380 lines
17 KiB
CSV
380 lines
17 KiB
CSV
layer,module,loss,samples,damp,time
|
|
0,self_attn.q_proj,0.0000008913,0.01000,6.138
|
|
0,self_attn.v_proj,0.0000000100,0.01000,6.138
|
|
0,self_attn.k_proj,0.0000017337,0.01000,6.164
|
|
0,self_attn.o_proj,0.0000000037,0.01000,1.578
|
|
0,mlp.gate_proj,0.0000001901,0.01000,3.440
|
|
0,mlp.up_proj,0.0000001856,0.01000,3.456
|
|
0,mlp.down_proj,0.0000000166,0.01000,5.620
|
|
1,self_attn.q_proj,0.0000003933,0.01000,4.576
|
|
1,self_attn.k_proj,0.0000002099,0.01000,4.613
|
|
1,self_attn.v_proj,0.0000000120,0.01000,4.671
|
|
1,self_attn.o_proj,0.0000000045,0.01000,1.574
|
|
1,mlp.up_proj,0.0000005750,0.01000,3.232
|
|
1,mlp.gate_proj,0.0000006601,0.01000,3.234
|
|
1,mlp.down_proj,0.0000000506,0.01000,5.622
|
|
2,self_attn.v_proj,0.0000000347,0.01000,4.567
|
|
2,self_attn.q_proj,0.0000005629,0.01000,4.628
|
|
2,self_attn.k_proj,0.0000001695,0.01000,4.645
|
|
2,self_attn.o_proj,0.0000000264,0.01000,1.567
|
|
2,mlp.up_proj,0.0000013546,0.01000,3.520
|
|
2,mlp.gate_proj,0.0000016016,0.01000,3.726
|
|
2,mlp.down_proj,0.0000000479,0.01000,5.599
|
|
3,self_attn.q_proj,0.0000012548,0.01000,4.518
|
|
3,self_attn.k_proj,0.0000003074,0.01000,4.541
|
|
3,self_attn.v_proj,0.0000000672,0.01000,4.547
|
|
3,self_attn.o_proj,0.0000000413,0.01000,1.530
|
|
3,mlp.up_proj,0.0000023189,0.01000,3.232
|
|
3,mlp.gate_proj,0.0000025972,0.01000,3.243
|
|
3,mlp.down_proj,0.0000000890,0.01000,5.554
|
|
4,self_attn.q_proj,0.0000027218,0.01000,4.525
|
|
4,self_attn.k_proj,0.0000008105,0.01000,4.566
|
|
4,self_attn.v_proj,0.0000001387,0.01000,4.572
|
|
4,self_attn.o_proj,0.0000000382,0.01000,1.526
|
|
4,mlp.gate_proj,0.0000035640,0.01000,3.192
|
|
4,mlp.up_proj,0.0000032485,0.01000,3.196
|
|
4,mlp.down_proj,0.0000001381,0.01000,5.408
|
|
5,self_attn.q_proj,0.0000028091,0.01000,4.644
|
|
5,self_attn.k_proj,0.0000008442,0.01000,4.659
|
|
5,self_attn.v_proj,0.0000001876,0.01000,4.669
|
|
5,self_attn.o_proj,0.0000000697,0.01000,1.523
|
|
5,mlp.up_proj,0.0000044974,0.01000,3.193
|
|
5,mlp.gate_proj,0.0000048562,0.01000,3.195
|
|
5,mlp.down_proj,0.0000131428,0.01000,5.395
|
|
6,self_attn.q_proj,0.0000052526,0.01000,4.537
|
|
6,self_attn.k_proj,0.0000018290,0.01000,4.557
|
|
6,self_attn.v_proj,0.0000003574,0.01000,4.575
|
|
6,self_attn.o_proj,0.0000001497,0.01000,1.521
|
|
6,mlp.up_proj,0.0000063462,0.01000,3.194
|
|
6,mlp.gate_proj,0.0000066522,0.01000,3.195
|
|
6,mlp.down_proj,0.0000003866,0.01000,5.493
|
|
7,self_attn.q_proj,0.0000072205,0.01000,4.526
|
|
7,self_attn.v_proj,0.0000005591,0.01000,4.558
|
|
7,self_attn.k_proj,0.0000023830,0.01000,4.754
|
|
7,self_attn.o_proj,0.0000002008,0.01000,1.552
|
|
