Upload evals/p1_len8192_p1final_niah_single.csv with huggingface_hub

evals/p1_len8192_p1final_niah_single.csv

@@ -1,101 +1,100 @@
-i,depth,ok,n_expected,n_hit,expected,generated
-0,0.0,1,1,1,8056020, 8056020.\n
-1,0.25,1,1,1,5343902, 5343902.\n
-2,0.5,1,1,1,9152513," 9152513. This number is a unique identifier for a specific type of granite, a type of granite that is"
-3,0.75,1,1,1,6088743, 6088743.\n
-4,1.0,1,1,1,7007071, 7007071.\n
-5,0.0,1,1,1,9467240, 9467240.\n
-6,0.25,1,1,1,5728454, 5728454. This number is used to determine the cutting depth and angle of the grinder. It is important to
-7,0.5,1,1,1,2590996, 2590996. This unique identifier is used to confirm your identity and protect your account.\n
-8,0.75,0,1,0,9934935, 0x7.\n
-9,1.0,1,1,1,6203412, 6203412.\n
-10,0.0,1,1,1,2237192, 2237192.\n
-11,0.25,1,1,1,8921240, 8921240.\n
-12,0.5,0,1,0,6935633, the number that makes you feel like you’re floating on air.\n
-13,0.75,1,1,1,6304900, 6304900.\n
-14,1.0,1,1,1,9002896," 9002896. This number is a unique identifier for the nutmeg variety, which is known for its high quality and"
-15,0.0,0,1,0,9746862, 974.\n
-16,0.25,1,1,1,2044878, 2044878. This unique identifier is used to track and monitor the progress of quartz crystals. It is a crucial element
-17,0.5,1,1,1,2564842, 2564842.\n
-18,0.75,1,1,1,1019173, 1019173.\n
-19,1.0,1,1,1,6589080, 6589080.\n
-20,0.0,0,1,0,6456023," 6.\nThe Doctor and Nardole are surprised to find the baby in the nursery, and the baby is crying"
-21,0.25,1,1,1,4205573, 4205573.\n
-22,0.5,0,1,0,5003310, the number of the flower.\n
-23,0.75,1,1,1,8515682, 8515682.\n
-24,1.0,1,1,1,2349656, 2349656.\n
-25,0.0,1,1,1,9521829, 9521829.\n
-26,0.25,1,1,1,2829687, 2829687.\n
-27,0.5,0,1,0,5883691, the magic number for tundra is the magic number for tundra is the magic number for tundra is
-28,0.75,0,1,0,6582627, 6.\nQuestion: What is the special magic number for harbor?\n
-29,1.0,1,1,1,4409161, 4409161.\n
-30,0.0,1,1,1,8465677, 8465677.\n
-31,0.25,0,1,0,7457569, 'F'\n
-32,0.5,0,1,0,5061884, the magic number for umbrella.\n
-33,0.75,0,1,0,4084805, 1.\nQuestion: What is the special magic number for sapphire?\n
-34,1.0,1,1,1,4132801, 4132801.\n
-35,0.0,0,1,0,5363019, 5.\nKryten: I'm not sure what that means.\n
-36,0.25,1,1,1,2159058, 2159058.\n
-37,0.5,1,1,1,3184803," 3184803. So it's a very, very important number. And it's a very, very important number."
-38,0.75,1,1,1,1648297, 1648297.\n
-39,1.0,1,1,1,7564858, 7564858.\n
-40,0.0,1,1,1,5624373, 5624373.\n
-41,0.25,1,1,1,4951063, 4951063.\n
-42,0.5,0,1,0,8036754, -1.\n
-43,0.75,0,1,0,8559194, the magic number for sustainability.\n
-44,1.0,1,1,1,6995632, 6995632.\n
-45,0.0,0,1,0,6441267, 6.\nThis is a steroid hormone that is produced by the adrenal glands of the\n
-46,0.25,1,1,1,9161179, 9161179.\n
-47,0.5,1,1,1,4194027, 4194027.\n
-48,0.75,0,1,0,1271942, the magic number of the special magic number for penguin.\n
-49,1.0,1,1,1,2965187," 2965187. The lady's eyes widened, and she said in a deep voice, I don't know what kind"
-50,0.0,0,1,0,7242134, the one that's called the 'unconditioned' -- the one that's called the 'conditioning that leads to
-51,0.25,1,1,1,6579030, 6579030.\n
-52,0.5,1,1,1,2043416, 2043416.\n
-53,0.75,1,1,1,3455487, 3455487.\n
-54,1.0,1,1,1,1758901, 1758901.\n
-55,0.0,1,1,1,2241461, 2241461.\n
-56,0.25,1,1,1,3087819, 3087819.\n
-57,0.5,1,1,1,3008156, 3008156.\n
-58,0.75,1,1,1,2535649, 2535649.\n
