layer,module,loss,samples,damp,time
0,linear_attn.in_proj_qkv,0.0000016380,,0.021
0,linear_attn.in_proj_z,0.0000016380,,0.031
0,linear_attn.out_proj,not applicable,,0.036
0,mlp.gate_proj,0.0000003862,,0.048
0,mlp.up_proj,0.0000003862,,0.059
0,mlp.down_proj,0.0000010086,,0.072
1,linear_attn.in_proj_qkv,0.0000012900,,0.008
1,linear_attn.in_proj_z,0.0000012900,,0.014
1,linear_attn.out_proj,not applicable,,0.019
1,mlp.gate_proj,0.0000011203,,0.028
1,mlp.up_proj,0.0000011203,,0.037
1,mlp.down_proj,0.0000016897,,0.046
2,linear_attn.in_proj_qkv,0.0000022176,,0.007
2,linear_attn.in_proj_z,0.0000022176,,0.012
2,linear_attn.out_proj,not applicable,,0.017
2,mlp.gate_proj,0.0000040707,,0.026
2,mlp.up_proj,0.0000040707,,0.035
2,mlp.down_proj,0.0000039030,,0.044
3,self_attn.q_proj,0.0000034477,,0.010
3,self_attn.k_proj,0.0000034477,,0.017
3,self_attn.v_proj,0.0000034477,,0.019
3,self_attn.o_proj,not applicable,,0.023
3,mlp.gate_proj,0.0000037049,,0.033
3,mlp.up_proj,0.0000037049,,0.042
3,mlp.down_proj,0.0000038534,,0.051
4,linear_attn.in_proj_qkv,0.0000038554,,0.007
4,linear_attn.in_proj_z,0.0000038554,,0.013
4,linear_attn.out_proj,not applicable,,0.017
4,mlp.gate_proj,0.0000080375,,0.027
4,mlp.up_proj,0.0000080375,,0.036
4,mlp.down_proj,0.0000061858,,0.045
5,linear_attn.in_proj_qkv,0.0000045622,,0.007
5,linear_attn.in_proj_z,0.0000045622,,0.013
5,linear_attn.out_proj,not applicable,,0.018
5,mlp.gate_proj,0.0000099294,,0.027
5,mlp.up_proj,0.0000099294,,0.037
5,mlp.down_proj,0.0000087976,,0.046
6,linear_attn.in_proj_qkv,0.0000073547,,0.008
6,linear_attn.in_proj_z,0.0000073547,,0.014
6,linear_attn.out_proj,not applicable,,0.018
6,mlp.gate_proj,0.0000167014,,0.028
6,mlp.up_proj,0.0000167014,,0.037
6,mlp.down_proj,0.0000156754,,0.047
7,self_attn.q_proj,0.0000117582,,0.010
7,self_attn.k_proj,0.0000117582,,0.016
7,self_attn.v_proj,0.0000117582,,0.018
7,self_attn.o_proj,not applicable,,0.022
7,mlp.gate_proj,0.0000187049,,0.032
7,mlp.up_proj,0.0000187049,,0.041
7,mlp.down_proj,0.0000153803,,0.051
8,linear_attn.in_proj_qkv,0.0000101067,,0.007
8,linear_attn.in_proj_z,0.0000101067,,0.015
8,linear_attn.out_proj,not applicable,,0.019
8,mlp.gate_proj,0.0000248312,,0.030
8,mlp.up_proj,0.0000248312,,0.040
8,mlp.down_proj,0.0000195886,,0.049
9,linear_attn.in_proj_qkv,0.0000095339,,0.007
9,linear_attn.in_proj_z,0.0000095339,,0.014
9,linear_attn.out_proj,not applicable,,0.019
9,mlp.gate_proj,0.0000238178,,0.030
9,mlp.up_proj,0.0000238178,,0.039
9,mlp.down_proj,0.0000189169,,0.049
10,linear_attn.in_proj_qkv,0.0000121491,,0.006
10,linear_attn.in_proj_z,0.0000121491,,0.013
10,linear_attn.out_proj,not applicable,,0.017
10,mlp.gate_proj,0.0000241134,,0.028
10,mlp.up_proj,0.0000241134,,0.037
