Upload eval_results/meta-llama/Llama-2-13b-chat-hf/main/agieval/results_2024-03-28T16-53-48.762881.json with huggingface_hub
Browse files
eval_results/meta-llama/Llama-2-13b-chat-hf/main/agieval/results_2024-03-28T16-53-48.762881.json
ADDED
@@ -0,0 +1,900 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config_general": {
|
3 |
+
"lighteval_sha": "?",
|
4 |
+
"num_fewshot_seeds": 1,
|
5 |
+
"override_batch_size": 1,
|
6 |
+
"max_samples": null,
|
7 |
+
"job_id": "",
|
8 |
+
"start_time": 8646774.98843263,
|
9 |
+
"end_time": 8647277.082037227,
|
10 |
+
"total_evaluation_time_secondes": "502.0936045963317",
|
11 |
+
"model_name": "meta-llama/Llama-2-13b-chat-hf",
|
12 |
+
"model_sha": "29655417e51232f4f2b9b5d3e1418e5a9b04e80e",
|
13 |
+
"model_dtype": "torch.bfloat16",
|
14 |
+
"model_size": "24.32 GB",
|
15 |
+
"config": null
|
16 |
+
},
|
17 |
+
"results": {
|
18 |
+
"lighteval|agieval:aqua-rat|0": {
|
19 |
+
"acc": 0.2047244094488189,
|
20 |
+
"acc_stderr": 0.02536783354473852,
|
21 |
+
"acc_norm": 0.2047244094488189,
|
22 |
+
"acc_norm_stderr": 0.02536783354473853
|
23 |
+
},
|
24 |
+
"lighteval|agieval:gaokao-biology|0": {
|
25 |
+
"acc": 0.28095238095238095,
|
26 |
+
"acc_stderr": 0.03109009446934462,
|
27 |
+
"acc_norm": 0.3142857142857143,
|
28 |
+
"acc_norm_stderr": 0.03211151353994384
|
29 |
+
},
|
30 |
+
"lighteval|agieval:gaokao-chemistry|0": {
|
31 |
+
"acc": 0.30917874396135264,
|
32 |
+
"acc_stderr": 0.03219986494000449,
|
33 |
+
"acc_norm": 0.2560386473429952,
|
34 |
+
"acc_norm_stderr": 0.03040845392239327
|
35 |
+
},
|
36 |
+
"lighteval|agieval:gaokao-chinese|0": {
|
37 |
+
"acc": 0.1991869918699187,
|
38 |
+
"acc_stderr": 0.025516024108089824,
|
39 |
+
"acc_norm": 0.21138211382113822,
|
40 |
+
"acc_norm_stderr": 0.02608461238305184
|
41 |
+
},
|
42 |
+
"lighteval|agieval:gaokao-english|0": {
|
43 |
+
"acc": 0.5490196078431373,
|
44 |
+
"acc_stderr": 0.02849199358617156,
|
45 |
+
"acc_norm": 0.4477124183006536,
|
46 |
+
"acc_norm_stderr": 0.028472938478033522
|
47 |
+
},
|
48 |
+
"lighteval|agieval:gaokao-geography|0": {
|
49 |
+
"acc": 0.3316582914572864,
|
50 |
+
"acc_stderr": 0.03345893526874066,
|
51 |
+
"acc_norm": 0.3015075376884422,
|
52 |
+
"acc_norm_stderr": 0.03261349587454653
|
53 |
+
},
|
54 |
+
"lighteval|agieval:gaokao-history|0": {
|
55 |
+
"acc": 0.33191489361702126,
|
56 |
+
"acc_stderr": 0.03078373675774565,
|
57 |
+
"acc_norm": 0.28936170212765955,
|
58 |
+
"acc_norm_stderr": 0.02964400657700962
|
59 |
+
},
|
60 |
+
"lighteval|agieval:gaokao-mathqa|0": {
|
61 |
+
"acc": 0.2706552706552707,
|
62 |
+
"acc_stderr": 0.023748744034266786,
|
63 |
+
"acc_norm": 0.2706552706552707,
|
64 |
+
"acc_norm_stderr": 0.023748744034266786
|
65 |
+
},
|
66 |
+
"lighteval|agieval:gaokao-physics|0": {
|
67 |
+
"acc": 0.27,
|
68 |
+
"acc_stderr": 0.03147145152843339,
|
69 |
+
"acc_norm": 0.315,
|
70 |
+
"acc_norm_stderr": 0.032928657464464904
|
71 |
+
},
|
72 |
+
"lighteval|agieval:logiqa-en|0": {
|
73 |
+
"acc": 0.3563748079877112,
|
74 |
+
"acc_stderr": 0.01878509246182,
|
75 |
+
"acc_norm": 0.3210445468509985,
|
76 |
+
"acc_norm_stderr": 0.01831245670147612
|
77 |
+
},
|
78 |
+
"lighteval|agieval:logiqa-zh|0": {
|
79 |
+
"acc": 0.26574500768049153,
|
80 |
+
"acc_stderr": 0.017326040808935687,
|
81 |
+
"acc_norm": 0.3333333333333333,
|
82 |
+
"acc_norm_stderr": 0.018490006540841045
|
83 |
+
},
|
84 |
+
"lighteval|agieval:lsat-ar|0": {
|
85 |
+
"acc": 0.21739130434782608,
|
86 |
+
"acc_stderr": 0.027256850838819964,
|
87 |
+
"acc_norm": 0.22608695652173913,
|
88 |
+
"acc_norm_stderr": 0.027641785707241334
|
89 |
+
},
|
90 |
+
"lighteval|agieval:lsat-lr|0": {
|
91 |
+
"acc": 0.3568627450980392,
|
92 |
+
"acc_stderr": 0.02123457379560983,