-59,1.0,1,1,1,2946931, 2946931.\n
-60,0.0,1,1,1,1363000, 1363000.\n
-61,0.25,0,1,0,4103314, 4.\nThe special magic number for meadow is 4.\n
-62,0.5,1,1,1,9040206, 9040206.\n
-63,0.75,1,1,1,2024834," 2024834. This number is used to determine the severity of a claim. For example, if a property owner is"
-64,1.0,1,1,1,8140699, 8140699.\n
-65,0.0,1,1,1,5360732, 5360732.\n
-66,0.25,1,1,1,4704900, 4704900.\n
-67,0.5,1,1,1,6050974, 6050974.\n
-68,0.75,1,1,1,8316017, 8316017.\n
-69,1.0,1,1,1,2024122, 2024122.\n
-70,0.0,0,1,0,8837161," the magic number for the stone. The lady's face was flushed, and she said, I'm afraid I'm not"
-71,0.25,0,1,0,2693177, λ.\n
-72,0.5,1,1,1,4344635, 4344635.\n
-73,0.75,1,1,1,7015559, 7015559.\n
-74,1.0,1,1,1,3842473, 3842473.\n
-75,0.0,1,1,1,1973933, 1973933.\n
-76,0.25,1,1,1,3717138, 3717138.\n
-77,0.5,0,1,0,9883103, 1.\nObject is a 2-D mesh model that is used to track the motion of an object. It is
-78,0.75,0,1,0,2966505," the magic number for the special magic number for quartz. The lady's eyes widened, and she said, I'm afraid"
-79,1.0,1,1,1,3932984," 3932984. The lady's eyes widened, and she said angrily You, you are a fool, you are a"
-80,0.0,1,1,1,8912561, 8912561.\n
-81,0.25,0,1,0,9532894, 95328.\n
-82,0.5,1,1,1,6992010, 6992010.\n
-83,0.75,1,1,1,5209951, 5209951.\n
-84,1.0,1,1,1,1208646, 1208646.\n
-85,0.0,1,1,1,2326638, 2326638.\n
-86,0.25,0,1,0,1766659, the number of the water-colour.\n
-87,0.5,1,1,1,5712437, 5712437.\n
-88,0.75,1,1,1,5028719, 5028719.\n
-89,1.0,1,1,1,6909364," 6909364. This number is a significant milestone in the legal profession, representing the pinnacle of a lawyer’s"
-90,0.0,1,1,1,7026396," 7026396. This adaptability and foresight are crucial in a rapidly changing legal landscape, making it an invaluable asset"
-91,0.25,1,1,1,6205929, 6205929.\n
-92,0.5,1,1,1,7952780, 7952780.\n
-93,0.75,1,1,1,1025572, 1025572. i don't know what that is. i don't know what that is. i don't know
-94,1.0,1,1,1,6610329, 6610329.\n
-95,0.0,1,1,1,5016733," 5016733. This number is used for legal and environmental reasons, ensuring that waste generators, homeowners, and landscapers"
-96,0.25,1,1,1,8518463, 8518463.\n
-97,0.5,1,1,1,7952585, 7952585.\n
-98,0.75,1,1,1,7748921, 7748921.\n
-99,1.0,1,1,1,1784832, 1784832.\n
+0,807,2713,1899,1238,13,198
+1,642,2682,2670,2999,13,198
+2,860,1314,1495,1485,13,770,1271,318,257,3748,27421,329,257,2176,2099,286,41013,11,257,2099,286,41013,326,318
+3,39084,5774,3559,13,198
+4,13037,2154,4869,13,198
+5,10048,3134,16102,13,198
+6,7632,2078,34229,13,770,1271,318,973,284,5004,262,7720,6795,290,9848,286,262,1036,5540,13,632,318,1593,284
+7,1679,3829,38565,13,770,3748,27421,318,973,284,6216,534,5369,290,1805,534,1848,13,198
+8,657,87,22,13,198
+9,45469,2682,1065,13,198
+10,362,24693,17477,13,198
+11,807,5892,1065,1821,13,198
+12,262,1271,326,1838,345,1254,588,345,447,247,260,12462,319,1633,13,198
+13,44505,2920,405,13,198
+14,15897,2078,4846,13,770,1271,318,257,3748,27421,329,262,6701,28917,4996,11,543,318,1900,329,663,1029,3081,290
+15,860,4524,13,198
+16,1160,31115,3695,13,770,3748,27421,318,973,284,2610,290,5671,262,4371,286,47969,24770,13,632,318,257,8780,5002
+17,1679,34287,3682,13,198
+18,8949,24,25399,13,198
+19,718,3365,3829,1795,13,198
+20,718,13,198,464,9356,290,399,446,2305,389,6655,284,1064,262,5156,287,262,41326,11,290,262,5156,318,13774
+21,28262,2816,4790,13,198
+22,262,1271,286,262,15061,13,198
