layer,module,loss,samples,damp,time
0,linear_attn.in_proj_qkv,0.0002923562,0.05000,0.757
0,linear_attn.in_proj_z,0.0001466612,0.05000,0.443
0,linear_attn.out_proj,0.0000000849,0.05000,0.441
0,mlp.up_proj,0.0000033608,0.05000,1.322
0,mlp.gate_proj,0.0000038972,0.05000,1.313
0,mlp.down_proj,0.0000000298,0.05000,2.017
1,linear_attn.in_proj_qkv,0.0000253694,0.05000,0.507
1,linear_attn.in_proj_z,0.0000127770,0.05000,0.446
1,linear_attn.out_proj,0.0000000393,0.05000,0.447
1,mlp.up_proj,0.0000081792,0.05000,1.538
1,mlp.gate_proj,0.0000091871,0.05000,1.567
1,mlp.down_proj,0.0000000763,0.05000,1.959
2,linear_attn.in_proj_qkv,0.0000438525,0.05000,0.508
2,linear_attn.in_proj_z,0.0000216663,0.05000,0.444
2,linear_attn.out_proj,0.0000000682,0.05000,0.444
2,mlp.gate_proj,0.0000150929,0.05000,1.324
2,mlp.up_proj,0.0000126798,0.05000,1.331
2,mlp.down_proj,0.0000001957,0.05000,1.974
3,self_attn.k_proj,0.0000192607,0.05000,1.806
3,self_attn.q_proj,0.0001859263,0.05000,1.821
3,self_attn.v_proj,0.0000181077,0.05000,1.834
3,self_attn.o_proj,0.0000001161,0.05000,0.441
3,mlp.up_proj,0.0000181847,0.05000,1.498
3,mlp.gate_proj,0.0000201043,0.05000,1.502
3,mlp.down_proj,0.0000002504,0.05000,1.937
4,linear_attn.in_proj_qkv,0.0000795212,0.05000,0.509
4,linear_attn.in_proj_z,0.0000402917,0.05000,0.448
4,linear_attn.out_proj,0.0000001660,0.05000,0.440
4,mlp.up_proj,0.0000272368,0.05000,1.245
4,mlp.gate_proj,0.0000302054,0.05000,1.251
4,mlp.down_proj,0.0000004177,0.05000,1.985
5,linear_attn.in_proj_qkv,0.0001058409,0.05000,0.507
5,linear_attn.in_proj_z,0.0000515063,0.05000,0.443
5,linear_attn.out_proj,0.0000003372,0.05000,0.441
5,mlp.up_proj,0.0000352061,0.05000,1.595
5,mlp.gate_proj,0.0000418450,0.05000,1.607
5,mlp.down_proj,0.0000007811,0.05000,1.945
6,linear_attn.in_proj_qkv,0.0001155280,0.05000,0.504
6,linear_attn.in_proj_z,0.0000475952,0.05000,0.445
6,linear_attn.out_proj,0.0000007005,0.05000,0.444
6,mlp.gate_proj,0.0000575008,0.05000,1.463
6,mlp.up_proj,0.0000465150,0.05000,1.484
6,mlp.down_proj,0.0000013511,0.05000,1.962
7,self_attn.k_proj,0.0000173141,0.05000,1.807
7,self_attn.q_proj,0.0001302608,0.05000,1.814
7,self_attn.v_proj,0.0000149477,0.05000,1.827
7,self_attn.o_proj,0.0000008519,0.05000,0.450
7,mlp.up_proj,0.0000492923,0.05000,1.635
7,mlp.gate_proj,0.0000618966,0.05000,1.636
7,mlp.down_proj,0.0000012843,0.05000,1.960
8,linear_attn.in_proj_qkv,0.0001362903,0.05000,0.506
8,linear_attn.in_proj_z,0.0000582160,0.05000,0.443
8,linear_attn.out_proj,0.0000007473,0.05000,0.448
8,mlp.gate_proj,0.0000654837,0.05000,1.272
8,mlp.up_proj,0.0000539881,0.05000,1.283
8,mlp.down_proj,0.0000013767,0.05000,1.944
9,linear_attn.in_proj_qkv,0.0001456481,0.05000,0.509
9,linear_attn.in_proj_z,0.0000594048,0.05000,0.443
9,linear_attn.out_proj,0.0000008285,0.05000,0.446
9,mlp.gate_proj,0.0000664895,0.05000,1.591
9,mlp.up_proj,0.0000585528,0.05000,1.611
9,mlp.down_proj,0.0000015177,0.05000,1.943
10,linear_attn.in_proj_qkv,0.0001391888,0.05000,0.505
10,linear_attn.in_proj_z,0.0000545197,0.05000,0.440
10,linear_attn.out_proj,0.0000009204,0.05000,0.448
10,mlp.up_proj,0.0000611052,0.05000,1.330
10,mlp.gate_proj,0.0000634157,0.05000,1.347