7,mlp.gate_proj,0.0000095508,0.01000,3.405
|
|
7,mlp.up_proj,0.0000091268,0.01000,3.627
|
|
7,mlp.down_proj,0.0000006677,0.01000,5.470
|
|
8,self_attn.q_proj,0.0000114084,0.01000,4.681
|
|
8,self_attn.k_proj,0.0000031581,0.01000,4.699
|
|
8,self_attn.v_proj,0.0000009229,0.01000,4.716
|
|
8,self_attn.o_proj,0.0000001933,0.01000,2.097
|
|
8,mlp.gate_proj,0.0000121788,0.01000,3.179
|
|
8,mlp.up_proj,0.0000116188,0.01000,3.184
|
|
8,mlp.down_proj,0.0000009437,0.01000,5.483
|
|
9,self_attn.q_proj,0.0000156803,0.01000,4.508
|
|
9,self_attn.v_proj,0.0000011937,0.01000,4.518
|
|
9,self_attn.k_proj,0.0000042363,0.01000,4.746
|
|
9,self_attn.o_proj,0.0000003874,0.01000,1.528
|
|
9,mlp.gate_proj,0.0000159241,0.01000,3.432
|
|
9,mlp.up_proj,0.0000149667,0.01000,3.607
|
|
9,mlp.down_proj,0.0000014772,0.01000,5.454
|
|
10,self_attn.k_proj,0.0000040977,0.01000,4.554
|
|
10,self_attn.q_proj,0.0000145022,0.01000,4.584
|
|
10,self_attn.v_proj,0.0000012288,0.01000,4.587
|
|
10,self_attn.o_proj,0.0000004555,0.01000,1.615
|
|
10,mlp.up_proj,0.0000178941,0.01000,3.440
|
|
10,mlp.gate_proj,0.0000192809,0.01000,3.624
|
|
10,mlp.down_proj,0.0000022575,0.01000,5.459
|
|
11,self_attn.q_proj,0.0000168993,0.01000,4.524
|
|
11,self_attn.v_proj,0.0000013383,0.01000,4.548
|
|
11,self_attn.k_proj,0.0000044527,0.01000,4.641
|
|
11,self_attn.o_proj,0.0000007151,0.01000,1.512
|
|
11,mlp.gate_proj,0.0000223744,0.01000,3.272
|
|
11,mlp.up_proj,0.0000209215,0.01000,3.326
|
|
11,mlp.down_proj,0.0000031872,0.01000,5.535
|
|
12,self_attn.k_proj,0.0000046569,0.01000,4.660
|
|
12,self_attn.q_proj,0.0000181386,0.01000,4.764
|
|
12,self_attn.v_proj,0.0000015525,0.01000,4.821
|
|
12,self_attn.o_proj,0.0000011414,0.01000,1.546
|
|
12,mlp.up_proj,0.0000247787,0.01000,3.290
|
|
12,mlp.gate_proj,0.0000268349,0.01000,3.439
|
|
12,mlp.down_proj,0.0000043331,0.01000,5.436
|
|
13,self_attn.q_proj,0.0000233999,0.01000,4.523
|
|
13,self_attn.v_proj,0.0000017773,0.01000,4.595
|
|
13,self_attn.k_proj,0.0000057049,0.01000,4.649
|
|
13,self_attn.o_proj,0.0000014400,0.01000,1.534
|
|
13,mlp.up_proj,0.0000294066,0.01000,3.293
|
|
13,mlp.gate_proj,0.0000312232,0.01000,3.328
|
|
13,mlp.down_proj,0.0000056300,0.01000,6.001
|
|
14,self_attn.q_proj,0.0000261586,0.01000,5.173
|
|
14,self_attn.k_proj,0.0000066188,0.01000,5.212
|
|
14,self_attn.v_proj,0.0000021216,0.01000,5.231
|
|
14,self_attn.o_proj,0.0000018467,0.01000,1.538
|
|
14,mlp.up_proj,0.0000330952,0.01000,3.399
|
|
14,mlp.gate_proj,0.0000342462,0.01000,3.615
|
|
14,mlp.down_proj,0.0000091821,0.01000,5.479
|
|
15,self_attn.q_proj,0.0000223956,0.01000,5.307
|
|
15,self_attn.v_proj,0.0000020811,0.01000,5.426
|
|
15,self_attn.k_proj,0.0000056626,0.01000,5.445