10,mlp.down_proj,0.0000199430,,0.047
11,self_attn.q_proj,0.0000221919,,0.009
11,self_attn.k_proj,0.0000221919,,0.015
11,self_attn.v_proj,0.0000221919,,0.017
11,self_attn.o_proj,not applicable,,0.021
11,mlp.gate_proj,0.0000247778,,0.031
11,mlp.up_proj,0.0000247778,,0.040
11,mlp.down_proj,0.0000206496,,0.049
12,linear_attn.in_proj_qkv,0.0000174694,,0.009
12,linear_attn.in_proj_z,0.0000174694,,0.017
12,linear_attn.out_proj,not applicable,,0.021
12,mlp.gate_proj,0.0000251065,,0.031
12,mlp.up_proj,0.0000251065,,0.040
12,mlp.down_proj,0.0000208054,,0.049
13,linear_attn.in_proj_qkv,0.0000190737,,0.006
13,linear_attn.in_proj_z,0.0000190737,,0.014
13,linear_attn.out_proj,not applicable,,0.018
13,mlp.gate_proj,0.0000274123,,0.028
13,mlp.up_proj,0.0000274123,,0.037
13,mlp.down_proj,0.0000234874,,0.046
14,linear_attn.in_proj_qkv,0.0000267416,,0.008
14,linear_attn.in_proj_z,0.0000267416,,0.014
14,linear_attn.out_proj,not applicable,,0.018
14,mlp.gate_proj,0.0000290493,,0.027
14,mlp.up_proj,0.0000290493,,0.036
14,mlp.down_proj,0.0000248887,,0.045
15,self_attn.q_proj,0.0000299744,,0.009
15,self_attn.k_proj,0.0000299744,,0.016
15,self_attn.v_proj,0.0000299744,,0.019
15,self_attn.o_proj,not applicable,,0.024
15,mlp.gate_proj,0.0000348603,,0.033
15,mlp.up_proj,0.0000348603,,0.044
15,mlp.down_proj,0.0000292151,,0.053
16,linear_attn.in_proj_qkv,0.0000269105,,0.009
16,linear_attn.in_proj_z,0.0000269105,,0.017
16,linear_attn.out_proj,not applicable,,0.021
16,mlp.gate_proj,0.0000426992,,0.031
16,mlp.up_proj,0.0000426992,,0.040
16,mlp.down_proj,0.0000366058,,0.049
17,linear_attn.in_proj_qkv,0.0000358655,,0.007
17,linear_attn.in_proj_z,0.0000358655,,0.015
17,linear_attn.out_proj,not applicable,,0.020
17,mlp.gate_proj,0.0000543341,,0.029
17,mlp.up_proj,0.0000543341,,0.039
17,mlp.down_proj,0.0000475483,,0.048
18,linear_attn.in_proj_qkv,0.0000441931,,0.007
18,linear_attn.in_proj_z,0.0000441931,,0.015
18,linear_attn.out_proj,not applicable,,0.019
18,mlp.gate_proj,0.0000884037,,0.028
18,mlp.up_proj,0.0000884037,,0.038
18,mlp.down_proj,0.0000819403,,0.047
19,self_attn.q_proj,0.0001163868,,0.013
19,self_attn.k_proj,0.0001163868,,0.019
19,self_attn.v_proj,0.0001163868,,0.021
19,self_attn.o_proj,not applicable,,0.026
19,mlp.gate_proj,0.0001117514,,0.035
19,mlp.up_proj,0.0001117514,,0.045
19,mlp.down_proj,0.0001028360,,0.054
20,linear_attn.in_proj_qkv,0.0000673925,,0.008
20,linear_attn.in_proj_z,0.0000673925,,0.017
20,linear_attn.out_proj,not applicable,,0.022
20,mlp.gate_proj,0.0001333659,,0.032
20,mlp.up_proj,0.0001333659,,0.042
20,mlp.down_proj,0.0001111933,,0.052
21,linear_attn.in_proj_qkv,0.0000724064,,0.006
21,linear_attn.in_proj_z,0.0000724064,,0.013