10,mlp.down_proj,0.0000016957,0.05000,1.938
11,self_attn.k_proj,0.0000148096,0.05000,1.792
11,self_attn.q_proj,0.0001025371,0.05000,1.802
11,self_attn.v_proj,0.0000139872,0.05000,1.817
11,self_attn.o_proj,0.0000014906,0.05000,0.443
11,mlp.up_proj,0.0000636308,0.05000,1.240
11,mlp.gate_proj,0.0000622587,0.05000,1.257
11,mlp.down_proj,0.0000017404,0.05000,1.934
12,linear_attn.in_proj_qkv,0.0001382742,0.05000,0.506
12,linear_attn.in_proj_z,0.0000501939,0.05000,0.450
12,linear_attn.out_proj,0.0000011899,0.05000,0.448
12,mlp.gate_proj,0.0000613396,0.05000,1.444
12,mlp.up_proj,0.0000652184,0.05000,1.475
12,mlp.down_proj,0.0000018146,0.05000,1.946
13,linear_attn.in_proj_qkv,0.0001527687,0.05000,0.509
13,linear_attn.in_proj_z,0.0000576133,0.05000,0.435
13,linear_attn.out_proj,0.0000011374,0.05000,0.447
13,mlp.up_proj,0.0000669694,0.05000,1.612
13,mlp.gate_proj,0.0000618521,0.05000,1.628
13,mlp.down_proj,0.0000019409,0.05000,1.931
14,linear_attn.in_proj_qkv,0.0001479856,0.05000,0.511
14,linear_attn.in_proj_z,0.0000557005,0.05000,0.443
14,linear_attn.out_proj,0.0000018432,0.05000,0.447
14,mlp.gate_proj,0.0000602646,0.05000,1.386
14,mlp.up_proj,0.0000687781,0.05000,1.395
14,mlp.down_proj,0.0000021436,0.05000,1.947
15,self_attn.q_proj,0.0001035363,0.05000,1.816
15,self_attn.v_proj,0.0000182662,0.05000,1.835
15,self_attn.k_proj,0.0000149197,0.05000,1.844
15,self_attn.o_proj,0.0000017794,0.05000,0.440
15,mlp.gate_proj,0.0000654744,0.05000,1.591
15,mlp.up_proj,0.0000758326,0.05000,1.606
15,mlp.down_proj,0.0000024666,0.05000,1.959
16,linear_attn.in_proj_qkv,0.0001525745,0.05000,0.506
16,linear_attn.in_proj_z,0.0000568288,0.05000,0.449
16,linear_attn.out_proj,0.0000015897,0.05000,0.442
16,mlp.up_proj,0.0000812780,0.05000,1.391
16,mlp.gate_proj,0.0000707985,0.05000,1.402
16,mlp.down_proj,0.0000029527,0.05000,1.959
17,linear_attn.in_proj_qkv,0.0002041090,0.05000,0.503
17,linear_attn.in_proj_z,0.0000627605,0.05000,0.442
17,linear_attn.out_proj,0.0000018685,0.05000,0.439
17,mlp.up_proj,0.0000876574,0.05000,1.601
17,mlp.gate_proj,0.0000753859,0.05000,1.619
17,mlp.down_proj,0.0000039025,0.05000,1.941
18,linear_attn.in_proj_qkv,0.0001874450,0.05000,0.501
18,linear_attn.in_proj_z,0.0000663500,0.05000,0.450
18,linear_attn.out_proj,0.0000032130,0.05000,0.438
18,mlp.gate_proj,0.0000935092,0.05000,1.572
18,mlp.up_proj,0.0001019622,0.05000,1.592
18,mlp.down_proj,0.0000082581,0.05000,1.961
19,self_attn.k_proj,0.0000220895,0.05000,1.790
19,self_attn.q_proj,0.0001441360,0.05000,1.805
19,self_attn.v_proj,0.0000465971,0.05000,1.823
19,self_attn.o_proj,0.0000064091,0.05000,0.450
19,mlp.gate_proj,0.0001120633,0.05000,1.334
19,mlp.up_proj,0.0001273858,0.05000,1.355
19,mlp.down_proj,0.0000112897,0.05000,1.961
20,linear_attn.in_proj_qkv,0.0003139259,0.05000,0.506
20,linear_attn.in_proj_z,0.0001078105,0.05000,0.441
20,linear_attn.out_proj,0.0000030580,0.05000,0.445
20,mlp.up_proj,0.0001373163,0.05000,1.439
20,mlp.gate_proj,0.0001436044,0.05000,1.448
20,mlp.down_proj,0.0000117298,0.05000,1.940
21,linear_attn.in_proj_qkv,0.0003123837,0.05000,0.506
21,linear_attn.in_proj_z,0.0001131420,0.05000,0.447