|
|
15,self_attn.o_proj,0.0000022301,0.01000,1.520
|
|
15,mlp.gate_proj,0.0000347192,0.01000,3.406
|
|
15,mlp.up_proj,0.0000351988,0.01000,3.634
|
|
15,mlp.down_proj,0.0000077845,0.01000,6.912
|
|
16,self_attn.v_proj,0.0000029328,0.01000,4.544
|
|
16,self_attn.k_proj,0.0000076021,0.01000,4.568
|
|
16,self_attn.q_proj,0.0000341581,0.01000,4.649
|
|
16,self_attn.o_proj,0.0000029574,0.01000,1.566
|
|
16,mlp.up_proj,0.0000392853,0.01000,3.208
|
|
16,mlp.gate_proj,0.0000383945,0.01000,3.214
|
|
16,mlp.down_proj,0.0000100357,0.01000,5.512
|
|
17,self_attn.q_proj,0.0000354530,0.01000,4.517
|
|
17,self_attn.v_proj,0.0000032930,0.01000,4.533
|
|
17,self_attn.k_proj,0.0000075661,0.01000,4.551
|
|
17,self_attn.o_proj,0.0000044376,0.01000,1.509
|
|
17,mlp.gate_proj,0.0000417208,0.01000,3.201
|
|
17,mlp.up_proj,0.0000431488,0.01000,3.208
|
|
17,mlp.down_proj,0.0000128390,0.01000,5.423
|
|
18,self_attn.q_proj,0.0000325484,0.01000,4.493
|
|
18,self_attn.v_proj,0.0000036216,0.01000,4.508
|
|
18,self_attn.k_proj,0.0000069052,0.01000,4.522
|
|
18,self_attn.o_proj,0.0000045402,0.01000,1.529
|
|
18,mlp.gate_proj,0.0000436114,0.01000,3.217
|
|
18,mlp.up_proj,0.0000459943,0.01000,3.232
|
|
18,mlp.down_proj,0.0000143081,0.01000,5.420
|
|
19,self_attn.q_proj,0.0000389733,0.01000,4.467
|
|
19,self_attn.v_proj,0.0000042069,0.01000,4.495
|
|
19,self_attn.k_proj,0.0000081779,0.01000,4.523
|
|
19,self_attn.o_proj,0.0000049657,0.01000,1.522
|
|
19,mlp.gate_proj,0.0000456067,0.01000,3.177
|
|
19,mlp.up_proj,0.0000487316,0.01000,3.184
|
|
19,mlp.down_proj,0.0000162543,0.01000,5.404
|
|
20,self_attn.q_proj,0.0000394778,0.01000,5.646
|
|
20,self_attn.v_proj,0.0000048935,0.01000,5.670
|
|
20,self_attn.k_proj,0.0000079125,0.01000,5.712
|
|
20,self_attn.o_proj,0.0000074877,0.01000,1.554
|
|
20,mlp.gate_proj,0.0000466254,0.01000,3.202
|
|
20,mlp.up_proj,0.0000507956,0.01000,3.200
|
|
20,mlp.down_proj,0.0000190122,0.01000,5.437
|
|
21,self_attn.q_proj,0.0000425122,0.01000,4.633
|
|
21,self_attn.v_proj,0.0000054937,0.01000,4.734
|
|
21,self_attn.k_proj,0.0000084130,0.01000,4.829
|
|
21,self_attn.o_proj,0.0000087002,0.01000,1.527
|
|
21,mlp.gate_proj,0.0000512173,0.01000,3.390
|
|
21,mlp.up_proj,0.0000561848,0.01000,3.614
|
|
21,mlp.down_proj,0.0000240307,0.01000,5.434
|
|
22,self_attn.q_proj,0.0000426710,0.01000,4.411
|
|
22,self_attn.k_proj,0.0000084810,0.01000,4.457
|
|
22,self_attn.v_proj,0.0000054290,0.01000,4.463
|
|
22,self_attn.o_proj,0.0000088443,0.01000,2.071
|
|
22,mlp.gate_proj,0.0000557083,0.01000,3.178
|
|
22,mlp.up_proj,0.0000607494,0.01000,3.185
|
|
22,mlp.down_proj,0.0000272708,0.01000,5.403
|
|
23,self_attn.q_proj,0.0000450702,0.01000,4.429
