Skip to content

Commit 82a2a14

Browse files
More F2LLM-v2 results (#527)
* eng_v1, 80m * eng_v1, 160m-14b * law, 80m * law, 160m-8b * law, 14b * remaining results * update model meta
1 parent 63d7bae commit 82a2a14

944 files changed

Lines changed: 162714 additions & 8906 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.
Lines changed: 166 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,166 @@
1+
{
2+
"dataset_revision": "4106e6bcc72e0698d714ea8b101355e3e238431a",
3+
"task_name": "AILACasedocs",
4+
"mteb_version": "2.6.7",
5+
"scores": {
6+
"test": [
7+
{
8+
"ndcg_at_1": 0.4,
9+
"ndcg_at_3": 0.36511,
10+
"ndcg_at_5": 0.38301,
11+
"ndcg_at_10": 0.41093,
12+
"ndcg_at_20": 0.4343,
13+
"ndcg_at_100": 0.53255,
14+
"ndcg_at_1000": 0.54859,
15+
"map_at_1": 0.15126,
16+
"map_at_3": 0.22727,
17+
"map_at_5": 0.27242,
18+
"map_at_10": 0.31095,
19+
"map_at_20": 0.32082,
20+
"map_at_100": 0.3455,
21+
"map_at_1000": 0.34756,
22+
"recall_at_1": 0.15126,
23+
"recall_at_3": 0.26497,
24+
"recall_at_5": 0.36384,
25+
"recall_at_10": 0.47524,
26+
"recall_at_20": 0.55726,
27+
"recall_at_100": 0.91651,
28+
"recall_at_1000": 1.0,
29+
"accuracy": 0.15126,
30+
"precision_at_1": 0.4,
31+
"precision_at_3": 0.28667,
32+
"precision_at_5": 0.248,
33+
"precision_at_10": 0.172,
34+
"precision_at_20": 0.1,
35+
"precision_at_100": 0.036,
36+
"precision_at_1000": 0.0039,
37+
"mrr_at_1": 0.4,
38+
"mrr_at_3": 0.476667,
39+
"mrr_at_5": 0.489667,
40+
"mrr_at_10": 0.50369,
41+
"mrr_at_20": 0.509391,
42+
"mrr_at_100": 0.513302,
43+
"mrr_at_1000": 0.513562,
44+
"nauc_ndcg_at_1_max": 0.468383,
45+
"nauc_ndcg_at_1_std": -0.027034,
46+
"nauc_ndcg_at_1_diff1": 0.274022,
47+
"nauc_ndcg_at_3_max": 0.517913,
48+
"nauc_ndcg_at_3_std": -0.046652,
49+
"nauc_ndcg_at_3_diff1": 0.331869,
50+
"nauc_ndcg_at_5_max": 0.477423,
51+
"nauc_ndcg_at_5_std": 0.061527,
52+
"nauc_ndcg_at_5_diff1": 0.326106,
53+
"nauc_ndcg_at_10_max": 0.505209,
54+
"nauc_ndcg_at_10_std": 0.036154,
55+
"nauc_ndcg_at_10_diff1": 0.357014,
56+
"nauc_ndcg_at_20_max": 0.499644,
57+
"nauc_ndcg_at_20_std": 0.112534,
58+
"nauc_ndcg_at_20_diff1": 0.29871,
59+
"nauc_ndcg_at_100_max": 0.476105,
60+
"nauc_ndcg_at_100_std": 0.083023,
61+
"nauc_ndcg_at_100_diff1": 0.323535,
62+
"nauc_ndcg_at_1000_max": 0.484464,
63+
"nauc_ndcg_at_1000_std": 0.05137,
64+
"nauc_ndcg_at_1000_diff1": 0.329496,
65+
"nauc_map_at_1_max": 0.28733,
66+
"nauc_map_at_1_std": -0.079886,
67+
"nauc_map_at_1_diff1": 0.387813,
68+
"nauc_map_at_3_max": 0.414421,
69+
"nauc_map_at_3_std": -0.102055,
70+
"nauc_map_at_3_diff1": 0.41573,
71+
"nauc_map_at_5_max": 0.44536,
72+
"nauc_map_at_5_std": -0.013916,
73+
"nauc_map_at_5_diff1": 0.383886,
74+
"nauc_map_at_10_max": 0.51143,
75+
"nauc_map_at_10_std": -0.005299,
76+
"nauc_map_at_10_diff1": 0.36328,
77+
"nauc_map_at_20_max": 0.511559,
78+
"nauc_map_at_20_std": 0.024793,
79+
"nauc_map_at_20_diff1": 0.341675,
80+
"nauc_map_at_100_max": 0.503906,
81+
"nauc_map_at_100_std": 0.023126,
82+