|
93 |
+
"acc_norm": 0.28823529411764703,
|
94 |
+
"acc_norm_stderr": 0.02007626467805952
|
95 |
+
},
|
96 |
+
"lighteval|agieval:lsat-rc|0": {
|
97 |
+
"acc": 0.4200743494423792,
|
98 |
+
"acc_stderr": 0.030149620080212006,
|
99 |
+
"acc_norm": 0.31226765799256506,
|
100 |
+
"acc_norm_stderr": 0.02830778120469435
|
101 |
+
},
|
102 |
+
"lighteval|agieval:sat-en|0": {
|
103 |
+
"acc": 0.6019417475728155,
|
104 |
+
"acc_stderr": 0.03418799390613399,
|
105 |
+
"acc_norm": 0.4077669902912621,
|
106 |
+
"acc_norm_stderr": 0.03432222290260263
|
107 |
+
},
|
108 |
+
"lighteval|agieval:sat-en-without-passage|0": {
|
109 |
+
"acc": 0.3640776699029126,
|
110 |
+
"acc_stderr": 0.03360641055142781,
|
111 |
+
"acc_norm": 0.25728155339805825,
|
112 |
+
"acc_norm_stderr": 0.030530892446123826
|
113 |
+
},
|
114 |
+
"lighteval|agieval:sat-math|0": {
|
115 |
+
"acc": 0.2863636363636364,
|
116 |
+
"acc_stderr": 0.030547478139694613,
|
117 |
+
"acc_norm": 0.2636363636363636,
|
118 |
+
"acc_norm_stderr": 0.02977328576472747
|
119 |
+
},
|
120 |
+
"lighteval|agieval:_average|0": {
|
121 |
+
"acc": 0.3303601093059411,
|
122 |
+
"acc_stderr": 0.027954278754128786,
|
123 |
+
"acc_norm": 0.2953129711654506,
|
124 |
+
"acc_norm_stderr": 0.0275785265743656
|
125 |
+
},
|
126 |
+
"all": {
|
127 |
+
"acc": 0.3303601093059411,
|
128 |
+
"acc_stderr": 0.027954278754128786,
|
129 |
+
"acc_norm": 0.2953129711654506,
|
130 |
+
"acc_norm_stderr": 0.0275785265743656
|
131 |
+
}
|
132 |
+
},
|
133 |
+
"versions": {
|
134 |
+
"lighteval|agieval:aqua-rat|0": 0,
|
135 |
+
"lighteval|agieval:gaokao-biology|0": 0,
|
136 |
+
"lighteval|agieval:gaokao-chemistry|0": 0,
|
137 |
+
"lighteval|agieval:gaokao-chinese|0": 0,
|
138 |
+
"lighteval|agieval:gaokao-english|0": 0,
|
139 |
+
"lighteval|agieval:gaokao-geography|0": 0,
|
140 |
+
"lighteval|agieval:gaokao-history|0": 0,
|
141 |
+
"lighteval|agieval:gaokao-mathqa|0": 0,
|
142 |
+
"lighteval|agieval:gaokao-physics|0": 0,
|
143 |
+
"lighteval|agieval:logiqa-en|0": 0,
|
144 |
+
"lighteval|agieval:logiqa-zh|0": 0,
|
145 |
+
"lighteval|agieval:lsat-ar|0": 0,
|
146 |
+
"lighteval|agieval:lsat-lr|0": 0,
|
147 |
+
"lighteval|agieval:lsat-rc|0": 0,
|
148 |
+
"lighteval|agieval:sat-en|0": 0,
|
149 |
+
"lighteval|agieval:sat-en-without-passage|0": 0,
|
150 |
+
"lighteval|agieval:sat-math|0": 0
|
151 |
+
},
|
152 |
+
"config_tasks": {
|
153 |
+
"lighteval|agieval:aqua-rat": {
|
154 |
+
"name": "agieval:aqua-rat",
|
155 |
+
"prompt_function": "agieval",
|
156 |
+
"hf_repo": "dmayhem93/agieval-aqua-rat",
|
157 |
+
"hf_subset": "default",
|
158 |
+
"metric": [
|
159 |
+
"loglikelihood_acc",
|
160 |
+
"loglikelihood_acc_norm_nospace"
|
161 |
+
],
|
162 |
+
"hf_avail_splits": [
|
163 |
+
"test"
|
164 |
+
],
|
165 |
+
"evaluation_splits": [
|
166 |
+
"test"
|
167 |
+
],
|
168 |
+
"few_shots_split": null,
|
169 |
+
"few_shots_select": "random_sampling",
|
170 |
+
"generation_size": 1,
|
171 |
+
"stop_sequence": null,
|
172 |
+
"output_regex": null,
|
173 |
+
"frozen": false,
|
174 |
+
"suite": [
|
175 |
+
"lighteval"
|
176 |
+
],
|
177 |
+
"original_num_docs": 254,
|
178 |
+
"effective_num_docs": 254,
|
179 |
+
"trust_dataset": true,
|
180 |
+
"must_remove_duplicate_docs": null
|
181 |
+
},
|
182 |
+
"lighteval|agieval:gaokao-biology": {
|
183 |
+
"name": "agieval:gaokao-biology",
|
184 |
+
"prompt_function": "agieval",
|
185 |
+
"hf_repo": "dmayhem93/agieval-gaokao-biology",
|
186 |
+
"hf_subset": "default",
|
187 |
+
"metric": [
|
188 |
+
"loglikelihood_acc",
|
189 |
+
"loglikelihood_acc_norm_nospace"
|
190 |
+
],
|
191 |
+
"hf_avail_splits": [
|
192 |
+
"test"
|
193 |
+
],
|
194 |
+
"evaluation_splits": [
|
195 |
+
"test"
|
196 |
+
],
|