21,linear_attn.out_proj,not applicable,,0.017
21,mlp.gate_proj,0.0001530533,,0.026
21,mlp.up_proj,0.0001530533,,0.036
21,mlp.down_proj,0.0001211819,,0.045
22,linear_attn.in_proj_qkv,0.0000684318,,0.007
22,linear_attn.in_proj_z,0.0000684318,,0.017
22,linear_attn.out_proj,not applicable,,0.021
22,mlp.gate_proj,0.0001648623,,0.031
22,mlp.up_proj,0.0001648623,,0.041
22,mlp.down_proj,0.0001336086,,0.050
23,self_attn.q_proj,0.0001666454,,0.010
23,self_attn.k_proj,0.0001666454,,0.016
23,self_attn.v_proj,0.0001666454,,0.019
23,self_attn.o_proj,not applicable,,0.023
23,mlp.gate_proj,0.0001898821,,0.033
23,mlp.up_proj,0.0001898821,,0.042
23,mlp.down_proj,0.0001388790,,0.052
24,linear_attn.in_proj_qkv,0.0001078959,,0.008
24,linear_attn.in_proj_z,0.0001078959,,0.015
24,linear_attn.out_proj,not applicable,,0.019
24,mlp.gate_proj,0.0002328693,,0.030
24,mlp.up_proj,0.0002328693,,0.039
24,mlp.down_proj,0.0001753442,,0.048
25,linear_attn.in_proj_qkv,0.0001290192,,0.007
25,linear_attn.in_proj_z,0.0001290192,,0.013
25,linear_attn.out_proj,not applicable,,0.017
25,mlp.gate_proj,0.0002542316,,0.027
25,mlp.up_proj,0.0002542316,,0.036
25,mlp.down_proj,0.0001938546,,0.045
26,linear_attn.in_proj_qkv,0.0001712637,,0.007
26,linear_attn.in_proj_z,0.0001712637,,0.015
26,linear_attn.out_proj,not applicable,,0.019
26,mlp.gate_proj,0.0002860233,,0.028
26,mlp.up_proj,0.0002860233,,0.037
26,mlp.down_proj,0.0002183416,,0.047
27,self_attn.q_proj,0.0006835859,,0.011
27,self_attn.k_proj,0.0006835859,,0.017
27,self_attn.v_proj,0.0006835859,,0.020
27,self_attn.o_proj,not applicable,,0.024
27,mlp.gate_proj,0.0003562241,,0.034
27,mlp.up_proj,0.0003562241,,0.044
27,mlp.down_proj,0.0002953839,,0.053
28,linear_attn.in_proj_qkv,0.0002207250,,0.008
28,linear_attn.in_proj_z,0.0002207250,,0.016
28,linear_attn.out_proj,not applicable,,0.021
28,mlp.gate_proj,0.0003317673,,0.030
28,mlp.up_proj,0.0003317673,,0.040
28,mlp.down_proj,0.0002664407,,0.049
29,linear_attn.in_proj_qkv,0.0001950549,,0.009
29,linear_attn.in_proj_z,0.0001950549,,0.018
29,linear_attn.out_proj,not applicable,,0.023
29,mlp.gate_proj,0.0003462141,,0.032
29,mlp.up_proj,0.0003462141,,0.042
29,mlp.down_proj,0.0002838155,,0.051
30,linear_attn.in_proj_qkv,0.0002944490,,0.006
30,linear_attn.in_proj_z,0.0002944490,,0.013
30,linear_attn.out_proj,not applicable,,0.017
30,mlp.gate_proj,0.0003567455,,0.026
30,mlp.up_proj,0.0003567455,,0.036
30,mlp.down_proj,0.0002943160,,0.045
31,self_attn.q_proj,0.0005755530,,0.015
31,self_attn.k_proj,0.0005755530,,0.024
31,self_attn.v_proj,0.0005755530,,0.026
31,self_attn.o_proj,not applicable,,0.030
31,mlp.gate_proj,0.0004014420,,0.039
31,mlp.up_proj,0.0004014420,,0.048
31,mlp.down_proj,0.0003186199,,0.058
