
70
+ "alias": " - moral_scenarios",
71
+ "acc,none": 0.2424581005586592,
72
+ "acc_stderr,none": 0.014333522059217887
73
+ },
74
+ "mmlu_philosophy": {
75
+ "alias": " - philosophy",
76
+ "acc,none": 0.21543408360128619,
77
+ "acc_stderr,none": 0.02335022547547142
78
+ },
79
+ "mmlu_prehistory": {
80
+ "alias": " - prehistory",
81
+ "acc,none": 0.25,
82
+ "acc_stderr,none": 0.02409347123262133
83
+ },
84
+ "mmlu_professional_law": {
85
+ "alias": " - professional_law",
86
+ "acc,none": 0.24119947848761408,
87
+ "acc_stderr,none": 0.010926496102034956
88
+ },
89
+ "mmlu_world_religions": {
90
+ "alias": " - world_religions",
91
+ "acc,none": 0.25146198830409355,
92
+ "acc_stderr,none": 0.033275044238468436
93
+ },
94
+ "mmlu_other": {
95
+ "acc,none": 0.26746057289990344,
96
+ "acc_stderr,none": 0.007934731141101426,
97
+ "alias": " - other"
98
+ },
99
+ "mmlu_business_ethics": {
100
+ "alias": " - business_ethics",
101
+ "acc,none": 0.33,
102
+ "acc_stderr,none": 0.047258156262526045
103
+ },
104
+ "mmlu_clinical_knowledge": {
105
+ "alias": " - clinical_knowledge",
106
+ "acc,none": 0.2490566037735849,
107
+ "acc_stderr,none": 0.0266164829805017
108
+ },
109
+ "mmlu_college_medicine": {
110
+ "alias": " - college_medicine",
111
+ "acc,none": 0.31213872832369943,
112
+ "acc_stderr,none": 0.035331333893236574
113
+ },
114
+ "mmlu_global_facts": {
115
+ "alias": " - global_facts",
116
+ "acc,none": 0.39,
117
+ "acc_stderr,none": 0.04902071300001975
118
+ },
119
+ "mmlu_human_aging": {
120
+ "alias": " - human_aging",
121
+ "acc,none": 0.22869955156950672,
122
+ "acc_stderr,none": 0.028188240046929186
123
+ },
124
+ "mmlu_management": {
125
+ "alias": " - management",
126
+ "acc,none": 0.24271844660194175,
127
+ "acc_stderr,none": 0.042450224863844935
128
+ },
129
+ "mmlu_marketing": {
130
+ "alias": " - marketing",
131
+ "acc,none": 0.24786324786324787,
132
+ "acc_stderr,none": 0.028286324075564404
133
+ },
134
+ "mmlu_medical_genetics": {
135
+ "alias": " - medical_genetics",
136
+ "acc,none": 0.27,
137
+ "acc_stderr,none": 0.0446196043338474
138
+ },
139
+ "mmlu_miscellaneous": {
140
+ "alias": " - miscellaneous",
141
+ "acc,none": 0.25798212005108556,
142
+ "acc_stderr,none": 0.01564583018834895
143
+ },
144
+ "mmlu_nutrition": {
145
+ "alias": " - nutrition",
146
+ "acc,none": 0.2777777777777778,
147
+ "acc_stderr,none": 0.02564686309713791
148
+ },
149
+ "mmlu_professional_accounting": {
150
+ "alias": " - professional_accounting",
151
+ "acc,none": 0.23404255319148937,
152
+ "acc_stderr,none": 0.025257861359432424
153
+ },
154
+ "mmlu_professional_medicine": {
155
+ "alias": " - professional_medicine",
156
+ "acc,none": 0.27205882352941174,
157
+ "acc_stderr,none": 0.027033041151681456
158
+ },
159
+ "mmlu_virology": {
160
+ "alias": " - virology",
161
+ "acc,none": 0.3072289156626506,
162
+ "acc_stderr,none": 0.035915667978246635
163
+ },
164
+ "mmlu_social_sciences": {
165
+ "acc,none": 0.23626909327266818,
166
+ "acc_stderr,none": 0.007654663504823933,
167
+ "alias": " - social sciences"
168
+ },
169
+ "mmlu_econometrics": {
170
+ "alias": " - econometrics",
171