|
|
23,self_attn.k_proj,0.0000091971,0.01000,4.454
|
|
23,self_attn.v_proj,0.0000064182,0.01000,4.456
|
|
23,self_attn.o_proj,0.0000108490,0.01000,1.528
|
|
23,mlp.gate_proj,0.0000583830,0.01000,3.210
|
|
23,mlp.up_proj,0.0000642057,0.01000,3.216
|
|
23,mlp.down_proj,0.0000326036,0.01000,5.404
|
|
24,self_attn.q_proj,0.0000472265,0.01000,4.426
|
|
24,self_attn.v_proj,0.0000070015,0.01000,4.464
|
|
24,self_attn.k_proj,0.0000094841,0.01000,4.472
|
|
24,self_attn.o_proj,0.0000130456,0.01000,1.549
|
|
24,mlp.gate_proj,0.0000658193,0.01000,3.195
|
|
24,mlp.up_proj,0.0000721073,0.01000,3.199
|
|
24,mlp.down_proj,0.0000394027,0.01000,5.393
|
|
25,self_attn.k_proj,0.0000099797,0.01000,4.542
|
|
25,self_attn.v_proj,0.0000084211,0.01000,4.574
|
|
25,self_attn.q_proj,0.0000518252,0.01000,4.751
|
|
25,self_attn.o_proj,0.0000112846,0.01000,1.528
|
|
25,mlp.up_proj,0.0000784803,0.01000,3.309
|
|
25,mlp.gate_proj,0.0000712152,0.01000,3.409
|
|
25,mlp.down_proj,0.0000474415,0.01000,5.389
|
|
26,self_attn.q_proj,0.0000525890,0.01000,4.498
|
|
26,self_attn.k_proj,0.0000100229,0.01000,4.550
|
|
26,self_attn.v_proj,0.0000088433,0.01000,4.573
|
|
26,self_attn.o_proj,0.0000152159,0.01000,1.528
|
|
26,mlp.gate_proj,0.0000789596,0.01000,3.292
|
|
26,mlp.up_proj,0.0000868882,0.01000,3.367
|
|
26,mlp.down_proj,0.0000558948,0.01000,6.902
|
|
27,self_attn.k_proj,0.0000098061,0.01000,5.597
|
|
27,self_attn.q_proj,0.0000516858,0.01000,5.658
|
|
27,self_attn.v_proj,0.0000085428,0.01000,5.663
|
|
27,self_attn.o_proj,0.0000154769,0.01000,1.519
|
|
27,mlp.gate_proj,0.0000842932,0.01000,3.147
|
|
27,mlp.up_proj,0.0000933967,0.01000,3.148
|
|
27,mlp.down_proj,0.0000697337,0.01000,6.840
|
|
28,self_attn.k_proj,0.0000096209,0.01000,4.523
|
|
28,self_attn.v_proj,0.0000105874,0.01000,4.536
|
|
28,self_attn.q_proj,0.0000543645,0.01000,4.558
|
|
28,self_attn.o_proj,0.0000256079,0.01000,1.521
|
|
28,mlp.gate_proj,0.0000956455,0.01000,3.191
|
|
28,mlp.up_proj,0.0001060709,0.01000,3.192
|
|
28,mlp.down_proj,0.0000868129,0.01000,5.381
|
|
29,self_attn.k_proj,0.0000105517,0.01000,4.459
|
|
29,self_attn.q_proj,0.0000600444,0.01000,4.473
|
|
29,self_attn.v_proj,0.0000127455,0.01000,4.478
|
|
29,self_attn.o_proj,0.0000294386,0.01000,1.498
|
|
29,mlp.up_proj,0.0001240473,0.01000,3.173
|
|
29,mlp.gate_proj,0.0001110740,0.01000,3.178
|
|
29,mlp.down_proj,0.0001162564,0.01000,5.380
|
|
30,self_attn.q_proj,0.0000613605,0.01000,4.478
|
|
30,self_attn.v_proj,0.0000136211,0.01000,4.521
|
|
30,self_attn.k_proj,0.0000101663,0.01000,4.528
|
|
30,self_attn.o_proj,0.0000277450,0.01000,1.515
|
|
30,mlp.up_proj,0.0001366665,0.01000,3.192
|
|
30,mlp.gate_proj,0.0001220095,0.01000,3.194