"nauc_map_at_100_diff1": 0.34094,
83+
"nauc_map_at_1000_max": 0.505134,
84+
"nauc_map_at_1000_std": 0.020682,
85+
"nauc_map_at_1000_diff1": 0.343698,
86+
"nauc_recall_at_1_max": 0.28733,
87+
"nauc_recall_at_1_std": -0.079886,
88+
"nauc_recall_at_1_diff1": 0.387813,
89+
"nauc_recall_at_3_max": 0.367768,
90+
"nauc_recall_at_3_std": -0.0684,
91+
"nauc_recall_at_3_diff1": 0.39776,
92+
"nauc_recall_at_5_max": 0.361188,
93+
"nauc_recall_at_5_std": 0.154026,
94+
"nauc_recall_at_5_diff1": 0.296032,
95+
"nauc_recall_at_10_max": 0.43057,
96+
"nauc_recall_at_10_std": 0.098937,
97+
"nauc_recall_at_10_diff1": 0.2973,
98+
"nauc_recall_at_20_max": 0.365265,
99+
"nauc_recall_at_20_std": 0.325892,
100+
"nauc_recall_at_20_diff1": 0.102912,
101+
"nauc_recall_at_100_max": 0.221687,
102+
"nauc_recall_at_100_std": 0.591706,
103+
"nauc_recall_at_100_diff1": 0.225906,
104+
"nauc_recall_at_1000_max": NaN,
105+
"nauc_recall_at_1000_std": NaN,
106+
"nauc_recall_at_1000_diff1": NaN,
107+
"nauc_precision_at_1_max": 0.468383,
108+
"nauc_precision_at_1_std": -0.027034,
109+
"nauc_precision_at_1_diff1": 0.274022,
110+
"nauc_precision_at_3_max": 0.518877,
111+
"nauc_precision_at_3_std": 0.001021,
112+
"nauc_precision_at_3_diff1": 0.226489,
113+
"nauc_precision_at_5_max": 0.49305,
114+
"nauc_precision_at_5_std": 0.13996,
115+
"nauc_precision_at_5_diff1": 0.165585,
116+
"nauc_precision_at_10_max": 0.50381,
117+
"nauc_precision_at_10_std": 0.103586,
118+
"nauc_precision_at_10_diff1": 0.106033,
119+
"nauc_precision_at_20_max": 0.442222,
120+
"nauc_precision_at_20_std": 0.198639,
121+
"nauc_precision_at_20_diff1": 0.007087,
122+
"nauc_precision_at_100_max": 0.143766,
123+
"nauc_precision_at_100_std": 0.065557,
124+
"nauc_precision_at_100_diff1": 0.013013,
125+
"nauc_precision_at_1000_max": 0.12908,
126+
"nauc_precision_at_1000_std": 0.022807,
127+
"nauc_precision_at_1000_diff1": 0.029306,
128+
"nauc_mrr_at_1_max": 0.468383,
129+
"nauc_mrr_at_1_std": -0.027034,
130+
"nauc_mrr_at_1_diff1": 0.274022,
131+
"nauc_mrr_at_3_max": 0.438641,
132+
"nauc_mrr_at_3_std": 0.007315,
133+
"nauc_mrr_at_3_diff1": 0.300607,
134+
"nauc_mrr_at_5_max": 0.439247,
135+
"nauc_mrr_at_5_std": 0.039593,
136+
"nauc_mrr_at_5_diff1": 0.295719,
137+
"nauc_mrr_at_10_max": 0.44262,
138+
"nauc_mrr_at_10_std": 0.024607,
139+
"nauc_mrr_at_10_diff1": 0.322262,
140+
"nauc_mrr_at_20_max": 0.445463,
141+
"nauc_mrr_at_20_std": 0.035134,
142+
"nauc_mrr_at_20_diff1": 0.311507,
143+
"nauc_mrr_at_100_max": 0.444169,
144+
"nauc_mrr_at_100_std": 0.031705,
145+
"nauc_mrr_at_100_diff1": 0.311013,
146+
"nauc_mrr_at_1000_max": 0.444106,
147+
"nauc_mrr_at_1000_std": 0.03105,
148+
"nauc_mrr_at_1000_diff1": 0.31084,
149+
"cv_recall_at_1": 0.4,
150+
"cv_recall_at_3": 0.58,
151+
"cv_recall_at_5": 0.64,
152+
"cv_recall_at_10": 0.74,
153+
"cv_recall_at_20": 0.82,
154+
"cv_recall_at_100": 0.96,
155+
"cv_recall_at_1000": 1.0,
156+
"main_score": 0.41093,
157+
"hf_subset": "default",
158+
"languages": [
159+
"eng-Latn"