+ "acc,none": 0.2631578947368421,
172
+ "acc_stderr,none": 0.0414243971948936
173
+ },
174
+ "mmlu_high_school_geography": {
175
+ "alias": " - high_school_geography",
176
+ "acc,none": 0.22727272727272727,
177
+ "acc_stderr,none": 0.029857515673386417
178
+ },
179
+ "mmlu_high_school_government_and_politics": {
180
+ "alias": " - high_school_government_and_politics",
181
+ "acc,none": 0.24352331606217617,
182
+ "acc_stderr,none": 0.030975436386845443
183
+ },
184
+ "mmlu_high_school_macroeconomics": {
185
+ "alias": " - high_school_macroeconomics",
186
+ "acc,none": 0.23846153846153847,
187
+ "acc_stderr,none": 0.021606294494647727
188
+ },
189
+ "mmlu_high_school_microeconomics": {
190
+ "alias": " - high_school_microeconomics",
191
+ "acc,none": 0.2857142857142857,
192
+ "acc_stderr,none": 0.02934457250063432
193
+ },
194
+ "mmlu_high_school_psychology": {
195
+ "alias": " - high_school_psychology",
196
+ "acc,none": 0.21100917431192662,
197
+ "acc_stderr,none": 0.017493922404112648
198
+ },
199
+ "mmlu_human_sexuality": {
200
+ "alias": " - human_sexuality",
201
+ "acc,none": 0.22900763358778625,
202
+ "acc_stderr,none": 0.036853466317118506
203
+ },
204
+ "mmlu_professional_psychology": {
205
+ "alias": " - professional_psychology",
206
+ "acc,none": 0.2222222222222222,
207
+ "acc_stderr,none": 0.016819028375736383
208
+ },
209
+ "mmlu_public_relations": {
210
+ "alias": " - public_relations",
211
+ "acc,none": 0.34545454545454546,
212
+ "acc_stderr,none": 0.04554619617541054
213
+ },
214
+ "mmlu_security_studies": {
215
+ "alias": " - security_studies",
216
+ "acc,none": 0.21224489795918366,
217
+ "acc_stderr,none": 0.026176967197866767
218
+ },
219
+ "mmlu_sociology": {
220
+ "alias": " - sociology",
221
+ "acc,none": 0.24378109452736318,
222
+ "acc_stderr,none": 0.03036049015401464
223
+ },
224
+ "mmlu_us_foreign_policy": {
225
+ "alias": " - us_foreign_policy",
226
+ "acc,none": 0.24,
227
+ "acc_stderr,none": 0.04292346959909283
228
+ },
229
+ "mmlu_stem": {
230
+ "acc,none": 0.2572153504598795,
231
+ "acc_stderr,none": 0.007787146376816209,
232
+ "alias": " - stem"
233
+ },
234
+ "mmlu_abstract_algebra": {
235
+ "alias": " - abstract_algebra",
236
+ "acc,none": 0.21,
237
+ "acc_stderr,none": 0.04093601807403326
238
+ },
239
+ "mmlu_anatomy": {
240
+ "alias": " - anatomy",
241
+ "acc,none": 0.22962962962962963,
242
+ "acc_stderr,none": 0.03633384414073465
243
+ },
244
+ "mmlu_astronomy": {
245
+ "alias": " - astronomy",
246
+ "acc,none": 0.23026315789473684,
247
+ "acc_stderr,none": 0.034260594244031654
248
+ },
249
+ "mmlu_college_biology": {
250
+ "alias": " - college_biology",
251
+ "acc,none": 0.2638888888888889,
252
+ "acc_stderr,none": 0.03685651095897532
253
+ },
254
+ "mmlu_college_chemistry": {
255
+ "alias": " - college_chemistry",
256
+ "acc,none": 0.26,
257
+ "acc_stderr,none": 0.044084400227680794
258
+ },
259
+ "mmlu_college_computer_science": {
260
+ "alias": " - college_computer_science",
261
+ "acc,none": 0.28,
262
+ "acc_stderr,none": 0.04512608598542128
263
+ },
264
+ "mmlu_college_mathematics": {
265
+ "alias": " - college_mathematics",
266
+ "acc,none": 0.24,
267