197 |
+
"few_shots_split": null,
|
198 |
+
"few_shots_select": "random_sampling",
|
199 |
+
"generation_size": 1,
|
200 |
+
"stop_sequence": null,
|
201 |
+
"output_regex": null,
|
202 |
+
"frozen": false,
|
203 |
+
"suite": [
|
204 |
+
"lighteval"
|
205 |
+
],
|
206 |
+
"original_num_docs": 210,
|
207 |
+
"effective_num_docs": 210,
|
208 |
+
"trust_dataset": true,
|
209 |
+
"must_remove_duplicate_docs": null
|
210 |
+
},
|
211 |
+
"lighteval|agieval:gaokao-chemistry": {
|
212 |
+
"name": "agieval:gaokao-chemistry",
|
213 |
+
"prompt_function": "agieval",
|
214 |
+
"hf_repo": "dmayhem93/agieval-gaokao-chemistry",
|
215 |
+
"hf_subset": "default",
|
216 |
+
"metric": [
|
217 |
+
"loglikelihood_acc",
|
218 |
+
"loglikelihood_acc_norm_nospace"
|
219 |
+
],
|
220 |
+
"hf_avail_splits": [
|
221 |
+
"test"
|
222 |
+
],
|
223 |
+
"evaluation_splits": [
|
224 |
+
"test"
|
225 |
+
],
|
226 |
+
"few_shots_split": null,
|
227 |
+
"few_shots_select": "random_sampling",
|
228 |
+
"generation_size": 1,
|
229 |
+
"stop_sequence": null,
|
230 |
+
"output_regex": null,
|
231 |
+
"frozen": false,
|
232 |
+
"suite": [
|
233 |
+
"lighteval"
|
234 |
+
],
|
235 |
+
"original_num_docs": 207,
|
236 |
+
"effective_num_docs": 207,
|
237 |
+
"trust_dataset": true,
|
238 |
+
"must_remove_duplicate_docs": null
|
239 |
+
},
|
240 |
+
"lighteval|agieval:gaokao-chinese": {
|
241 |
+
"name": "agieval:gaokao-chinese",
|
242 |
+
"prompt_function": "agieval",
|
243 |
+
"hf_repo": "dmayhem93/agieval-gaokao-chinese",
|
244 |
+
"hf_subset": "default",
|
245 |
+
"metric": [
|
246 |
+
"loglikelihood_acc",
|
247 |
+
"loglikelihood_acc_norm_nospace"
|
248 |
+
],
|
249 |
+
"hf_avail_splits": [
|
250 |
+
"test"
|
251 |
+
],
|
252 |
+
"evaluation_splits": [
|
253 |
+
"test"
|
254 |
+
],
|
255 |
+
"few_shots_split": null,
|
256 |
+
"few_shots_select": "random_sampling",
|
257 |
+
"generation_size": 1,
|
258 |
+
"stop_sequence": null,
|
259 |
+
"output_regex": null,
|
260 |
+
"frozen": false,
|
261 |
+
"suite": [
|
262 |
+
"lighteval"
|
263 |
+
],
|
264 |
+
"original_num_docs": 246,
|
265 |
+
"effective_num_docs": 246,
|
266 |
+
"trust_dataset": true,
|
267 |
+
"must_remove_duplicate_docs": null
|
268 |
+
},
|
269 |
+
"lighteval|agieval:gaokao-english": {
|
270 |
+
"name": "agieval:gaokao-english",
|
271 |
+
"prompt_function": "agieval",
|
272 |
+
"hf_repo": "dmayhem93/agieval-gaokao-english",
|
273 |
+
"hf_subset": "default",
|
274 |
+
"metric": [
|
275 |
+
"loglikelihood_acc",
|
276 |
+
"loglikelihood_acc_norm_nospace"
|
277 |
+
],
|
278 |
+
"hf_avail_splits": [
|
279 |
+
"test"
|
280 |
+
],
|
281 |
+
"evaluation_splits": [
|
282 |
+
"test"
|
283 |
+
],
|
284 |
+
"few_shots_split": null,
|
285 |
+
"few_shots_select": "random_sampling",
|
286 |
+
"generation_size": 1,
|
287 |
+
"stop_sequence": null,
|
288 |
+
"output_regex": null,
|
289 |
+
"frozen": false,
|
290 |
+
"suite": [
|
291 |
+
"lighteval"
|
292 |
+
],
|
293 |
+
"original_num_docs": 306,
|
294 |
+
"effective_num_docs": 306,
|
295 |
+
"trust_dataset": true,
|
296 |
+
"must_remove_duplicate_docs": null
|
297 |
+
},
|
298 |
+
"lighteval|agieval:gaokao-geography": {
|
299 |
+
"name": "agieval:gaokao-geography",
|
300 |
+
"prompt_function": "agieval",
|
301 |
+
"hf_repo": "dmayhem93/agieval-gaokao-geography",
|
302 |
+
"hf_subset": "default",
|
303 |
+
"metric": [
|
304 |
+
"loglikelihood_acc",
|
305 |
+
"loglikelihood_acc_norm_nospace"
|
306 |
+
],
|
307 |
+
"hf_avail_splits": [
|
308 |
+
"test"
|
309 |
+
],
|
310 |
+
"evaluation_splits": [
|
311 |
+
"test"
|
312 |
+
],
|
313 |
+
"few_shots_split": null,
|
314 |
+
"few_shots_select": "random_sampling",
|
315 |
+
"generation_size": 1,
|
316 |
+
"stop_sequence": null,
|
317 |
+
