TxT360 / data /txt360_eval /CKPT Eval - WinoGrande.csv
hunterhector's picture
add eval results
9a127b5
raw
history blame
8.04 kB
,Slim-Pajama 600B (bsz=4K x 1024),,,,,,FineWeb-1.5T,,Ours-Base,,Ours-Upsampling1,,Ours-Upsampling2,,Ours-Code-Upsampling2,,All-Upsampling1,,All-Upsampling1,,All-Upsampling1,,All-Upsampling1,,DCLM-Base,
0-shot: 3 min,Llama-8x8B-baseline,,Llama-8x8B-seq8192,,Llama-8x8B-mup,,Llama-8x8B-seq8192,,Llama-8x8B-seq8192,,Llama-8x8B-seq8192,,Llama-8x8B-seq8192,,Llama-8x8B-seq8192,,Llama-8x8B-seq8192,,Llama-1x8B-seq8192,,Llama_extend-1x8B-seq8192,,Jais-1x8B-seq8192,,Llama-1x8B-seq8192,
5-shot: 3 min,0-shot,5-shot,0-shot,5-shot,0-shot,5-shot,0-shot,5-shot,0-shot,5-shot,0-shot,5-shot,0-shot,5-shot,0-shot,5-shot,0-shot,5-shot,0-shot,5-shot,0-shot,5-shot,0-shot,5-shot,0-shot,5-shot
5k,0.5454,0.5367,0.5572,0.5367,,,0.5691,0.5335,0.5351,0.5233,0.5241,,0.5367,0.5391,0.5470,0.5414,0.5383,0.5320,0.5067,0.5201,0.5257,0.5122,0.5020,0.5217,0.5217,0.5312
10k,0.5801,0.6054,0.5730,0.5525,,,0.5904,0.5620,0.5604,0.5738,0.5825,0.5691,0.5817,0.5809,0.5777,0.5706,0.5667,0.5620,0.5383,0.5375,0.5241,0.5430,0.5343,0.5241,0.5722,0.5517
15k,0.6172,0.6038,0.5848,0.6046,,,0.5927,0.5951,0.5919,0.5699,,0.6014,0.5880,0.5856,0.5991,0.5943,0.5896,0.5841,0.5596,0.5470,0.5391,0.5414,0.5509,0.5454,0.5620,0.5612
20k,0.6109,0.6267,0.5935,0.6085,,,0.6448,0.6022,0.6006,,0.6204,,0.6180,0.6235,0.6014,0.6062,0.5935,0.6014,0.5580,0.5691,0.5533,0.5328,0.5659,0.5580,0.5943,0.5714
25k,0.6417,0.6369,0.5998,0.6140,,,0.6196,0.6164,0.6125,0.5998,0.6093,0.6117,0.6062,0.6117,0.6212,0.6014,0.6101,0.6188,0.5785,0.5770,0.5556,0.5572,0.5762,0.5691,0.5904,0.5864
30k,0.6377,0.6456,0.6251,0.6361,,,0.6488,0.6251,,,0.6330,0.5983,0.6140,0.6022,0.6338,0.6109,0.6322,0.6188,0.5667,0.5770,0.5612,0.5493,0.5919,0.5604,0.6054,0.5935
35k,0.6472,0.6456,0.6196,0.5935,,,0.6440,0.6227,0.6030,0.6172,0.6393,0.6243,0.6259,0.6093,0.6172,0.6164,0.6212,0.6188,0.5817,0.5572,0.5848,0.5612,0.5777,0.5714,0.6172,0.5975
40k,0.6606,0.6630,0.6369,0.6259,,,0.6496,0.6077,0.6338,0.5951,,,0.6267,0.6101,0.6417,0.6235,0.6433,0.6361,0.5856,0.5770,0.5817,0.5777,0.5927,0.5635,0.6117,0.5959
45k,0.6717,0.6496,0.6196,0.6425,,,0.6456,0.6417,0.6172,0.6109,0.6448,0.6235,0.6393,0.6417,0.6425,0.6369,0.6393,0.6346,0.5777,0.5699,0.5872,0.5809,0.5951,0.5833,0.6156,0.6085
50k,0.6756,0.6725,0.6369,0.6377,,,0.6464,0.6275,0.6401,0.5975,0.6322,0.6322,0.6164,0.614,0.6425,0.6425,0.6472,0.6393,0.5833,0.5683,0.5872,0.5675,0.5967,0.5580,0.6338,0.6022
55k,0.6661,0.6590,0.6496,0.6614,,,0.6567,0.6314,0.6235,0.6062,0.6519,0.6133,0.6314,0.6235,0.6377,0.648,0.6464,0.6322,0.5738,0.5612,0.5935,0.5722,0.6148,0.5533,0.6140,0.614
