|
,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: 4 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,0.7236,0.7073,0.7176,0.7133,,,0.7470,0.7263,,0.7106,0.7280,0.7242,0.7378,0.7296,0.7356,0.7323,0.7318,0.7263,0.7078,0.7002,0.7057,0.6844,0.7116,0.6975,0.7046,0.6942
|
|
10k,0.7492,0.7421,0.7427,0.7318,,,0.7650,0.7524,0.7573,0.7454,0.7568,0.7486,0.7557,0.7492,0.7726,0.7568,0.7612,0.7486,0.7198,0.7089,0.7209,0.7127,0.7280,0.7236,0.7367,0.7144
|
|
15k,0.7688,0.7541,0.7639,0.7481,,,0.7775,0.7655,0.7628,,0.7748,0.7622,0.7769,0.7622,0.7786,0.7737,0.7655,0.7661,0.7367,0.7329,0.7378,0.7312,0.7350,0.7318,0.7443,0.7133
|
|
20k,0.7639,0.7655,0.7682,0.7579,,,0.7807,0.7612,0.7671,0.7590,0.7845,,0.7709,0.7693,0.7813,0.7650,0.7840,0.7758,0.7465,0.7378,0.7470,0.7312,0.7486,0.7394,0.7514,0.7323
|
|
25k,0.7639,0.7677,0.7682,0.7671,,,0.7878,0.7748,,0.7590,,0.7693,0.7913,0.7671,0.7818,0.7715,0.7791,0.7715,0.7470,0.7378,0.7503,0.7437,0.7470,0.7492,0.7497,0.7345
|
|
30k,0.7764,0.7677,0.7797,0.7563,,,0.7862,0.7704,0.7780,0.7617,0.7802,0.7737,0.7829,0.7655,0.7813,0.7661,0.7889,0.7731,0.7524,0.7388,0.7497,0.7497,0.7546,0.7437,0.7563,0.7427
|
|
35k,0.7802,0.7677,0.7769,0.7622,,,0.7933,0.7726,0.7769,0.7699,0.7878,0.7682,0.7824,0.7737,0.7813,0.7797,0.7987,0.7780,0.7573,0.7361,0.7508,0.7421,0.7612,0.7579,0.7655,0.7486
|
|
40k,0.7873,0.7802,0.7802,0.7682,,,0.7905,0.7758,,0.7731,0.7889,0.7731,0.7943,0.7704,0.7835,0.7775,0.7878,0.7769,0.7573,0.7383,0.7579,0.7481,0.7606,0.7492,0.7650,0.7519
|
|
45k,0.7813,0.7786,0.7764,0.7699,,,0.7982,0.7824,0.7786,0.7661,0.7911,0.7775,0.7829,0.7737,0.7894,0.7835,0.7949,0.7780,0.7579,0.7465,0.7639,0.7465,0.7612,0.7514,0.7677,0.7497
|
|
50k,0.7818,0.7797,0.7878,0.7753,,,0.7992,0.7780,0.7775,0.7748,0.7856,0.7775,0.7943,0.7699,0.7998,0.7851,0.7933,0.7786,0.7557,0.7437,0.7524,0.7443,0.7677,0.7579,0.7802,0.7601
|
|
55k,0.7900,0.7780,0.7905,0.7829,,,0.8079,0.7737,0.7786,0.7775,0.7878,0.7731,0.7884,0.7780,0.7976,0.7905,0.7943,0.7824,0.7661,0.7546,0.7655,0.7541,0.7704,0.7606,0.7704,0.7606
|
|
60k,0.7916,0.7851,0.7911,0.7797,,,0.7922,0.7797,0.7818,0.7813,0.7900,0.7699,0.7905,0.7661,0.7943,0.7878,0.8003,0.7818,0.7650,0.7530,0.7628,0.7557,0.7661,0.7628,0.7661,0.7579
|
|
65k,0.7938,0.7840,0.7927,0.7840,,,0.7976,0.7769,0.7900,0.7780,0.7933,0.7731,0.7835,0.7671,0.7960,0.7845,0.7943,0.7780,0.7720,0.7492,0.7606,0.7535,0.7748,0.7639,0.7704,0.7584
|
|
70k,0.7922,0.7835,0.7922,0.7845,,,0.8052,0.7916,0.7916,0.7818,0.7949,0.7807,0.7900,0.7726,0.7889,0.7845,0.7976,0.7900,0.7633,0.7524,0.7612,0.7552,0.7644,0.7622,0.7699,0.7568
|
|