"output_regex": null,
|
318 |
+
"frozen": false,
|
319 |
+
"suite": [
|
320 |
+
"lighteval"
|
321 |
+
],
|
322 |
+
"original_num_docs": 199,
|
323 |
+
"effective_num_docs": 199,
|
324 |
+
"trust_dataset": true,
|
325 |
+
"must_remove_duplicate_docs": null
|
326 |
+
},
|
327 |
+
"lighteval|agieval:gaokao-history": {
|
328 |
+
"name": "agieval:gaokao-history",
|
329 |
+
"prompt_function": "agieval",
|
330 |
+
"hf_repo": "dmayhem93/agieval-gaokao-history",
|
331 |
+
"hf_subset": "default",
|
332 |
+
"metric": [
|
333 |
+
"loglikelihood_acc",
|
334 |
+
"loglikelihood_acc_norm_nospace"
|
335 |
+
],
|
336 |
+
"hf_avail_splits": [
|
337 |
+
"test"
|
338 |
+
],
|
339 |
+
"evaluation_splits": [
|
340 |
+
"test"
|
341 |
+
],
|
342 |
+
"few_shots_split": null,
|
343 |
+
"few_shots_select": "random_sampling",
|
344 |
+
"generation_size": 1,
|
345 |
+
"stop_sequence": null,
|
346 |
+
"output_regex": null,
|
347 |
+
"frozen": false,
|
348 |
+
"suite": [
|
349 |
+
"lighteval"
|
350 |
+
],
|
351 |
+
"original_num_docs": 235,
|
352 |
+
"effective_num_docs": 235,
|
353 |
+
"trust_dataset": true,
|
354 |
+
"must_remove_duplicate_docs": null
|
355 |
+
},
|
356 |
+
"lighteval|agieval:gaokao-mathqa": {
|
357 |
+
"name": "agieval:gaokao-mathqa",
|
358 |
+
"prompt_function": "agieval",
|
359 |
+
"hf_repo": "dmayhem93/agieval-gaokao-mathqa",
|
360 |
+
"hf_subset": "default",
|
361 |
+
"metric": [
|
362 |
+
"loglikelihood_acc",
|
363 |
+
"loglikelihood_acc_norm_nospace"
|
364 |
+
],
|
365 |
+
"hf_avail_splits": [
|
366 |
+
"test"
|
367 |
+
],
|
368 |
+
"evaluation_splits": [
|
369 |
+
"test"
|
370 |
+
],
|
371 |
+
"few_shots_split": null,
|
372 |
+
"few_shots_select": "random_sampling",
|
373 |
+
"generation_size": 1,
|
374 |
+
"stop_sequence": null,
|
375 |
+
"output_regex": null,
|
376 |
+
"frozen": false,
|
377 |
+
"suite": [
|
378 |
+
"lighteval"
|
379 |
+
],
|
380 |
+
"original_num_docs": 351,
|
381 |
+
"effective_num_docs": 351,
|
382 |
+
"trust_dataset": true,
|
383 |
+
"must_remove_duplicate_docs": null
|
384 |
+
},
|
385 |
+
"lighteval|agieval:gaokao-physics": {
|
386 |
+
"name": "agieval:gaokao-physics",
|
387 |
+
"prompt_function": "agieval",
|
388 |
+
"hf_repo": "dmayhem93/agieval-gaokao-physics",
|
389 |
+
"hf_subset": "default",
|
390 |
+
"metric": [
|
391 |
+
"loglikelihood_acc",
|
392 |
+
"loglikelihood_acc_norm_nospace"
|
393 |
+
],
|
394 |
+
"hf_avail_splits": [
|
395 |
+
"test"
|
396 |
+
],
|
397 |
+
"evaluation_splits": [
|
398 |
+
"test"
|
399 |
+
],
|
400 |
+
"few_shots_split": null,
|
401 |
+
"few_shots_select": "random_sampling",
|
402 |
+
"generation_size": 1,
|
403 |
+
"stop_sequence": null,
|
404 |
+
"output_regex": null,
|
405 |
+
"frozen": false,
|
406 |
+
"suite": [
|
407 |
+
"lighteval"
|
408 |
+
],
|
409 |
+
"original_num_docs": 200,
|
410 |
+
"effective_num_docs": 200,
|
411 |
+
"trust_dataset": true,
|
412 |
+
"must_remove_duplicate_docs": null
|
413 |
+
},
|
414 |
+
"lighteval|agieval:logiqa-en": {
|
415 |
+
"name": "agieval:logiqa-en",
|
416 |
+
"prompt_function": "agieval",
|
417 |
+
"hf_repo": "dmayhem93/agieval-logiqa-en",
|
418 |
+
"hf_subset": "default",
|
419 |
+
"metric": [
|
420 |
+
"loglikelihood_acc",
|
421 |
+
"loglikelihood_acc_norm_nospace"
|
422 |
+
],
|
423 |
+
"hf_avail_splits": [
|
424 |
+
"test"
|
425 |
+
],
|
426 |
+
"evaluation_splits": [
|
427 |
+
"test"
|
428 |
+
],
|
429 |
+
"few_shots_split": null,
|
430 |
+
"few_shots_select": "random_sampling",
|
431 |
+
"generation_size": 1,
|
432 |
+
"stop_sequence": null,
|
433 |
+
"output_regex": null,
|
434 |
+
"frozen": false,
|
435 |
+
"suite": [
|
436 |
+
"lighteval"
|
437 |
+
],
|
438 |
+
"original_num_docs": 651,
|
439 |
+
"effective_num_docs": 651,
|
440 |
+