160+
]
161+
}
162+
]
163+
},
164+
"evaluation_time": 15.57795763015747,
165+
"kg_co2_emissions": null
166+
}
Lines changed: 166 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,166 @@
1+
{
2+
"dataset_revision": "61b42fe57d9a44e30f47b9b878b664a95472ec80",
3+
"task_name": "ARCChallenge",
4+
"mteb_version": "2.6.7",
5+
"scores": {
6+
"test": [
7+
{
8+
"ndcg_at_1": 0.08362,
9+
"ndcg_at_3": 0.14337,
10+
"ndcg_at_5": 0.16599,
11+
"ndcg_at_10": 0.18622,
12+
"ndcg_at_20": 0.20685,
13+
"ndcg_at_100": 0.24658,
14+
"ndcg_at_1000": 0.28301,
15+
"map_at_1": 0.08362,
16+
"map_at_3": 0.12813,
17+
"map_at_5": 0.14076,
18+
"map_at_10": 0.14915,
19+
"map_at_20": 0.15488,
20+
"map_at_100": 0.16027,
21+
"map_at_1000": 0.16152,
22+
"recall_at_1": 0.08362,
23+
"recall_at_3": 0.18771,
24+
"recall_at_5": 0.24232,
25+
"recall_at_10": 0.30461,
26+
"recall_at_20": 0.38567,
27+
"recall_at_100": 0.60154,
28+
"recall_at_1000": 0.89505,
29+
"accuracy": 0.08362,
30+
"precision_at_1": 0.08362,
31+
"precision_at_3": 0.06257,
32+
"precision_at_5": 0.04846,
33+
"precision_at_10": 0.03046,
34+
"precision_at_20": 0.01928,
35+
"precision_at_100": 0.00602,
36+
"precision_at_1000": 0.0009,
37+
"mrr_at_1": 0.083618,
38+
"mrr_at_3": 0.128129,
39+
"mrr_at_5": 0.140757,
40+
"mrr_at_10": 0.149149,
41+
"mrr_at_20": 0.154878,
42+
"mrr_at_100": 0.160274,
43+
"mrr_at_1000": 0.161522,
44+
"nauc_ndcg_at_1_max": 0.245511,
45+
"nauc_ndcg_at_1_std": -0.022355,
46+
"nauc_ndcg_at_1_diff1": 0.136061,
47+
"nauc_ndcg_at_3_max": 0.228965,
48+
"nauc_ndcg_at_3_std": -0.001166,
49+
"nauc_ndcg_at_3_diff1": 0.063524,
50+
"nauc_ndcg_at_5_max": 0.240023,
51+
"nauc_ndcg_at_5_std": 0.002102,
52+
"nauc_ndcg_at_5_diff1": 0.062677,
53+
"nauc_ndcg_at_10_max": 0.232372,
54+
"nauc_ndcg_at_10_std": 0.018462,
55+
"nauc_ndcg_at_10_diff1": 0.06018,
56+
"nauc_ndcg_at_20_max": 0.229872,
57+
"nauc_ndcg_at_20_std": 0.030424,
58+
"nauc_ndcg_at_20_diff1": 0.060554,
59+
"nauc_ndcg_at_100_max": 0.220131,
60+
"nauc_ndcg_at_100_std": 0.034353,
61+
"nauc_ndcg_at_100_diff1": 0.049692,
62+
"nauc_ndcg_at_1000_max": 0.216179,
63+
"nauc_ndcg_at_1000_std": 0.027568,
64+
"nauc_ndcg_at_1000_diff1": 0.058607,
65+
"nauc_map_at_1_max": 0.245511,
66+
"nauc_map_at_1_std": -0.022355,
67+
"nauc_map_at_1_diff1": 0.136061,
68+
"nauc_map_at_3_max": 0.230475,
69+
"nauc_map_at_3_std": -0.004867,
70+
"nauc_map_at_3_diff1": 0.075621,
71+
"nauc_map_at_5_max": 0.237769,
72+
"nauc_map_at_5_std": -0.00226,
73+
"nauc_map_at_5_diff1": 0.07423,
74+
"nauc_map_at_10_max": 0.234581,
75+
"nauc_map_at_10_std": 0.005999,
76+
"nauc_map_at_10_diff1": 0.073037,
77+
"nauc_map_at_20_max": 0.233302,
78+
"nauc_map_at_20_std": 0.009709,
79+
"nauc_map_at_20_diff1": 0.072853,
80+
"nauc_map_at_100_max": 0.231001,
81+
"nauc_map_at_100_std": 0.010141,
82+
"nauc_map_at_100_diff1": 0.07131,
83+
"nauc_map_at_1000_max": 0.230681,
84+
"nauc_map_at_1000_std": 0.009627,
85+
"nauc_map_at_1000_diff1": 0.071693,
86+
"nauc_recall_at_1_max": 0.245511,
87+