32,linear_attn.in_proj_qkv,0.0003106689,,0.009
32,linear_attn.in_proj_z,0.0003106689,,0.018
32,linear_attn.out_proj,not applicable,,0.022
32,mlp.gate_proj,0.0004421567,,0.032
32,mlp.up_proj,0.0004421567,,0.042
32,mlp.down_proj,0.0003454416,,0.051
33,linear_attn.in_proj_qkv,0.0003900356,,0.006
33,linear_attn.in_proj_z,0.0003900356,,0.015
33,linear_attn.out_proj,not applicable,,0.020
33,mlp.gate_proj,0.0004678640,,0.029
33,mlp.up_proj,0.0004678640,,0.038
33,mlp.down_proj,0.0003478689,,0.048
34,linear_attn.in_proj_qkv,0.0003785149,,0.008
34,linear_attn.in_proj_z,0.0003785149,,0.016
34,linear_attn.out_proj,not applicable,,0.021
34,mlp.gate_proj,0.0006320122,,0.030
34,mlp.up_proj,0.0006320122,,0.040
34,mlp.down_proj,0.0004934073,,0.049
35,self_attn.q_proj,0.0011108149,,0.011
35,self_attn.k_proj,0.0011108149,,0.017
35,self_attn.v_proj,0.0011108149,,0.019
35,self_attn.o_proj,not applicable,,0.024
35,mlp.gate_proj,0.0006238400,,0.034
35,mlp.up_proj,0.0006238400,,0.043
35,mlp.down_proj,0.0004824514,,0.052
36,linear_attn.in_proj_qkv,0.0002366832,,0.009
36,linear_attn.in_proj_z,0.0002366832,,0.017
36,linear_attn.out_proj,not applicable,,0.022
36,mlp.gate_proj,0.0005296277,,0.031
36,mlp.up_proj,0.0005296277,,0.040
36,mlp.down_proj,0.0003962678,,0.050
37,linear_attn.in_proj_qkv,0.0002503380,,0.006
37,linear_attn.in_proj_z,0.0002503380,,0.013
37,linear_attn.out_proj,not applicable,,0.017
37,mlp.gate_proj,0.0005041908,,0.027
37,mlp.up_proj,0.0005041908,,0.036
37,mlp.down_proj,0.0003558242,,0.045
38,linear_attn.in_proj_qkv,0.0001721865,,0.006
38,linear_attn.in_proj_z,0.0001721865,,0.012
38,linear_attn.out_proj,not applicable,,0.016
38,mlp.gate_proj,0.0005179235,,0.025
38,mlp.up_proj,0.0005179235,,0.035
38,mlp.down_proj,0.0003848562,,0.044
39,self_attn.q_proj,0.0006607451,,0.010
39,self_attn.k_proj,0.0006607451,,0.014
39,self_attn.v_proj,0.0006607451,,0.017
39,self_attn.o_proj,not applicable,,0.021
39,mlp.gate_proj,0.0005020925,,0.031
39,mlp.up_proj,0.0005020925,,0.040
39,mlp.down_proj,0.0003556356,,0.049
40,linear_attn.in_proj_qkv,0.0002660381,,0.007
40,linear_attn.in_proj_z,0.0002660381,,0.015
40,linear_attn.out_proj,not applicable,,0.020
40,mlp.gate_proj,0.0005828155,,0.029
40,mlp.up_proj,0.0005828155,,0.038
40,mlp.down_proj,0.0004103785,,0.048
41,linear_attn.in_proj_qkv,0.0002335446,,0.009
41,linear_attn.in_proj_z,0.0002335446,,0.017
41,linear_attn.out_proj,not applicable,,0.021
41,mlp.gate_proj,0.0006417350,,0.031
41,mlp.up_proj,0.0006417350,,0.041
41,mlp.down_proj,0.0004168435,,0.050
42,linear_attn.in_proj_qkv,0.0003170260,,0.007
42,linear_attn.in_proj_z,0.0003170260,,0.014
42,linear_attn.out_proj,not applicable,,0.018
42,mlp.gate_proj,0.0007591126,,0.027