|
|
30,mlp.down_proj,0.0001533648,0.01000,5.372
|
|
31,self_attn.q_proj,0.0000629197,0.01000,4.667
|
|
31,self_attn.v_proj,0.0000150755,0.01000,4.716
|
|
31,self_attn.k_proj,0.0000100236,0.01000,4.764
|
|
31,self_attn.o_proj,0.0000394865,0.01000,1.541
|
|
31,mlp.gate_proj,0.0001309123,0.01000,3.410
|
|
31,mlp.up_proj,0.0001460293,0.01000,3.633
|
|
31,mlp.down_proj,0.0001916053,0.01000,5.504
|
|
32,self_attn.q_proj,0.0000688052,0.01000,4.727
|
|
32,self_attn.v_proj,0.0000199689,0.01000,4.771
|
|
32,self_attn.k_proj,0.0000101955,0.01000,4.908
|
|
32,self_attn.o_proj,0.0000414511,0.01000,1.675
|
|
32,mlp.gate_proj,0.0001506769,0.01000,3.193
|
|
32,mlp.up_proj,0.0001681236,0.01000,3.198
|
|
32,mlp.down_proj,0.0002321370,0.01000,5.405
|
|
33,self_attn.q_proj,0.0000790759,0.01000,5.877
|
|
33,self_attn.k_proj,0.0000119265,0.01000,6.008
|
|
33,self_attn.v_proj,0.0000245031,0.01000,6.027
|
|
33,self_attn.o_proj,0.0000481164,0.01000,1.537
|
|
33,mlp.gate_proj,0.0001631006,0.01000,3.384
|
|
33,mlp.up_proj,0.0001819707,0.01000,3.558
|
|
33,mlp.down_proj,0.0002729572,0.01000,5.446
|
|
34,self_attn.q_proj,0.0000711151,0.01000,4.468
|
|
34,self_attn.k_proj,0.0000106548,0.01000,4.487
|
|
34,self_attn.v_proj,0.0000241654,0.01000,4.530
|
|
34,self_attn.o_proj,0.0000437769,0.01000,2.056
|
|
34,mlp.up_proj,0.0001999646,0.01000,3.210
|
|
34,mlp.gate_proj,0.0001800606,0.01000,3.243
|
|
34,mlp.down_proj,0.0002995736,0.01000,6.643
|
|
35,self_attn.v_proj,0.0000267306,0.01000,4.621
|
|
35,self_attn.q_proj,0.0000763110,0.01000,4.682
|
|
35,self_attn.k_proj,0.0000114702,0.01000,4.714
|
|
35,self_attn.o_proj,0.0000432579,0.01000,1.510
|
|
35,mlp.up_proj,0.0002159799,0.01000,3.189
|
|
35,mlp.gate_proj,0.0001948314,0.01000,3.190
|
|
35,mlp.down_proj,0.0003204718,0.01000,5.387
|
|
36,self_attn.k_proj,0.0000131923,0.01000,4.720
|
|
36,self_attn.v_proj,0.0000260484,0.01000,4.742
|
|
36,self_attn.q_proj,0.0000835342,0.01000,4.761
|
|
36,self_attn.o_proj,0.0000440268,0.01000,1.542
|
|
36,mlp.gate_proj,0.0002087337,0.01000,3.193
|
|
36,mlp.up_proj,0.0002316518,0.01000,3.194
|
|
36,mlp.down_proj,0.0003474331,0.01000,5.490
|
|
37,self_attn.k_proj,0.0000136178,0.01000,4.508
|
|
37,self_attn.q_proj,0.0000840837,0.01000,4.556
|
|
37,self_attn.v_proj,0.0000244343,0.01000,4.574
|
|
37,self_attn.o_proj,0.0000274780,0.01000,1.536
|
|
37,mlp.gate_proj,0.0002214634,0.01000,3.221
|
|
37,mlp.up_proj,0.0002454306,0.01000,3.239
|
|
37,mlp.down_proj,0.0003771611,0.01000,5.486
|
|
38,self_attn.q_proj,0.0000895742,0.01000,4.848
|
|
38,self_attn.k_proj,0.0000140327,0.01000,4.926
|
|
38,self_attn.v_proj,0.0000301099,0.01000,4.934
|
|
38,self_attn.o_proj,0.0000425441,0.01000,1.517