"trust_dataset": true,
|
441 |
+
"must_remove_duplicate_docs": null
|
442 |
+
},
|
443 |
+
"lighteval|agieval:logiqa-zh": {
|
444 |
+
"name": "agieval:logiqa-zh",
|
445 |
+
"prompt_function": "agieval",
|
446 |
+
"hf_repo": "dmayhem93/agieval-logiqa-zh",
|
447 |
+
"hf_subset": "default",
|
448 |
+
"metric": [
|
449 |
+
"loglikelihood_acc",
|
450 |
+
"loglikelihood_acc_norm_nospace"
|
451 |
+
],
|
452 |
+
"hf_avail_splits": [
|
453 |
+
"test"
|
454 |
+
],
|
455 |
+
"evaluation_splits": [
|
456 |
+
"test"
|
457 |
+
],
|
458 |
+
"few_shots_split": null,
|
459 |
+
"few_shots_select": "random_sampling",
|
460 |
+
"generation_size": 1,
|
461 |
+
"stop_sequence": null,
|
462 |
+
"output_regex": null,
|
463 |
+
"frozen": false,
|
464 |
+
"suite": [
|
465 |
+
"lighteval"
|
466 |
+
],
|
467 |
+
"original_num_docs": 651,
|
468 |
+
"effective_num_docs": 651,
|
469 |
+
"trust_dataset": true,
|
470 |
+
"must_remove_duplicate_docs": null
|
471 |
+
},
|
472 |
+
"lighteval|agieval:lsat-ar": {
|
473 |
+
"name": "agieval:lsat-ar",
|
474 |
+
"prompt_function": "agieval",
|
475 |
+
"hf_repo": "dmayhem93/agieval-lsat-ar",
|
476 |
+
"hf_subset": "default",
|
477 |
+
"metric": [
|
478 |
+
"loglikelihood_acc",
|
479 |
+
"loglikelihood_acc_norm_nospace"
|
480 |
+
],
|
481 |
+
"hf_avail_splits": [
|
482 |
+
"test"
|
483 |
+
],
|
484 |
+
"evaluation_splits": [
|
485 |
+
"test"
|
486 |
+
],
|
487 |
+
"few_shots_split": null,
|
488 |
+
"few_shots_select": "random_sampling",
|
489 |
+
"generation_size": 1,
|
490 |
+
"stop_sequence": null,
|
491 |
+
"output_regex": null,
|
492 |
+
"frozen": false,
|
493 |
+
"suite": [
|
494 |
+
"lighteval"
|
495 |
+
],
|
496 |
+
"original_num_docs": 230,
|
497 |
+
"effective_num_docs": 230,
|
498 |
+
"trust_dataset": true,
|
499 |
+
"must_remove_duplicate_docs": null
|
500 |
+
},
|
501 |
+
"lighteval|agieval:lsat-lr": {
|
502 |
+
"name": "agieval:lsat-lr",
|
503 |
+
"prompt_function": "agieval",
|
504 |
+
"hf_repo": "dmayhem93/agieval-lsat-lr",
|
505 |
+
"hf_subset": "default",
|
506 |
+
"metric": [
|
507 |
+
"loglikelihood_acc",
|
508 |
+
"loglikelihood_acc_norm_nospace"
|
509 |
+
],
|
510 |
+
"hf_avail_splits": [
|
511 |
+
"test"
|
512 |
+
],
|
513 |
+
"evaluation_splits": [
|
514 |
+
"test"
|
515 |
+
],
|
516 |
+
"few_shots_split": null,
|
517 |
+
"few_shots_select": "random_sampling",
|
518 |
+
"generation_size": 1,
|
519 |
+
"stop_sequence": null,
|
520 |
+
"output_regex": null,
|
521 |
+
"frozen": false,
|
522 |
+
"suite": [
|
523 |
+
"lighteval"
|
524 |
+
],
|
525 |
+
"original_num_docs": 510,
|
526 |
+
"effective_num_docs": 510,
|
527 |
+
"trust_dataset": true,
|
528 |
+
"must_remove_duplicate_docs": null
|
529 |
+
},
|
530 |
+
"lighteval|agieval:lsat-rc": {
|
531 |
+
"name": "agieval:lsat-rc",
|
532 |
+
"prompt_function": "agieval",
|
533 |
+
"hf_repo": "dmayhem93/agieval-lsat-rc",
|
534 |
+
"hf_subset": "default",
|
535 |
+
"metric": [
|
536 |
+
"loglikelihood_acc",
|
537 |
+
"loglikelihood_acc_norm_nospace"
|
538 |
+
],
|
539 |
+
"hf_avail_splits": [
|
540 |
+
"test"
|
541 |
+
],
|
542 |
+
"evaluation_splits": [
|
543 |
+
"test"
|
544 |
+
],
|
545 |
+
"few_shots_split": null,
|
546 |
+
"few_shots_select": "random_sampling",
|
547 |
+
"generation_size": 1,
|
548 |
+
"stop_sequence": null,
|
549 |
+
"output_regex": null,
|
550 |
+
"frozen": false,
|
551 |
+
"suite": [
|
552 |
+
"lighteval"
|
553 |
+
],
|
554 |
+
"original_num_docs": 269,
|
555 |
+
"effective_num_docs": 269,
|
556 |
+
"trust_dataset": true,
|
557 |
+
"must_remove_duplicate_docs": null
|
558 |
+
},
|
559 |
+
"lighteval|agieval:sat-en": {
|
560 |
+
"name": "agieval:sat-en",
|
561 |
+
"prompt_function": "agieval",
|
562 |
+
"hf_repo": "dmayhem93/agieval-sat-en",
|
563 |
+