42,mlp.up_proj,0.0007591126,,0.037
42,mlp.down_proj,0.0004959149,,0.046
43,self_attn.q_proj,0.0011036232,,0.006
43,self_attn.k_proj,0.0011036232,,0.012
43,self_attn.v_proj,0.0011036232,,0.015
43,self_attn.o_proj,not applicable,,0.019
43,mlp.gate_proj,0.0007401613,,0.029
43,mlp.up_proj,0.0007401613,,0.038
43,mlp.down_proj,0.0004964855,,0.048
44,linear_attn.in_proj_qkv,0.0004131533,,0.008
44,linear_attn.in_proj_z,0.0004131533,,0.018
44,linear_attn.out_proj,not applicable,,0.023
44,mlp.gate_proj,0.0007805692,,0.034
44,mlp.up_proj,0.0007805692,,0.043
44,mlp.down_proj,0.0005284736,,0.053
45,linear_attn.in_proj_qkv,0.0003519070,,0.009
45,linear_attn.in_proj_z,0.0003519070,,0.018
45,linear_attn.out_proj,not applicable,,0.023
45,mlp.gate_proj,0.0008203685,,0.033
45,mlp.up_proj,0.0008203685,,0.042
45,mlp.down_proj,0.0005516273,,0.051
46,linear_attn.in_proj_qkv,0.0005885546,,0.006
46,linear_attn.in_proj_z,0.0005885546,,0.012
46,linear_attn.out_proj,not applicable,,0.016
46,mlp.gate_proj,0.0009080387,,0.026
46,mlp.up_proj,0.0009080387,,0.035
46,mlp.down_proj,0.0006251069,,0.044
47,self_attn.q_proj,0.0012794546,,0.010
47,self_attn.k_proj,0.0012794546,,0.017
47,self_attn.v_proj,0.0012794546,,0.019
47,self_attn.o_proj,not applicable,,0.023
47,mlp.gate_proj,0.0010251296,,0.033
47,mlp.up_proj,0.0010251296,,0.043
47,mlp.down_proj,0.0007053357,,0.052
48,linear_attn.in_proj_qkv,0.0005421048,,0.013
48,linear_attn.in_proj_z,0.0005421048,,0.021
48,linear_attn.out_proj,not applicable,,0.026
48,mlp.gate_proj,0.0012638368,,0.035
48,mlp.up_proj,0.0012638368,,0.045
48,mlp.down_proj,0.0008488864,,0.055
49,linear_attn.in_proj_qkv,0.0004842966,,0.007
49,linear_attn.in_proj_z,0.0004842966,,0.013
49,linear_attn.out_proj,not applicable,,0.018
49,mlp.gate_proj,0.0014845806,,0.028
49,mlp.up_proj,0.0014845806,,0.037
49,mlp.down_proj,0.0009813060,,0.047
50,linear_attn.in_proj_qkv,0.0008999808,,0.005
50,linear_attn.in_proj_z,0.0008999808,,0.011
50,linear_attn.out_proj,not applicable,,0.015
50,mlp.gate_proj,0.0024173252,,0.025
50,mlp.up_proj,0.0024173252,,0.034
50,mlp.down_proj,0.0018818722,,0.043
51,self_attn.q_proj,0.0039922510,,0.008
51,self_attn.k_proj,0.0039922510,,0.014
51,self_attn.v_proj,0.0039922510,,0.016
51,self_attn.o_proj,not applicable,,0.020
51,mlp.gate_proj,0.0027920838,,0.029
51,mlp.up_proj,0.0027920838,,0.039
51,mlp.down_proj,0.0022079181,,0.048
52,linear_attn.in_proj_qkv,0.0006440525,,0.007
52,linear_attn.in_proj_z,0.0006440525,,0.018
52,linear_attn.out_proj,not applicable,,0.022
52,mlp.gate_proj,0.0023486493,,0.031
52,mlp.up_proj,0.0023486493,,0.041
52,mlp.down_proj,0.0018052340,,0.050
53,linear_attn.in_proj_qkv,0.0005554363,,0.007
53,linear_attn.in_proj_z,0.0005554363,,0.015