60k,0.6622,0.6511,0.6377,0.6582,,,0.6480,0.6464,0.6251,0.6117,0.6535,0.6251,0.6219,0.6235,0.6480,0.6196,0.6369,0.6338,0.5864,0.5730,0.5746,0.5683,0.5896,0.5785,0.6062,0.6283
65k,0.6669,0.6772,0.6590,0.6685,,,0.6654,0.6354,0.6283,0.6180,0.6519,0.6196,0.6401,0.6393,0.6559,0.633,0.6504,0.6275,0.5919,0.5754,0.5825,0.5793,0.6101,0.5959,0.6290,0.6125
70k,0.6827,0.6811,0.6567,0.6701,,,0.6709,0.6401,0.6322,0.6235,0.6622,,0.6417,0.6409,0.6433,0.6338,0.6559,0.6361,0.5975,0.5927,0.5738,0.5588,0.5983,0.5738,0.6330,0.6101
75k,0.6788,0.6819,0.6543,0.6685,,,0.6709,0.6283,0.6480,0.6172,0.6654,0.6409,0.6527,0.6267,0.6488,0.6551,0.6527,0.6638,0.5959,0.5817,0.5880,0.5517,0.6164,0.5793,0.6196,0.6164
80k,0.6835,0.6882,0.6748,0.6638,,,0.6843,0.6464,0.6504,0.6275,0.6677,0.6401,0.6369,0.6298,0.6606,0.6488,0.6519,0.6440,0.5872,0.5675,0.5856,0.5564,0.6148,0.6038,0.6188,0.5983
85k,0.6867,0.6882,0.6638,0.6590,,,0.6875,0.6504,0.6409,0.6188,,0.6535,0.6575,0.6283,0.6606,0.6393,0.6393,0.6543,0.6085,0.5919,0.5872,0.5738,0.6156,0.5817,0.6361,0.6196
90k,0.6827,0.6803,0.6740,0.6598,,,0.6740,0.6393,0.6369,0.6306,0.6496,0.6543,0.6488,0.6409,0.6606,0.6314,0.6527,0.6409,0.5927,0.5825,0.5951,0.5888,0.6148,0.6077,0.6259,0.6164
95k,0.6859,0.6859,0.6764,0.6575,,,0.6835,0.6401,0.6369,0.6361,0.6551,0.6322,0.6654,0.6338,0.6630,0.6322,0.6409,0.6582,0.6156,0.5927,0.5864,0.5919,0.6164,0.5809,0.6283,0.6014
100k,0.6898,,0.6661,0.6851,,,0.6756,0.6567,,,0.6567,0.6472,0.6590,0.6488,0.6748,0.6204,0.6511,0.6519,0.6109,0.5817,0.5919,0.5746,0.6133,0.6030,0.6488,0.6338
105k,0.6811,0.6772,0.6654,0.6646,,,0.6772,0.6519,,,0.6661,0.6472,0.6732,0.6369,0.6638,0.633,0.6740,0.6638,0.6140,0.5991,0.5912,0.5833,0.6046,0.5943,0.6496,0.618
110k,0.7017,0.6867,0.6701,0.6654,,,0.6669,0.6480,0.6559,0.6456,0.6756,0.6551,0.6567,0.6401,0.6661,0.6456,0.6551,0.6535,0.6196,0.6006,,,0.6219,0.6069,0.6417,0.6338
115k,0.6890,0.7040,0.6701,0.6654,,,0.6732,0.6511,0.6456,0.6227,0.6559,0.6456,0.6661,0.6488,0.6748,0.6527,0.6622,0.6448,0.6156,0.6014,,,0.6338,0.6069,0.6575,0.6196
120k,0.6930,0.6953,0.6717,0.6701,,,0.6764,0.6464,0.6519,0.6275,0.6622,0.6480,0.6590,0.6322,0.6732,0.6377,0.6519,0.6622,0.5872,0.5612,,,0.6227,0.6077,0.6504,0.6275
125k,0.6961,0.6977,0.6811,0.6819,,,0.6985,0.6433,0.6393,0.6417,0.6685,0.6433,0.6646,0.6338,0.6740,0.6559,0.6803,0.6693,0.6014,0.5888,,,0.6298,0.6243,0.6488,0.6117
130k,0.6922,0.7056,0.6859,0.6717,,,0.6811,0.6330,0.6614,0.6393,0.6780,0.6322,0.6590,0.6361,0.6748,0.6456,0.6559,0.6472,0.6085,0.5880,,,,,0.6614,0.6235
135k,0.6961,0.6953,0.6788,0.6756,,,0.6827,0.6614,,,0.6606,0.6575,0.6551,0.6464,0.6748,0.629,0.6677,0.6535,0.5991,0.5959,,,,,0.6433,0.6417
140k,,,0.6819,0.6827,,,0.6867,0.6630,,,0.6598,0.6551,0.6567,0.6369,0.6709,0.6551,0.6638,0.6519,0.6038,0.5809,,,,,0.6472,0.6314