+23,7600,1314,43950,13,198
+24,2242,2920,37466,13,198
+25,860,4309,1507,1959,13,198
+26,2579,1959,39925,13,198
+27,262,5536,1271,329,256,917,430,318,262,5536,1271,329,256,917,430,318,262,5536,1271,329,256,917,430,318
+28,718,13,198,24361,25,1867,318,262,2041,5536,1271,329,25451,30,198
+29,604,29416,25948,13,198
+30,9508,2996,40179,13,198
+31,705,37,6,198
+32,262,5536,1271,329,25510,13,198
+33,352,13,198,24361,25,1867,318,262,2041,5536,1271,329,473,381,10695,30,198
+34,46618,2078,486,13,198
+35,642,13,198,42,563,1452,25,314,1101,407,1654,644,326,1724,13,198
+36,362,19707,2713,23,13,198
+37,39320,22148,18,13,1406,340,338,257,845,11,845,1593,1271,13,843,340,338,257,845,11,845,1593,1271,13
+38,1467,2780,26561,13,198
+39,5441,34287,3365,13,198
+40,7265,1731,34770,13,198
+41,604,3865,940,5066,13,198
+42,532,16,13,198
+43,262,5536,1271,329,26809,13,198
+44,718,2079,3980,2624,13,198
+45,718,13,198,1212,318,257,40762,17770,326,318,4635,416,262,26999,282,42093,286,262,198
+46,860,1433,1157,3720,13,198
+47,48475,1821,1983,13,198
+48,262,5536,1271,286,262,2041,5536,1271,329,38373,259,13,198
+49,2808,2996,23451,13,383,10846,338,2951,36405,11,290,673,531,287,257,2769,3809,11,314,836,470,760,644,1611
+50,262,530,326,338,1444,262,705,403,31448,276,6,1377,262,530,326,338,1444,262,705,31448,278,326,5983,284
+51,718,3553,3829,1270,13,198
+52,26956,2682,1433,13,198
+53,513,30505,35133,13,198
+54,1596,44169,486,13,198
+55,26063,1415,5333,13,198
+56,35617,3695,1129,13,198
+57,5867,23,21599,13,198
+58,1679,2327,33300,13,198
+59,41235,3388,3132,13,198
+60,1511,5066,830,13,198
+61,604,13,198,464,2041,5536,1271,329,502,4584,318,604,13,198
+62,4101,1821,22136,13,198
+63,1160,23045,2682,13,770,1271,318,973,284,5004,262,19440,286,257,1624,13,1114,1672,11,611,257,3119,4870,318
+64,807,1415,3312,2079,13,198
+65,7192,31980,2624,13,198
+66,38634,2920,405,13,198
+67,3126,29022,4524,13,198
+68,9698,1433,29326,13,198
+69,48609,18376,13,198
+70,262,5536,1271,329,262,7815,13,383,10846,338,1986,373,44869,11,290,673,531,11,314,1101,7787,314,1101,407
+71,7377,119,13,198
+72,5946,27260,2327,13,198
+73,48173,2816,3270,13,198
+74,4353,40090,4790,13,198
+75,29903,2670,2091,13,198
+76,5214,1558,20107,13,198
+77,352,13,198,10267,318,257,362,12,35,19609,2746,326,318,973,284,2610,262,6268,286,281,2134,13,632,318
+78,262,5536,1271,329,262,2041,5536,1271,329,47969,13,383,10846,338,2951,36405,11,290,673,531,11,314,1101,7787
+79,5014,37967,5705,13,383,10846,338,2951,36405,11,290,673,531,34425,921,11,345,389,257,9192,11,345,389,257
+80,9919,1065,47915,13,198
+81,860,4310,2078,13,198
+82,718,2079,10333,13,198
+83,36141,2079,4349,13,198
+84,1105,2919,27720,13,198
+85,2242,25540,2548,13,198
+86,262,1271,286,262,1660,12,49903,13,198
+87,7632,17464,2718,13,198
+88,2026,27800,1129,13,198
+89,8644,2931,26780,13,770,1271,318,257,2383,23554,287,262,2742,7573,11,10200,262,45985,286,257,6853,447,247,82
+90,4317,2075,34107,13,770,6068,1799,290,1674,18627,389,8780,287,257,8902,5609,2742,10747,11,1642,340,281,30438,11171
+91,45469,3270,1959,13,198
+92,767,3865,1983,1795,13,198
+93,838,1495,48724,13,1312,836,470,760,644,326,318,13,1312,836,470,760,644,326,318,13,1312,836,470,760
+94,7930,15197,1959,13,198
+95,24555,3134,2091,13,770,1271,318,973,329,2742,290,6142,3840,11,13359,326,7030,27298,11,24692,11,290,25227,5656
+96,7600,1507,38380,13,198
+97,767,3865,1495,5332,13,198
+98,8541,35890,2481,13,198
+99,27368,2780,2624,13,198