+ "acc_stderr,none": 0.04292346959909283
268
+ },
269
+ "mmlu_college_physics": {
270
+ "alias": " - college_physics",
271
+ "acc,none": 0.29411764705882354,
272
+ "acc_stderr,none": 0.04533838195929777
273
+ },
274
+ "mmlu_computer_security": {
275
+ "alias": " - computer_security",
276
+ "acc,none": 0.31,
277
+ "acc_stderr,none": 0.04648231987117316
278
+ },
279
+ "mmlu_conceptual_physics": {
280
+ "alias": " - conceptual_physics",
281
+ "acc,none": 0.2425531914893617,
282
+ "acc_stderr,none": 0.028020226271200217
283
+ },
284
+ "mmlu_electrical_engineering": {
285
+ "alias": " - electrical_engineering",
286
+ "acc,none": 0.2620689655172414,
287
+ "acc_stderr,none": 0.036646663372252565
288
+ },
289
+ "mmlu_elementary_mathematics": {
290
+ "alias": " - elementary_mathematics",
291
+ "acc,none": 0.24867724867724866,
292
+ "acc_stderr,none": 0.022261817692400192
293
+ },
294
+ "mmlu_high_school_biology": {
295
+ "alias": " - high_school_biology",
296
+ "acc,none": 0.29354838709677417,
297
+ "acc_stderr,none": 0.02590608702131929
298
+ },
299
+ "mmlu_high_school_chemistry": {
300
+ "alias": " - high_school_chemistry",
301
+ "acc,none": 0.22660098522167488,
302
+ "acc_stderr,none": 0.02945486383529297
303
+ },
304
+ "mmlu_high_school_computer_science": {
305
+ "alias": " - high_school_computer_science",
306
+ "acc,none": 0.23,
307
+ "acc_stderr,none": 0.042295258468165044
308
+ },
309
+ "mmlu_high_school_mathematics": {
310
+ "alias": " - high_school_mathematics",
311
+ "acc,none": 0.22592592592592592,
312
+ "acc_stderr,none": 0.025497532639609546
313
+ },
314
+ "mmlu_high_school_physics": {
315
+ "alias": " - high_school_physics",
316
+ "acc,none": 0.33112582781456956,
317
+ "acc_stderr,none": 0.038425817186598696
318
+ },
319
+ "mmlu_high_school_statistics": {
320
+ "alias": " - high_school_statistics",
321
+ "acc,none": 0.24074074074074073,
322
+ "acc_stderr,none": 0.029157522184605617
323
+ },
324
+ "mmlu_machine_learning": {
325
+ "alias": " - machine_learning",
326
+ "acc,none": 0.3125,
327
+ "acc_stderr,none": 0.043994650575715215
328
+ }
329
+ }
330
+ }
lm_eval/RWKV-x060-World-3B-v2.1-20240417-ctx4096/pad_11/0.4.8_2025-03-17T01-14-51.366696_mmlu.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/models/RWKV-x060-World-3B-v2.1-20240417-ctx4096.pth",
3
+ "tasks": [
4
+ "mmlu"
5
+ ],
6
+ "num_fewshot": 5,
7
+ "lm_eval_version": "0.4.8",
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "custom_prefix_token_id": 11,
11
+ "pad_token_ids": [
12
+ 11
13
+ ],
14
+ "stop_token_ids": [
15
+ 11,
16
+ 261
17
+ ],
18
+ "results": {
19
+ "mmlu": {
20
+ "acc,none": 0.28300811850163793,
21
+ "acc_stderr,none": 0.0037926401279525677,
22
+ "alias": "mmlu"
23
+ },
24
+ "mmlu_humanities": {
25
+ "acc,none": 0.29330499468650373,
26
+ "acc_stderr,none": 0.00661831036231422,
27
+ "alias": " - humanities"
28
+ },
29
+ "mmlu_formal_logic": {
30
+ "alias": " - formal_logic",
31
+ "acc,none": 0.23809523809523808,
32
+ "acc_stderr,none": 0.03809523809523811
33
+ },
34
+ "mmlu_high_school_european_history": {
35
+ "alias": " - high_school_european_history",
36
+ "acc,none": 0.37575757575757573,
37