75k,0.7938,0.7927,0.7949,0.7840,,,0.8030,0.7873,0.7878,0.7715,0.7938,0.7807,0.8079,0.7922,0.7927,0.7905,0.8020,0.7933,0.7655,0.7541,0.7682,0.7508,0.7737,0.7568,0.7737,0.7573
|
|
80k,0.7911,0.7878,0.7873,0.7894,,,0.7971,0.7742,0.7829,0.7797,0.7987,0.7824,0.7992,0.7894,0.8003,0.7900,0.7933,0.7884,0.7671,0.7497,0.7682,0.7524,0.7748,0.7563,0.7742,0.7628
|
|
85k,0.7949,0.7894,0.7900,0.7889,,,0.8003,0.7840,0.8014,0.7786,0.8025,0.7894,0.7949,0.7818,0.7992,0.7894,0.7965,0.7851,0.7682,0.7530,0.7731,0.7563,0.7829,0.7622,0.7780,0.7704
|
|
90k,0.7982,0.7894,0.7916,0.7943,,,0.7976,0.7797,0.7873,0.7720,0.7971,0.7862,0.7856,0.7845,0.7960,0.7976,0.7998,0.7878,0.7731,0.7535,0.7650,0.7552,0.7737,0.7622,0.7742,0.7617
|
|
95k,0.8058,0.7992,0.8020,0.7873,,,0.8041,0.7742,0.7905,0.7840,0.8014,0.7807,0.7954,0.7829,0.8025,0.7911,0.8003,0.7884,0.7709,0.7535,0.7699,0.7519,0.7731,0.7612,0.7753,0.7704
|
|
100k,0.8069,0.7992,0.8052,0.7873,,,0.8069,0.7856,,,0.8041,0.7851,0.7998,0.7824,0.8014,0.7927,0.8009,0.7905,0.7628,0.7508,0.7715,0.7628,0.7748,0.7584,0.7758,0.7720
|
|
105k,0.8058,0.7965,0.8025,0.7943,,,0.8074,0.7916,,,0.8030,0.7900,0.8063,0.7927,0.8036,0.7949,0.7960,0.7905,0.7688,0.7568,0.7644,0.7601,0.7753,0.7682,0.7797,0.7639
|
|
110k,0.8041,0.7987,0.8069,0.7982,,,0.8085,0.7797,0.7856,0.7856,0.8009,0.7922,0.7938,0.7856,0.8020,0.7911,0.7998,0.7916,0.7682,0.7563,,,0.7791,0.7699,0.7845,0.7633
|
|
115k,0.8090,0.8009,0.8069,0.7982,,,0.8118,0.7867,0.7911,0.7802,0.8020,0.7867,0.8041,0.7922,0.8052,0.7916,0.8052,0.7938,0.7612,0.7541,,,0.7780,0.7633,0.7709,0.7639
|
|
120k,0.8145,0.7949,0.8041,0.7911,,,0.8074,0.7878,0.7982,0.7851,0.7976,0.7922,0.8025,0.7905,0.7938,0.7927,0.7949,0.7905,0.7704,0.7715,,,0.7813,0.7720,0.7867,0.7758
|
|
125k,0.8079,0.8009,0.8058,0.7900,,,0.8107,0.7829,0.8009,0.7900,0.8020,0.7894,0.8047,0.7916,0.8047,0.7976,0.8003,0.7922,0.7677,0.7671,,,0.7824,0.7737,0.7764,0.7699
|
|
130k,0.8069,0.8058,0.8041,0.7982,,,0.8079,0.7845,0.7916,0.7797,0.8036,0.7916,0.8014,0.7949,0.8058,0.8014,0.7922,0.7943,0.7835,0.7622,,,,,0.7748,0.7720
|
|
135k,0.8063,0.8047,0.8090,0.8020,,,0.8074,0.7878,,,0.8009,0.7878,0.8052,0.7835,0.8014,0.8030,0.8014,0.7927,0.7764,0.7682,,,,,0.7867,0.7813
|
|
140k,,,0.8090,0.7992,,,0.8123,0.7911,,,0.8047,0.7916,0.8063,0.7971,0.8079,0.8036,0.7987,0.7976,0.7764,0.7628,,,,,0.7862,0.7720
|
|
145k,,,,,,,0.8069,0.7807,,,0.8047,0.7922,0.8052,0.7845,0.7982,0.8025,0.8030,0.8085,0.7748,0.7688,,,,,0.7791,0.7699
|
|
150k,,,,,,,0.8058,0.7949,,,0.8058,0.7878,,,0.8090,0.7998,0.7987,0.8025,0.7693,0.7579,,,,,0.7916,0.7769
|
|