53,linear_attn.out_proj,not applicable,,0.019
53,mlp.gate_proj,0.0023646984,,0.029
53,mlp.up_proj,0.0023646984,,0.038
53,mlp.down_proj,0.0018894822,,0.047
54,linear_attn.in_proj_qkv,0.0005636523,,0.007
54,linear_attn.in_proj_z,0.0005636523,,0.014
54,linear_attn.out_proj,not applicable,,0.020
54,mlp.gate_proj,0.0029807497,,0.029
54,mlp.up_proj,0.0029807497,,0.038
54,mlp.down_proj,0.0026787185,,0.047
55,self_attn.q_proj,0.0037838577,,0.010
55,self_attn.k_proj,0.0037838577,,0.016
55,self_attn.v_proj,0.0037838577,,0.018
55,self_attn.o_proj,not applicable,,0.022
55,mlp.gate_proj,0.0024683767,,0.034
55,mlp.up_proj,0.0024683767,,0.043
55,mlp.down_proj,0.0018751933,,0.053
56,linear_attn.in_proj_qkv,0.0007844024,,0.006
56,linear_attn.in_proj_z,0.0007844024,,0.014
56,linear_attn.out_proj,not applicable,,0.018
56,mlp.gate_proj,0.0023013421,,0.028
56,mlp.up_proj,0.0023013421,,0.037
56,mlp.down_proj,0.0016854609,,0.047
57,linear_attn.in_proj_qkv,0.0005686481,,0.006
57,linear_attn.in_proj_z,0.0005686481,,0.013
57,linear_attn.out_proj,not applicable,,0.017
57,mlp.gate_proj,0.0023689751,,0.026
57,mlp.up_proj,0.0023689751,,0.036
57,mlp.down_proj,0.0016684245,,0.046
58,linear_attn.in_proj_qkv,0.0006748634,,0.006
58,linear_attn.in_proj_z,0.0006748634,,0.015
58,linear_attn.out_proj,not applicable,,0.020
58,mlp.gate_proj,0.0032920326,,0.030
58,mlp.up_proj,0.0032920326,,0.039
58,mlp.down_proj,0.0021778252,,0.048
59,self_attn.q_proj,0.0099577962,,0.009
59,self_attn.k_proj,0.0099577962,,0.015
59,self_attn.v_proj,0.0099577962,,0.016
59,self_attn.o_proj,not applicable,,0.020
59,mlp.gate_proj,0.0040843336,,0.030
59,mlp.up_proj,0.0040843336,,0.039
59,mlp.down_proj,0.0031100676,,0.049
60,linear_attn.in_proj_qkv,0.0012042811,,0.009
60,linear_attn.in_proj_z,0.0012042811,,0.017
60,linear_attn.out_proj,not applicable,,0.021
60,mlp.gate_proj,0.0043294880,,0.031
60,mlp.up_proj,0.0043294880,,0.042
60,mlp.down_proj,0.0036994821,,0.051
61,linear_attn.in_proj_qkv,0.0013711013,,0.006
61,linear_attn.in_proj_z,0.0013711013,,0.014
61,linear_attn.out_proj,not applicable,,0.018
61,mlp.gate_proj,0.0055645517,,0.028
61,mlp.up_proj,0.0055645517,,0.037
61,mlp.down_proj,0.0049028226,,0.046
62,linear_attn.in_proj_qkv,0.0044048463,,0.007
62,linear_attn.in_proj_z,0.0044048463,,0.012
62,linear_attn.out_proj,not applicable,,0.016
62,mlp.gate_proj,0.0093146329,,0.026
62,mlp.up_proj,0.0093146329,,0.036
62,mlp.down_proj,0.0091457848,,0.045
63,self_attn.q_proj,0.0142782208,,0.012
63,self_attn.k_proj,0.0142782208,,0.018
63,self_attn.v_proj,0.0142782208,,0.020
63,self_attn.o_proj,not applicable,,0.024
63,mlp.gate_proj,0.0228790123,,0.034
63,mlp.up_proj,0.0228790123,,0.043
63,mlp.down_proj,0.0271780144,,0.052