"hf_subset": "default",
|
564 |
+
"metric": [
|
565 |
+
"loglikelihood_acc",
|
566 |
+
"loglikelihood_acc_norm_nospace"
|
567 |
+
],
|
568 |
+
"hf_avail_splits": [
|
569 |
+
"test"
|
570 |
+
],
|
571 |
+
"evaluation_splits": [
|
572 |
+
"test"
|
573 |
+
],
|
574 |
+
"few_shots_split": null,
|
575 |
+
"few_shots_select": "random_sampling",
|
576 |
+
"generation_size": 1,
|
577 |
+
"stop_sequence": null,
|
578 |
+
"output_regex": null,
|
579 |
+
"frozen": false,
|
580 |
+
"suite": [
|
581 |
+
"lighteval"
|
582 |
+
],
|
583 |
+
"original_num_docs": 206,
|
584 |
+
"effective_num_docs": 206,
|
585 |
+
"trust_dataset": true,
|
586 |
+
"must_remove_duplicate_docs": null
|
587 |
+
},
|
588 |
+
"lighteval|agieval:sat-en-without-passage": {
|
589 |
+
"name": "agieval:sat-en-without-passage",
|
590 |
+
"prompt_function": "agieval",
|
591 |
+
"hf_repo": "dmayhem93/agieval-sat-en-without-passage",
|
592 |
+
"hf_subset": "default",
|
593 |
+
"metric": [
|
594 |
+
"loglikelihood_acc",
|
595 |
+
"loglikelihood_acc_norm_nospace"
|
596 |
+
],
|
597 |
+
"hf_avail_splits": [
|
598 |
+
"test"
|
599 |
+
],
|
600 |
+
"evaluation_splits": [
|
601 |
+
"test"
|
602 |
+
],
|
603 |
+
"few_shots_split": null,
|
604 |
+
"few_shots_select": "random_sampling",
|
605 |
+
"generation_size": 1,
|
606 |
+
"stop_sequence": null,
|
607 |
+
"output_regex": null,
|
608 |
+
"frozen": false,
|
609 |
+
"suite": [
|
610 |
+
"lighteval"
|
611 |
+
],
|
612 |
+
"original_num_docs": 206,
|
613 |
+
"effective_num_docs": 206,
|
614 |
+
"trust_dataset": true,
|
615 |
+
"must_remove_duplicate_docs": null
|
616 |
+
},
|
617 |
+
"lighteval|agieval:sat-math": {
|
618 |
+
"name": "agieval:sat-math",
|
619 |
+
"prompt_function": "agieval",
|
620 |
+
"hf_repo": "dmayhem93/agieval-sat-math",
|
621 |
+
"hf_subset": "default",
|
622 |
+
"metric": [
|
623 |
+
"loglikelihood_acc",
|
624 |
+
"loglikelihood_acc_norm_nospace"
|
625 |
+
],
|
626 |
+
"hf_avail_splits": [
|
627 |
+
"test"
|
628 |
+
],
|
629 |
+
"evaluation_splits": [
|
630 |
+
"test"
|
631 |
+
],
|
632 |
+
"few_shots_split": null,
|
633 |
+
"few_shots_select": "random_sampling",
|
634 |
+
"generation_size": 1,
|
635 |
+
"stop_sequence": null,
|
636 |
+
"output_regex": null,
|
637 |
+
"frozen": false,
|
638 |
+
"suite": [
|
639 |
+
"lighteval"
|
640 |
+
],
|
641 |
+
"original_num_docs": 220,
|
642 |
+
"effective_num_docs": 220,
|
643 |
+
"trust_dataset": true,
|
644 |
+
"must_remove_duplicate_docs": null
|
645 |
+
}
|
646 |
+
},
|
647 |
+
"summary_tasks": {
|
648 |
+
"lighteval|agieval:aqua-rat|0": {
|
649 |
+
"hashes": {
|
650 |
+
"hash_examples": "f09607f69e5b7525",
|
651 |
+
"hash_full_prompts": "3861b27efd5a6170",
|
652 |
+
"hash_input_tokens": "b81ddf32d9e36b1f",
|
653 |
+
"hash_cont_tokens": "d68d99aa7aafcf10"
|
654 |
+
},
|
655 |
+
"truncated": 0,
|
656 |
+
"non_truncated": 254,
|
657 |
+
"padded": 1270,
|
658 |
+
"non_padded": 0,
|
659 |
+
"effective_few_shots": 0.0,
|
660 |
+
"num_truncated_few_shots": 0
|
661 |
+
},
|
662 |
+
"lighteval|agieval:gaokao-biology|0": {
|
663 |
+
"hashes": {
|
664 |
+
"hash_examples": "f262eaf4a72db963",
|
665 |
+
"hash_full_prompts": "1ef14dcf5933ff33",
|
666 |
+
"hash_input_tokens": "0e02a46ea2b2e076",
|
667 |
+
"hash_cont_tokens": "fb818e5d1e6cfaf9"
|
668 |
+
},
|
669 |
+
"truncated": 0,
|
670 |
+
"non_truncated": 210,
|
671 |
+
"padded": 840,
|
672 |
+
"non_padded": 0,
|
673 |
+
"effective_few_shots": 0.0,
|
674 |
+
"num_truncated_few_shots": 0
|
675 |
+
},
|
676 |
+
"lighteval|agieval:gaokao-chemistry|0": {
|
677 |
+
"hashes": {
|
678 |
+
"hash_examples": "47f2e649f58d9da5",
|
679 |
+
"hash_full_prompts": "324a4d07d3b7de40",
|
680 |
+
"hash_input_tokens": "ab927b5975095914",
|
681 |
+
"hash_cont_tokens": "cae820a904612b14"