+ "acc_stderr,none": 0.03781887353205982
38
+ },
39
+ "mmlu_high_school_us_history": {
40
+ "alias": " - high_school_us_history",
41
+ "acc,none": 0.29411764705882354,
42
+ "acc_stderr,none": 0.031980016601150726
43
+ },
44
+ "mmlu_high_school_world_history": {
45
+ "alias": " - high_school_world_history",
46
+ "acc,none": 0.2616033755274262,
47
+ "acc_stderr,none": 0.028609516716994934
48
+ },
49
+ "mmlu_international_law": {
50
+ "alias": " - international_law",
51
+ "acc,none": 0.38016528925619836,
52
+ "acc_stderr,none": 0.04431324501968432
53
+ },
54
+ "mmlu_jurisprudence": {
55
+ "alias": " - jurisprudence",
56
+ "acc,none": 0.2777777777777778,
57
+ "acc_stderr,none": 0.04330043749650741
58
+ },
59
+ "mmlu_logical_fallacies": {
60
+ "alias": " - logical_fallacies",
61
+ "acc,none": 0.3312883435582822,
62
+ "acc_stderr,none": 0.03697983910025588
63
+ },
64
+ "mmlu_moral_disputes": {
65
+ "alias": " - moral_disputes",
66
+ "acc,none": 0.3063583815028902,
67
+ "acc_stderr,none": 0.024818350129436596
68
+ },
69
+ "mmlu_moral_scenarios": {
70
+ "alias": " - moral_scenarios",
71
+ "acc,none": 0.2324022346368715,
72
+ "acc_stderr,none": 0.014125968754673403
73
+ },
74
+ "mmlu_philosophy": {
75
+ "alias": " - philosophy",
76
+ "acc,none": 0.33762057877813506,
77
+ "acc_stderr,none": 0.02685882587948854
78
+ },
79
+ "mmlu_prehistory": {
80
+ "alias": " - prehistory",
81
+ "acc,none": 0.3425925925925926,
82
+ "acc_stderr,none": 0.02640614597362568
83
+ },
84
+ "mmlu_professional_law": {
85
+ "alias": " - professional_law",
86
+ "acc,none": 0.2907431551499348,
87
+ "acc_stderr,none": 0.011598062372851981
88
+ },
89
+ "mmlu_world_religions": {
90
+ "alias": " - world_religions",
91
+ "acc,none": 0.3508771929824561,
92
+ "acc_stderr,none": 0.03660298834049163
93
+ },
94
+ "mmlu_other": {
95
+ "acc,none": 0.28451882845188287,
96
+ "acc_stderr,none": 0.008058064756071836,
97
+ "alias": " - other"
98
+ },
99
+ "mmlu_business_ethics": {
100
+ "alias": " - business_ethics",
101
+ "acc,none": 0.32,
102
+ "acc_stderr,none": 0.046882617226215034
103
+ },
104
+ "mmlu_clinical_knowledge": {
105
+ "alias": " - clinical_knowledge",
106
+ "acc,none": 0.24150943396226415,
107
+ "acc_stderr,none": 0.02634148037111836
108
+ },
109
+ "mmlu_college_medicine": {
110
+ "alias": " - college_medicine",
111
+ "acc,none": 0.2543352601156069,
112
+ "acc_stderr,none": 0.0332055644308557
113
+ },
114
+ "mmlu_global_facts": {
115
+ "alias": " - global_facts",
116
+ "acc,none": 0.32,
117
+ "acc_stderr,none": 0.04688261722621505
118
+ },
119
+ "mmlu_human_aging": {
120
+ "alias": " - human_aging",
121
+ "acc,none": 0.2242152466367713,
122
+ "acc_stderr,none": 0.02799153425851952
123
+ },
124
+ "mmlu_management": {
125
+ "alias": " - management",
126
+ "acc,none": 0.20388349514563106,
127
+ "acc_stderr,none": 0.0398913985953177
128
+ },
129
+ "mmlu_marketing": {
130
+ "alias": " - marketing",
131
+ "acc,none": 0.3247863247863248,
132
+ "acc_stderr,none": 0.030679022765498835
133
+ },
134
+ "mmlu_medical_genetics": {
135
+ "alias": " - medical_genetics",
136
+ "acc,none": 0.19,
137
+ "acc_stderr,none": 0.03942772444036623
138
+ },