"nauc_recall_at_1_std": -0.022355,
88+
"nauc_recall_at_1_diff1": 0.136061,
89+
"nauc_recall_at_3_max": 0.226187,
90+
"nauc_recall_at_3_std": 0.006667,
91+
"nauc_recall_at_3_diff1": 0.038094,
92+
"nauc_recall_at_5_max": 0.245478,
93+
"nauc_recall_at_5_std": 0.010551,
94+
"nauc_recall_at_5_diff1": 0.040597,
95+
"nauc_recall_at_10_max": 0.226755,
96+
"nauc_recall_at_10_std": 0.044506,
97+
"nauc_recall_at_10_diff1": 0.036365,
98+
"nauc_recall_at_20_max": 0.22214,
99+
"nauc_recall_at_20_std": 0.077085,
100+
"nauc_recall_at_20_diff1": 0.039421,
101+
"nauc_recall_at_100_max": 0.188899,
102+
"nauc_recall_at_100_std": 0.102217,
103+
"nauc_recall_at_100_diff1": -0.010091,
104+
"nauc_recall_at_1000_max": 0.08734,
105+
"nauc_recall_at_1000_std": 0.147336,
106+
"nauc_recall_at_1000_diff1": 0.024416,
107+
"nauc_precision_at_1_max": 0.245511,
108+
"nauc_precision_at_1_std": -0.022355,
109+
"nauc_precision_at_1_diff1": 0.136061,
110+
"nauc_precision_at_3_max": 0.226187,
111+
"nauc_precision_at_3_std": 0.006667,
112+
"nauc_precision_at_3_diff1": 0.038094,
113+
"nauc_precision_at_5_max": 0.245478,
114+
"nauc_precision_at_5_std": 0.010551,
115+
"nauc_precision_at_5_diff1": 0.040597,
116+
"nauc_precision_at_10_max": 0.226755,
117+
"nauc_precision_at_10_std": 0.044506,
118+
"nauc_precision_at_10_diff1": 0.036365,
119+
"nauc_precision_at_20_max": 0.22214,
120+
"nauc_precision_at_20_std": 0.077085,
121+
"nauc_precision_at_20_diff1": 0.039421,
122+
"nauc_precision_at_100_max": 0.188899,
123+
"nauc_precision_at_100_std": 0.102217,
124+
"nauc_precision_at_100_diff1": -0.010091,
125+
"nauc_precision_at_1000_max": 0.08734,
126+
"nauc_precision_at_1000_std": 0.147336,
127+
"nauc_precision_at_1000_diff1": 0.024416,
128+
"nauc_mrr_at_1_max": 0.245511,
129+
"nauc_mrr_at_1_std": -0.022355,
130+
"nauc_mrr_at_1_diff1": 0.136061,
131+
"nauc_mrr_at_3_max": 0.230475,
132+
"nauc_mrr_at_3_std": -0.004867,
133+
"nauc_mrr_at_3_diff1": 0.075621,
134+
"nauc_mrr_at_5_max": 0.237769,
135+
"nauc_mrr_at_5_std": -0.00226,
136+
"nauc_mrr_at_5_diff1": 0.07423,
137+
"nauc_mrr_at_10_max": 0.234581,
138+
"nauc_mrr_at_10_std": 0.005999,
139+
"nauc_mrr_at_10_diff1": 0.073037,
140+
"nauc_mrr_at_20_max": 0.233302,
141+
"nauc_mrr_at_20_std": 0.009709,
142+
"nauc_mrr_at_20_diff1": 0.072853,
143+
"nauc_mrr_at_100_max": 0.231001,
144+
"nauc_mrr_at_100_std": 0.010141,
145+
"nauc_mrr_at_100_diff1": 0.07131,
146+
"nauc_mrr_at_1000_max": 0.230681,
147+
"nauc_mrr_at_1000_std": 0.009627,
148+
"nauc_mrr_at_1000_diff1": 0.071693,
149+
"cv_recall_at_1": 0.08362,
150+
"cv_recall_at_3": 0.18771,
151+
"cv_recall_at_5": 0.24232,
152+
"cv_recall_at_10": 0.30461,
153+
"cv_recall_at_20": 0.38567,
154+
"cv_recall_at_100": 0.60154,
155+
"cv_recall_at_1000": 0.89505,
156+
"main_score": 0.18622,
157+
"hf_subset": "default",
158+
"languages": [
159+
"eng-Latn"
160+
]
161+
}
162+
]
163+
},
164+
"evaluation_time": 11.820145606994629,
165+
"kg_co2_emissions": null
166+
}

0 commit comments

Comments
 (0)