155k,,,,,,,0.8096,0.8041,,,0.8096,0.7922,0.7954,0.7775,0.8101,0.8041,0.8107,0.7965,0.7769,0.7639,,,,,0.7933,0.7731
|
|
160k,,,,,,,0.8101,0.7900,,,0.8014,0.7976,0.8020,0.7894,0.8128,0.8036,0.8079,0.8009,0.7753,0.7715,,,,,0.7987,0.7709
|
|
165k,,,,,,,0.8112,0.7933,,,0.8030,0.7971,0.8058,0.7878,,,0.8101,0.8009,0.7824,0.7709,,,,,0.7873,0.7682
|
|
170k,,,,,,,,0.7916,,,0.8047,0.7954,0.8041,0.7922,,,0.8036,0.8041,0.7797,0.7720,,,,,0.7884,0.7715
|
|
175k,,,,,,,0.8194,0.7965,,,0.8030,0.7911,0.7982,0.7927,,,0.8118,0.8096,0.7709,0.7666,,,,,0.7911,0.7802
|
|
180k,,,,,,,0.8118,0.7845,,,0.8041,0.7954,0.8025,0.7987,,,0.8172,0.7976,0.7775,0.7677,,,,,0.7884,0.7851
|
|
185k,,,,,,,0.8259,0.7982,,,0.8025,0.7960,0.8036,0.7905,,,0.8096,0.7987,0.7851,0.7737,,,,,0.7927,0.7813
|
|
190k,,,,,,,0.8139,0.8025,,,0.7998,0.7987,,,,,0.8128,0.7998,0.7840,0.7758,,,,,0.7922,0.7867
|
|
195k,,,,,,,0.8188,0.7965,,,0.8090,0.7878,,,,,0.8161,0.8052,0.7748,0.7677,,,,,0.7884,0.7769
|
|
200k,,,,,,,0.8112,0.8025,,,0.8079,0.8009,,,,,0.8128,0.8041,0.7802,0.7726,,,,,0.7916,0.7802
|
|
205k,,,,,,,0.8188,0.8009,,,0.8003,0.7938,,,,,0.8177,0.8145,0.7813,0.7726,,,,,0.7949,0.7748
|
|
210k,,,,,,,0.8188,0.7971,,,0.8047,0.7889,,,,,0.8161,0.8101,0.7818,0.7786,,,,,0.7894,0.7867
|
|
215k,,,,,,,0.8188,0.7992,,,0.8030,0.7922,,,,,0.8085,0.8085,0.7813,0.7748,,,,,0.7845,0.7802
|
|
220k,,,,,,,0.8199,0.8030,,,0.8085,0.7976,,,,,0.8096,0.8074,0.7769,0.7704,,,,,,
|
|
225k,,,,,,,0.8199,0.8041,,,0.8052,0.8014,,,,,0.8134,0.8101,0.7829,0.7731,,,,,,
|
|
230k,,,,,,,0.8172,0.8041,,,,,,,,,0.8134,0.8107,0.7824,0.7802,,,,,,
|
|
235k,,,,,,,0.8199,0.8085,,,,,,,,,0.8205,0.8118,0.7813,0.7764,,,,,,
|
|
240k,,,,,,,0.8166,0.8101,,,,,,,,,,,0.7829,0.7824,,,,,,
|
|
245k,,,,,,,0.8215,0.8090,,,,,,,,,,,0.7873,0.7753,,,,,,
|
|
250k,,,,,,,0.8172,0.8107,,,,,,,,,,,0.7807,0.7797,,,,,,
|
|
255k,,,,,,,0.8254,0.8128,,,,,,,,,,,0.7824,0.7737,,,,,,
|
|
260k,,,,,,,0.8215,0.809,,,,,,,,,,,0.7807,0.7797,,,,,,
|
|
265k,,,,,,,0.8210,0.8139,,,,,,,,,,,0.7775,0.7753,,,,,,
|
|
270k,,,,,,,0.8145,0.8079,,,,,,,,,,,0.7824,,,,,,,
|
|
275k,,,,,,,0.8161,0.8139,,,,,,,,,,,0.7889,0.7769,,,,,,
|
|
280k,,,,,,,0.8248,0.8150,,,,,,,,,,,0.7807,0.7726,,,,,,
|
|
285k,,,,,,,0.8210,0.8101,,,,,,,,,,,0.7916,0.7818,,,,,,
|
|
290k,,,,,,,,,,,,,,,,,,,0.7851,0.7758,,,,,,
|
|
300k,,,,,,,,,,,,,,,,,,,0.7840,0.7780,,,,,,
|
|
305k,,,,,,,,,,,,,,,,,,,0.7873,0.7829,,,,,,
|
|
310k,,,,,,,,,,,,,,,,,,,0.7813,0.7829,,,,,,
|
|
315k,,,,,,,,,,,,,,,,,,,0.7851,0.7791,,,,,,
|
|
320k,,,,,,,,,,,,,,,,,,,0.7873,0.7813,,,,,,
|
|
325k,,,,,,,,,,,,,,,,,,,,,,,,,,
|
|
330k,,,,,,,,,,,,,,,,,,,,,,,,,,
|
|
335k,,,,,,,,,,,,,,,,,,,,,,,,,, |