|
682 |
+
},
|
683 |
+
"truncated": 0,
|
684 |
+
"non_truncated": 207,
|
685 |
+
"padded": 831,
|
686 |
+
"non_padded": 0,
|
687 |
+
"effective_few_shots": 0.0,
|
688 |
+
"num_truncated_few_shots": 0
|
689 |
+
},
|
690 |
+
"lighteval|agieval:gaokao-chinese|0": {
|
691 |
+
"hashes": {
|
692 |
+
"hash_examples": "1010b21fde4726ab",
|
693 |
+
"hash_full_prompts": "938611fd6ecdbf4e",
|
694 |
+
"hash_input_tokens": "72d5df618421255b",
|
695 |
+
"hash_cont_tokens": "4f99bcd4d0795887"
|
696 |
+
},
|
697 |
+
"truncated": 0,
|
698 |
+
"non_truncated": 246,
|
699 |
+
"padded": 979,
|
700 |
+
"non_padded": 5,
|
701 |
+
"effective_few_shots": 0.0,
|
702 |
+
"num_truncated_few_shots": 0
|
703 |
+
},
|
704 |
+
"lighteval|agieval:gaokao-english|0": {
|
705 |
+
"hashes": {
|
706 |
+
"hash_examples": "4864e492a350ae93",
|
707 |
+
"hash_full_prompts": "2cff929f74eb0813",
|
708 |
+
"hash_input_tokens": "364e98db90c628be",
|
709 |
+
"hash_cont_tokens": "8b0fdf9d99f09625"
|
710 |
+
},
|
711 |
+
"truncated": 0,
|
712 |
+
"non_truncated": 306,
|
713 |
+
"padded": 1217,
|
714 |
+
"non_padded": 7,
|
715 |
+
"effective_few_shots": 0.0,
|
716 |
+
"num_truncated_few_shots": 0
|
717 |
+
},
|
718 |
+
"lighteval|agieval:gaokao-geography|0": {
|
719 |
+
"hashes": {
|
720 |
+
"hash_examples": "ec3a021e37650e7d",
|
721 |
+
"hash_full_prompts": "79c20e1e52638229",
|
722 |
+
"hash_input_tokens": "fb6db8d803e25b33",
|
723 |
+
"hash_cont_tokens": "0144954f291c77ff"
|
724 |
+
},
|
725 |
+
"truncated": 0,
|
726 |
+
"non_truncated": 199,
|
727 |
+
"padded": 796,
|
728 |
+
"non_padded": 0,
|
729 |
+
"effective_few_shots": 0.0,
|
730 |
+
"num_truncated_few_shots": 0
|
731 |
+
},
|
732 |
+
"lighteval|agieval:gaokao-history|0": {
|
733 |
+
"hashes": {
|
734 |
+
"hash_examples": "b3fad1596f1ae1f9",
|
735 |
+
"hash_full_prompts": "541c270a0bbab3fd",
|
736 |
+
"hash_input_tokens": "4461fd574f259120",
|
737 |
+
"hash_cont_tokens": "f7f0c87190e11336"
|
738 |
+
},
|
739 |
+
"truncated": 0,
|
740 |
+
"non_truncated": 235,
|
741 |
+
"padded": 940,
|
742 |
+
"non_padded": 0,
|
743 |
+
"effective_few_shots": 0.0,
|
744 |
+
"num_truncated_few_shots": 0
|
745 |
+
},
|
746 |
+
"lighteval|agieval:gaokao-mathqa|0": {
|
747 |
+
"hashes": {
|
748 |
+
"hash_examples": "1d1088556861b0b0",
|
749 |
+
"hash_full_prompts": "6002200193304ad6",
|
750 |
+
"hash_input_tokens": "e6fb6d8930aa10fa",
|
751 |
+
"hash_cont_tokens": "1c92bd434c8ca7cf"
|
752 |
+
},
|
753 |
+
"truncated": 0,
|
754 |
+
"non_truncated": 351,
|
755 |
+
"padded": 1404,
|
756 |
+
"non_padded": 0,
|
757 |
+
"effective_few_shots": 0.0,
|
758 |
+
"num_truncated_few_shots": 0
|
759 |
+
},
|
760 |
+
"lighteval|agieval:gaokao-physics|0": {
|
761 |
+
"hashes": {
|
762 |
+
"hash_examples": "eb05f035c7bfca2f",
|
763 |
+
"hash_full_prompts": "7b606fe0e48d1136",
|
764 |
+
"hash_input_tokens": "1c39aecbf26045ac",
|
765 |
+
"hash_cont_tokens": "2c78afa11a936dc4"
|
766 |
+
},
|
767 |
+
"truncated": 0,
|
768 |
+
"non_truncated": 200,
|
769 |
+
"padded": 800,
|
770 |
+
"non_padded": 0,
|
771 |
+
"effective_few_shots": 0.0,
|
772 |
+
"num_truncated_few_shots": 0
|
773 |
+
},
|
774 |
+
"lighteval|agieval:logiqa-en|0": {
|
775 |
+
"hashes": {
|
776 |
+
"hash_examples": "0a688a45f69c21e0",
|
777 |
+
"hash_full_prompts": "70df665a01ea64f7",
|
778 |
+
"hash_input_tokens": "61f22bb8a98d5e05",
|
779 |
+
"hash_cont_tokens": "1c7594dbf0a0a533"
|
780 |
+
},
|
781 |
+
"truncated": 0,
|
782 |
+
"non_truncated": 651,
|
783 |
+
"padded": 2588,
|
784 |
+
"non_padded": 16,
|
785 |
+
"effective_few_shots": 0.0,
|
786 |
+
"num_truncated_few_shots": 0
|
787 |
+
},
|
788 |
+
"lighteval|agieval:logiqa-zh|0": {
|
789 |
+
"hashes": {
|
790 |
+
"hash_examples": "620d6888b6012ea5",