|
|
38,mlp.up_proj,0.0002633508,0.01000,3.263
|
|
38,mlp.gate_proj,0.0002368640,0.01000,3.270
|
|
38,mlp.down_proj,0.0003942181,0.01000,6.156
|
|
39,self_attn.k_proj,0.0000140179,0.01000,4.522
|
|
39,self_attn.v_proj,0.0000313321,0.01000,4.537
|
|
39,self_attn.q_proj,0.0000908200,0.01000,4.553
|
|
39,self_attn.o_proj,0.0000534199,0.01000,1.533
|
|
39,mlp.up_proj,0.0002788311,0.01000,3.178
|
|
39,mlp.gate_proj,0.0002501276,0.01000,3.185
|
|
39,mlp.down_proj,0.0004236163,0.01000,5.421
|
|
40,self_attn.q_proj,0.0000999253,0.01000,4.997
|
|
40,self_attn.v_proj,0.0000328509,0.01000,5.026
|
|
40,self_attn.k_proj,0.0000157782,0.01000,5.058
|
|
40,self_attn.o_proj,0.0000260055,0.01000,1.529
|
|
40,mlp.up_proj,0.0002908479,0.01000,3.212
|
|
40,mlp.gate_proj,0.0002605559,0.01000,3.213
|
|
40,mlp.down_proj,0.0004451857,0.01000,5.371
|
|
41,self_attn.q_proj,0.0001023891,0.01000,5.047
|
|
41,self_attn.v_proj,0.0000318231,0.01000,5.110
|
|
41,self_attn.k_proj,0.0000167836,0.01000,5.250
|
|
41,self_attn.o_proj,0.0000375266,0.01000,1.543
|
|
41,mlp.gate_proj,0.0002773313,0.01000,3.425
|
|
41,mlp.up_proj,0.0003107931,0.01000,3.632
|
|
41,mlp.down_proj,0.0004739352,0.01000,5.388
|
|
42,self_attn.q_proj,0.0001094544,0.01000,4.987
|
|
42,self_attn.v_proj,0.0000319344,0.01000,5.083
|
|
42,self_attn.k_proj,0.0000180468,0.01000,5.092
|
|
42,self_attn.o_proj,0.0000348270,0.01000,2.082
|
|
42,mlp.gate_proj,0.0002944671,0.01000,3.209
|
|
42,mlp.up_proj,0.0003314464,0.01000,3.216
|
|
42,mlp.down_proj,0.0005044182,0.01000,6.817
|
|
43,self_attn.q_proj,0.0001125766,0.01000,4.619
|
|
43,self_attn.v_proj,0.0000335141,0.01000,4.636
|
|
43,self_attn.k_proj,0.0000183378,0.01000,4.664
|
|
43,self_attn.o_proj,0.0000649387,0.01000,1.550
|
|
43,mlp.gate_proj,0.0003134010,0.01000,3.325
|
|
43,mlp.up_proj,0.0003545903,0.01000,3.343
|
|
43,mlp.down_proj,0.0005684485,0.01000,5.398
|
|
44,self_attn.q_proj,0.0001224409,0.01000,4.553
|
|
44,self_attn.v_proj,0.0000358007,0.01000,4.602
|
|
44,self_attn.k_proj,0.0000201812,0.01000,4.633
|
|
44,self_attn.o_proj,0.0000679611,0.01000,1.541
|
|
44,mlp.gate_proj,0.0003327907,0.01000,3.233
|
|
44,mlp.up_proj,0.0003794263,0.01000,3.264
|
|
44,mlp.down_proj,0.0006130660,0.01000,5.382
|
|
45,self_attn.q_proj,0.0001163339,0.01000,4.507
|
|
45,self_attn.v_proj,0.0000354407,0.01000,4.566
|
|
45,self_attn.k_proj,0.0000192487,0.01000,4.578
|
|
45,self_attn.o_proj,0.0000531762,0.01000,2.069
|
|
45,mlp.gate_proj,0.0003525082,0.01000,3.193
|
|
45,mlp.up_proj,0.0004050766,0.01000,3.199
|
|
45,mlp.down_proj,0.0006635655,0.01000,5.426
|
|
46,self_attn.v_proj,0.0000432381,0.01000,4.585
|
|
46,self_attn.k_proj,0.0000209618,0.01000,4.626