145k,,,,,,,0.6819,0.6504,,,0.6717,0.6480,0.6669,0.6551,0.6661,0.6433,0.6725,0.6630,0.6180,0.5801,,,,,0.6606,0.644
150k,,,,,,,0.6835,0.6646,,,0.6693,0.6654,,,0.6732,0.6148,0.6788,0.6409,0.6062,0.5991,,,,,0.6567,0.6361
155k,,,,,,,0.6748,0.6590,,,0.6772,0.6677,0.6630,0.648,0.6851,0.6409,0.6922,0.6764,0.6204,0.6006,,,,,0.6677,0.6401
160k,,,,,,,0.6875,0.6614,,,0.6709,0.6669,0.6748,0.648,0.6622,0.6638,0.6811,0.6803,0.6133,0.5864,,,,,0.6567,0.6322
165k,,,,,,,0.6788,0.6661,,,0.6709,0.6717,0.6725,0.6433,,,,,0.6006,0.5856,,,,,0.6669,0.6472
170k,,,,,,,0.6938,0.6709,,,0.6701,0.6598,0.6725,0.6354,,,0.6717,0.6867,0.6085,0.5833,,,,,0.6685,0.6575
175k,,,,,,,0.6938,0.6693,,,0.6590,0.6622,0.6693,0.6614,,,0.6890,0.6867,0.6133,0.5754,,,,,0.6622,0.6598
180k,,,,,,,0.6977,0.6646,,,0.6661,0.6646,0.6740,0.6661,,,0.6685,0.6504,0.6235,0.5967,,,,,0.6732,0.6535
185k,,,,,,,0.6875,0.6519,,,0.6930,0.6535,0.6811,0.663,,,0.6851,0.6819,0.6156,0.5833,,,,,0.6661,0.648
190k,,,,,,,0.6914,0.6859,,,0.6819,0.6606,,,,,0.6693,0.6638,0.6361,0.6006,,,,,0.6701,0.6488
195k,,,,,,,0.6859,0.6614,,,0.6946,0.6732,,,,,0.6756,0.6638,0.6259,0.5841,,,,,0.6606,0.6543
200k,,,,,,,0.6875,0.6669,,,0.6898,0.6780,,,,,0.7017,0.6701,0.6227,0.5872,,,,,0.6590,0.648
205k,,,,,,,0.7072,0.6906,,,0.6969,0.6780,,,,,0.6827,0.6748,0.6306,0.5888,,,,,0.6725,0.659
210k,,,,,,,0.6859,0.6661,,,0.6827,0.6748,,,,,0.6882,0.6717,0.6322,0.5919,,,,,0.6669,0.6488
215k,,,,,,,0.7017,0.6780,,,0.6748,0.6772,,,,,0.6922,0.6709,0.6346,0.6006,,,,,0.6709,0.6661
220k,,,,,,,0.7040,0.6788,,,0.6859,0.6732,,,,,0.6969,0.6638,0.6346,0.5983,,,,,,
225k,,,,,,,0.7111,0.6717,,,0.6843,0.6685,,,,,0.6756,0.6606,0.6188,0.5935,,,,,,
230k,,,,,,,0.7103,0.6811,,,,,,,,,0.7096,0.6701,0.6235,0.5935,,,,,,
235k,,,,,,,0.7040,0.6772,,,,,,,,,0.7096,0.6764,0.6306,0.6062,,,,,,
240k,,,,,,,0.7080,0.6851,,,,,,,,,,,0.6219,,,,,,,
245k,,,,,,,0.6985,0.6938,,,,,,,,,,,0.6267,0.5888,,,,,,
250k,,,,,,,0.7127,0.6938,,,,,,,,,,,0.6361,0.6006,,,,,,
255k,,,,,,,0.7119,0.6827,,,,,,,,,,,0.6440,0.5998,,,,,,
260k,,,,,,,0.7056,0.6867,,,,,,,,,,,0.6322,0.5975,,,,,,
265k,,,,,,,0.7040,0.6756,,,,,,,,,,,0.6338,0.6069,,,,,,
270k,,,,,,,0.7111,0.6819,,,,,,,,,,,0.6314,0.5991,,,,,,
275k,,,,,,,0.7127,0.6811,,,,,,,,,,,0.6306,0.6148,,,,,,
280k,,,,,,,0.7064,0.6914,,,,,,,,,,,0.6251,0.6054,,,,,,
285k,,,,,,,0.7096,0.6977,,,,,,,,,,,0.6385,,,,,,,
290k,,,,,,,,,,,,,,,,,,,0.6338,0.6077,,,,,,
300k,,,,,,,,,,,,,,,,,,,0.6227,0.6093,,,,,,
305k,,,,,,,,,,,,,,,,,,,0.6290,0.6069,,,,,,
310k,,,,,,,,,,,,,,,,,,,0.6267,0.6156,,,,,,
315k,,,,,,,,,,,,,,,,,,,0.6314,0.6101,,,,,,
320k,,,,,,,,,,,,,,,,,,,0.6401,0.5991,,,,,,
325k,,,,,,,,,,,,,,,,,,,,,,,,,,
330k,,,,,,,,,,,,,,,,,,,,,,,,,,
335k,,,,,,,,,,,,,,,,,,,,,,,,,,