|
791 |
+
"hash_full_prompts": "79066930a44b0f7e",
|
792 |
+
"hash_input_tokens": "2fe19dd623007024",
|
793 |
+
"hash_cont_tokens": "16ad57705a79dec4"
|
794 |
+
},
|
795 |
+
"truncated": 0,
|
796 |
+
"non_truncated": 651,
|
797 |
+
"padded": 2585,
|
798 |
+
"non_padded": 19,
|
799 |
+
"effective_few_shots": 0.0,
|
800 |
+
"num_truncated_few_shots": 0
|
801 |
+
},
|
802 |
+
"lighteval|agieval:lsat-ar|0": {
|
803 |
+
"hashes": {
|
804 |
+
"hash_examples": "627c8f5ccd5da209",
|
805 |
+
"hash_full_prompts": "254286f37d4a76ce",
|
806 |
+
"hash_input_tokens": "dcb768476dabfd30",
|
807 |
+
"hash_cont_tokens": "32e72f9ac5e990db"
|
808 |
+
},
|
809 |
+
"truncated": 0,
|
810 |
+
"non_truncated": 230,
|
811 |
+
"padded": 1139,
|
812 |
+
"non_padded": 11,
|
813 |
+
"effective_few_shots": 0.0,
|
814 |
+
"num_truncated_few_shots": 0
|
815 |
+
},
|
816 |
+
"lighteval|agieval:lsat-lr|0": {
|
817 |
+
"hashes": {
|
818 |
+
"hash_examples": "794641c86de172f5",
|
819 |
+
"hash_full_prompts": "cf1badbb8c42f6a8",
|
820 |
+
"hash_input_tokens": "f46eacac0dc8f43d",
|
821 |
+
"hash_cont_tokens": "f59d4751382d6cd2"
|
822 |
+
},
|
823 |
+
"truncated": 0,
|
824 |
+
"non_truncated": 510,
|
825 |
+
"padded": 2527,
|
826 |
+
"non_padded": 23,
|
827 |
+
"effective_few_shots": 0.0,
|
828 |
+
"num_truncated_few_shots": 0
|
829 |
+
},
|
830 |
+
"lighteval|agieval:lsat-rc|0": {
|
831 |
+
"hashes": {
|
832 |
+
"hash_examples": "35981ed917ea01cf",
|
833 |
+
"hash_full_prompts": "5fbc2eae9474469b",
|
834 |
+
"hash_input_tokens": "29375d042cf27c7e",
|
835 |
+
"hash_cont_tokens": "3e5cd22ff2929a47"
|
836 |
+
},
|
837 |
+
"truncated": 0,
|
838 |
+
"non_truncated": 269,
|
839 |
+
"padded": 1345,
|
840 |
+
"non_padded": 0,
|
841 |
+
"effective_few_shots": 0.0,
|
842 |
+
"num_truncated_few_shots": 0
|
843 |
+
},
|
844 |
+
"lighteval|agieval:sat-en|0": {
|
845 |
+
"hashes": {
|
846 |
+
"hash_examples": "041c39c646536a1e",
|
847 |
+
"hash_full_prompts": "171c266251542e36",
|
848 |
+
"hash_input_tokens": "1ad83cc18fd43db0",
|
849 |
+
"hash_cont_tokens": "3bc244ff75c1a591"
|
850 |
+
},
|
851 |
+
"truncated": 0,
|
852 |
+
"non_truncated": 206,
|
853 |
+
"padded": 821,
|
854 |
+
"non_padded": 0,
|
855 |
+
"effective_few_shots": 0.0,
|
856 |
+
"num_truncated_few_shots": 0
|
857 |
+
},
|
858 |
+
"lighteval|agieval:sat-en-without-passage|0": {
|
859 |
+
"hashes": {
|
860 |
+
"hash_examples": "e4d9284367dff68f",
|
861 |
+
"hash_full_prompts": "66bc76f2704c6ca7",
|
862 |
+
"hash_input_tokens": "afd505d4ceeeaa45",
|
863 |
+
"hash_cont_tokens": "3bc244ff75c1a591"
|
864 |
+
},
|
865 |
+
"truncated": 0,
|
866 |
+
"non_truncated": 206,
|
867 |
+
"padded": 821,
|
868 |
+
"non_padded": 0,
|
869 |
+
"effective_few_shots": 0.0,
|
870 |
+
"num_truncated_few_shots": 0
|
871 |
+
},
|
872 |
+
"lighteval|agieval:sat-math|0": {
|
873 |
+
"hashes": {
|
874 |
+
"hash_examples": "01db7291603fc1a0",
|
875 |
+
"hash_full_prompts": "6016bbecd8642dbe",
|
876 |
+
"hash_input_tokens": "86192e0452c1707e",
|
877 |
+
"hash_cont_tokens": "5175b61accc0c5d1"
|
878 |
+
},
|
879 |
+
"truncated": 0,
|
880 |
+
"non_truncated": 220,
|
881 |
+
"padded": 879,
|
882 |
+
"non_padded": 1,
|
883 |
+
"effective_few_shots": 0.0,
|
884 |
+
"num_truncated_few_shots": 0
|
885 |
+
}
|
886 |
+
},
|
887 |
+
"summary_general": {
|
888 |
+
"hashes": {
|
889 |
+
"hash_examples": "da3af66181f18ddf",
|
890 |
+
"hash_full_prompts": "3554a21b6b69cbf8",
|
891 |
+
"hash_input_tokens": "4abd38d6a674e0cd",
|
892 |
+
"hash_cont_tokens": "0fc139d3b2070461"
|
893 |
+
},
|
894 |
+
"truncated": 0,
|
895 |
+
"non_truncated": 5151,
|
896 |
+
"padded": 21782,
|
897 |
+
"non_padded": 82,
|
898 |
+
"num_truncated_few_shots": 0
|
899 |
+
}
|
900 |
+
}
|