|
|
46,self_attn.q_proj,0.0001321122,0.01000,4.648
|
|
46,self_attn.o_proj,0.0000832375,0.01000,1.539
|
|
46,mlp.gate_proj,0.0003708685,0.01000,3.260
|
|
46,mlp.up_proj,0.0004293002,0.01000,3.261
|
|
46,mlp.down_proj,0.0007252367,0.01000,5.401
|
|
47,self_attn.q_proj,0.0001240910,0.01000,4.474
|
|
47,self_attn.v_proj,0.0000418121,0.01000,4.520
|
|
47,self_attn.k_proj,0.0000194023,0.01000,4.527
|
|
47,self_attn.o_proj,0.0001032710,0.01000,1.540
|
|
47,mlp.up_proj,0.0004477853,0.01000,3.191
|
|
47,mlp.gate_proj,0.0003832070,0.01000,3.192
|
|
47,mlp.down_proj,0.0007992553,0.01000,5.531
|
|
48,self_attn.q_proj,0.0001193619,0.01000,4.535
|
|
48,self_attn.v_proj,0.0000391486,0.01000,4.563
|
|
48,self_attn.k_proj,0.0000189018,0.01000,4.652
|
|
48,self_attn.o_proj,0.0000801096,0.01000,1.545
|
|
48,mlp.up_proj,0.0004526175,0.01000,3.296
|
|
48,mlp.gate_proj,0.0003852706,0.01000,3.302
|
|
48,mlp.down_proj,0.0008187147,0.01000,5.403
|
|
49,self_attn.k_proj,0.0000191849,0.01000,4.540
|
|
49,self_attn.q_proj,0.0001215081,0.01000,4.546
|
|
49,self_attn.v_proj,0.0000401676,0.01000,4.561
|
|
49,self_attn.o_proj,0.0000807410,0.01000,1.535
|
|
49,mlp.up_proj,0.0004751309,0.01000,3.198
|
|
49,mlp.gate_proj,0.0004003226,0.01000,3.204
|
|
49,mlp.down_proj,0.0009328053,0.01000,5.450
|
|
50,self_attn.q_proj,0.0001148517,0.01000,4.624
|
|
50,self_attn.k_proj,0.0000170242,0.01000,4.670
|
|
50,self_attn.v_proj,0.0000410779,0.01000,4.674
|
|
50,self_attn.o_proj,0.0001186695,0.01000,1.545
|
|
50,mlp.gate_proj,0.0003979134,0.01000,3.191
|
|
50,mlp.up_proj,0.0004742058,0.01000,3.198
|
|
50,mlp.down_proj,0.0010534921,0.01000,5.385
|
|
51,self_attn.q_proj,0.0000908077,0.01000,4.519
|
|
51,self_attn.v_proj,0.0000311765,0.01000,4.532
|
|
51,self_attn.k_proj,0.0000149527,0.01000,4.540
|
|
51,self_attn.o_proj,0.0000697661,0.01000,1.545
|
|
51,mlp.up_proj,0.0004750221,0.01000,3.179
|
|
51,mlp.gate_proj,0.0003956558,0.01000,3.189
|
|
51,mlp.down_proj,0.0010364314,0.01000,5.418
|
|
52,self_attn.q_proj,0.0000817674,0.01000,4.758
|
|
52,self_attn.v_proj,0.0000265048,0.01000,4.802
|
|
52,self_attn.k_proj,0.0000131860,0.01000,4.860
|
|
52,self_attn.o_proj,0.0000599252,0.01000,1.541
|
|
52,mlp.gate_proj,0.0003909920,0.01000,3.215
|
|
52,mlp.up_proj,0.0004676292,0.01000,3.258
|
|
52,mlp.down_proj,0.0011807736,0.01000,5.416
|
|
53,self_attn.q_proj,0.0000785972,0.01000,4.487
|
|
53,self_attn.v_proj,0.0000265034,0.01000,4.546
|
|
53,self_attn.k_proj,0.0000117989,0.01000,4.755
|
|
53,self_attn.o_proj,0.0000894996,0.01000,1.527
|
|
53,mlp.up_proj,0.0004224250,0.01000,3.457
|
|
53,mlp.gate_proj,0.0003560778,0.01000,3.463
|
|
53,mlp.down_proj,0.0022309641,0.01000,5.440
|