139
+ "mmlu_miscellaneous": {
140
+ "alias": " - miscellaneous",
141
+ "acc,none": 0.351213282247765,
142
+ "acc_stderr,none": 0.01706998205149943
143
+ },
144
+ "mmlu_nutrition": {
145
+ "alias": " - nutrition",
146
+ "acc,none": 0.29411764705882354,
147
+ "acc_stderr,none": 0.026090162504279046
148
+ },
149
+ "mmlu_professional_accounting": {
150
+ "alias": " - professional_accounting",
151
+ "acc,none": 0.2765957446808511,
152
+ "acc_stderr,none": 0.026684564340461
153
+ },
154
+ "mmlu_professional_medicine": {
155
+ "alias": " - professional_medicine",
156
+ "acc,none": 0.22794117647058823,
157
+ "acc_stderr,none": 0.025483081468029804
158
+ },
159
+ "mmlu_virology": {
160
+ "alias": " - virology",
161
+ "acc,none": 0.2469879518072289,
162
+ "acc_stderr,none": 0.03357351982064536
163
+ },
164
+ "mmlu_social_sciences": {
165
+ "acc,none": 0.27494312642183943,
166
+ "acc_stderr,none": 0.008044129845426675,
167
+ "alias": " - social sciences"
168
+ },
169
+ "mmlu_econometrics": {
170
+ "alias": " - econometrics",
171
+ "acc,none": 0.24561403508771928,
172
+ "acc_stderr,none": 0.040493392977481425
173
+ },
174
+ "mmlu_high_school_geography": {
175
+ "alias": " - high_school_geography",
176
+ "acc,none": 0.29797979797979796,
177
+ "acc_stderr,none": 0.03258630383836556
178
+ },
179
+ "mmlu_high_school_government_and_politics": {
180
+ "alias": " - high_school_government_and_politics",
181
+ "acc,none": 0.31088082901554404,
182
+ "acc_stderr,none": 0.03340361906276586
183
+ },
184
+ "mmlu_high_school_macroeconomics": {
185
+ "alias": " - high_school_macroeconomics",
186
+ "acc,none": 0.22564102564102564,
187
+ "acc_stderr,none": 0.021193632525148533
188
+ },
189
+ "mmlu_high_school_microeconomics": {
190
+ "alias": " - high_school_microeconomics",
191
+ "acc,none": 0.23529411764705882,
192
+ "acc_stderr,none": 0.02755361446786379
193
+ },
194
+ "mmlu_high_school_psychology": {
195
+ "alias": " - high_school_psychology",
196
+ "acc,none": 0.27155963302752295,
197
+ "acc_stderr,none": 0.019069098363191445
198
+ },
199
+ "mmlu_human_sexuality": {
200
+ "alias": " - human_sexuality",
201
+ "acc,none": 0.2900763358778626,
202
+ "acc_stderr,none": 0.03980066246467766
203
+ },
204
+ "mmlu_professional_psychology": {
205
+ "alias": " - professional_psychology",
206
+ "acc,none": 0.29248366013071897,
207
+ "acc_stderr,none": 0.01840341571010978
208
+ },
209
+ "mmlu_public_relations": {
210
+ "alias": " - public_relations",
211
+ "acc,none": 0.36363636363636365,
212
+ "acc_stderr,none": 0.046075820907199756
213
+ },
214
+ "mmlu_security_studies": {
215
+ "alias": " - security_studies",
216
+ "acc,none": 0.2612244897959184,
217
+ "acc_stderr,none": 0.028123429335142787
218
+ },
219
+ "mmlu_sociology": {
220
+ "alias": " - sociology",
221
+ "acc,none": 0.3034825870646766,
222
+ "acc_stderr,none": 0.03251006816458619
223
+ },
224
+ "mmlu_us_foreign_policy": {
225
+ "alias": " - us_foreign_policy",
226
+ "acc,none": 0.25,
227
+ "acc_stderr,none": 0.04351941398892446
228
+ },
229
+ "mmlu_stem": {
230
+ "acc,none": 0.27402473834443386,
231
+ "acc_stderr,none": 0.007942050435080712,
232
+ "alias": " - stem"