21,linear_attn.out_proj,0.0000044404,0.05000,0.439
21,mlp.up_proj,0.0001441978,0.05000,1.432
21,mlp.gate_proj,0.0001608396,0.05000,1.442
21,mlp.down_proj,0.0000144337,0.05000,1.969
22,linear_attn.in_proj_qkv,0.0003056657,0.05000,0.500
22,linear_attn.in_proj_z,0.0001269550,0.05000,0.450
22,linear_attn.out_proj,0.0000055819,0.05000,0.448
22,mlp.gate_proj,0.0002304516,0.05000,1.337
22,mlp.up_proj,0.0001867799,0.05000,1.342
22,mlp.down_proj,0.0000269420,0.05000,1.964
23,self_attn.v_proj,0.0000701680,0.05000,1.793
23,self_attn.q_proj,0.0002147914,0.05000,1.801
23,self_attn.k_proj,0.0000358240,0.05000,1.807
23,self_attn.o_proj,0.0000100568,0.05000,0.445
23,mlp.up_proj,0.0001871019,0.05000,1.242
23,mlp.gate_proj,0.0002105997,0.05000,1.246
23,mlp.down_proj,0.0000214708,0.05000,1.961
24,linear_attn.in_proj_qkv,0.0003712067,0.05000,0.504
24,linear_attn.in_proj_z,0.0001371180,0.05000,0.440
24,linear_attn.out_proj,0.0000084203,0.05000,0.441
24,mlp.up_proj,0.0001981273,0.05000,1.262
24,mlp.gate_proj,0.0002350082,0.05000,1.264
24,mlp.down_proj,0.0000208720,0.05000,1.947
25,linear_attn.in_proj_qkv,0.0004077492,0.05000,0.507
25,linear_attn.in_proj_z,0.0001532642,0.05000,0.447
25,linear_attn.out_proj,0.0000076455,0.05000,0.445
25,mlp.gate_proj,0.0002800821,0.05000,1.241
25,mlp.up_proj,0.0002269588,0.05000,1.247
25,mlp.down_proj,0.0000223139,0.05000,1.959
26,linear_attn.in_proj_qkv,0.0003774328,0.05000,0.509
26,linear_attn.in_proj_z,0.0001634729,0.05000,0.437
26,linear_attn.out_proj,0.0000086689,0.05000,0.440
26,mlp.up_proj,0.0002674957,0.05000,1.266
26,mlp.gate_proj,0.0003367386,0.05000,1.272
26,mlp.down_proj,0.0000294222,0.05000,1.934
27,self_attn.k_proj,0.0000531112,0.05000,1.798
27,self_attn.v_proj,0.0001838021,0.05000,1.835
27,self_attn.q_proj,0.0002792344,0.05000,1.834
27,self_attn.o_proj,0.0000320682,0.05000,0.438
27,mlp.up_proj,0.0002780721,0.05000,1.264
27,mlp.gate_proj,0.0003418540,0.05000,1.281
27,mlp.down_proj,0.0000346843,0.05000,1.955
28,linear_attn.in_proj_qkv,0.0004718472,0.05000,0.497
28,linear_attn.in_proj_z,0.0001779310,0.05000,0.449
28,linear_attn.out_proj,0.0000171880,0.05000,0.442
28,mlp.gate_proj,0.0003511496,0.05000,1.426
28,mlp.up_proj,0.0002891008,0.05000,1.435
28,mlp.down_proj,0.0000412876,0.05000,1.966
29,linear_attn.in_proj_qkv,0.0003411556,0.05000,0.505
29,linear_attn.in_proj_z,0.0001564033,0.05000,0.439
29,linear_attn.out_proj,0.0000169771,0.05000,0.447
29,mlp.gate_proj,0.0003809890,0.05000,1.373
29,mlp.up_proj,0.0003110860,0.05000,1.395
29,mlp.down_proj,0.0000492641,0.05000,1.937
30,linear_attn.in_proj_qkv,0.0003637233,0.05000,0.511
30,linear_attn.in_proj_z,0.0001553133,0.05000,0.451
30,linear_attn.out_proj,0.0000314266,0.05000,0.451
30,mlp.up_proj,0.0002988835,0.05000,1.609
30,mlp.gate_proj,0.0003591503,0.05000,1.618
30,mlp.down_proj,0.0000692388,0.05000,1.969
31,self_attn.v_proj,0.0001614979,0.05000,1.466
31,self_attn.k_proj,0.0000528025,0.05000,1.486
31,self_attn.q_proj,0.0002747820,0.05000,1.487
31,self_attn.o_proj,0.0000677047,0.05000,0.453
31,mlp.gate_proj,0.0003321292,0.05000,1.419
31,mlp.up_proj,0.0002685991,0.05000,1.428
31,mlp.down_proj,0.0001504178,0.05000,1.965