233
+ },
234
+ "mmlu_abstract_algebra": {
235
+ "alias": " - abstract_algebra",
236
+ "acc,none": 0.23,
237
+ "acc_stderr,none": 0.042295258468165065
238
+ },
239
+ "mmlu_anatomy": {
240
+ "alias": " - anatomy",
241
+ "acc,none": 0.35555555555555557,
242
+ "acc_stderr,none": 0.04135176749720386
243
+ },
244
+ "mmlu_astronomy": {
245
+ "alias": " - astronomy",
246
+ "acc,none": 0.2894736842105263,
247
+ "acc_stderr,none": 0.03690677986137282
248
+ },
249
+ "mmlu_college_biology": {
250
+ "alias": " - college_biology",
251
+ "acc,none": 0.2777777777777778,
252
+ "acc_stderr,none": 0.03745554791462457
253
+ },
254
+ "mmlu_college_chemistry": {
255
+ "alias": " - college_chemistry",
256
+ "acc,none": 0.19,
257
+ "acc_stderr,none": 0.039427724440366234
258
+ },
259
+ "mmlu_college_computer_science": {
260
+ "alias": " - college_computer_science",
261
+ "acc,none": 0.27,
262
+ "acc_stderr,none": 0.0446196043338474
263
+ },
264
+ "mmlu_college_mathematics": {
265
+ "alias": " - college_mathematics",
266
+ "acc,none": 0.26,
267
+ "acc_stderr,none": 0.0440844002276808
268
+ },
269
+ "mmlu_college_physics": {
270
+ "alias": " - college_physics",
271
+ "acc,none": 0.21568627450980393,
272
+ "acc_stderr,none": 0.04092563958237656
273
+ },
274
+ "mmlu_computer_security": {
275
+ "alias": " - computer_security",
276
+ "acc,none": 0.31,
277
+ "acc_stderr,none": 0.04648231987117316
278
+ },
279
+ "mmlu_conceptual_physics": {
280
+ "alias": " - conceptual_physics",
281
+ "acc,none": 0.2425531914893617,
282
+ "acc_stderr,none": 0.028020226271200217
283
+ },
284
+ "mmlu_electrical_engineering": {
285
+ "alias": " - electrical_engineering",
286
+ "acc,none": 0.3103448275862069,
287
+ "acc_stderr,none": 0.038552896163789485
288
+ },
289
+ "mmlu_elementary_mathematics": {
290
+ "alias": " - elementary_mathematics",
291
+ "acc,none": 0.2698412698412698,
292
+ "acc_stderr,none": 0.022860838309232072
293
+ },
294
+ "mmlu_high_school_biology": {
295
+ "alias": " - high_school_biology",
296
+ "acc,none": 0.2870967741935484,
297
+ "acc_stderr,none": 0.02573654274559452
298
+ },
299
+ "mmlu_high_school_chemistry": {
300
+ "alias": " - high_school_chemistry",
301
+ "acc,none": 0.30049261083743845,
302
+ "acc_stderr,none": 0.03225799476233485
303
+ },
304
+ "mmlu_high_school_computer_science": {
305
+ "alias": " - high_school_computer_science",
306
+ "acc,none": 0.33,
307
+ "acc_stderr,none": 0.047258156262526045
308
+ },
309
+ "mmlu_high_school_mathematics": {
310
+ "alias": " - high_school_mathematics",
311
+ "acc,none": 0.25925925925925924,
312
+ "acc_stderr,none": 0.026719240783712184
313
+ },
314
+ "mmlu_high_school_physics": {
315
+ "alias": " - high_school_physics",
316
+ "acc,none": 0.2913907284768212,
317
+ "acc_stderr,none": 0.03710185726119994
318
+ },
319
+ "mmlu_high_school_statistics": {
320
+ "alias": " - high_school_statistics",
321
+ "acc,none": 0.22685185185185186,
322
+ "acc_stderr,none": 0.028561650102422263
323
+ },
324
+ "mmlu_machine_learning": {
325
+ "alias": " - machine_learning",
326
+ "acc,none": 0.30357142857142855,
327
+ "acc_stderr,none": 0.04364226155841044
328
+ }
329
+ }
330
+ }