ramblingpolymath's picture
Upload folder using huggingface_hub
e0f2250 verified
layer,module,loss,samples,damp,time
0,self_attn.k_proj,0.0000023605,0.01000,1.109
0,self_attn.q_proj,0.0000086476,0.01000,1.160
0,self_attn.v_proj,0.0000020977,0.01000,1.164
0,self_attn.o_proj,0.0000052760,0.01000,0.486
0,mlp.gate_proj,0.0004939233,0.01000,0.498
0,mlp.up_proj,0.0004369316,0.01000,0.501
0,mlp.down_proj,0.0000376342,0.01000,1.289
1,self_attn.k_proj,0.0000029303,0.01000,1.293
1,self_attn.q_proj,0.0000109612,0.01000,1.341
1,self_attn.v_proj,0.0000031558,0.01000,1.351
1,self_attn.o_proj,0.0000069946,0.01000,0.480
1,mlp.gate_proj,0.0261537310,0.01000,0.492
1,mlp.up_proj,0.0122033556,0.01000,0.494
1,mlp.down_proj,0.0003259176,0.01000,1.321
2,self_attn.k_proj,0.0000067474,0.01000,1.316
2,self_attn.v_proj,0.0000073258,0.01000,1.391
2,self_attn.q_proj,0.0000247712,0.01000,1.393
2,self_attn.o_proj,0.0000055998,0.01000,0.481
2,mlp.gate_proj,0.0526233968,0.01000,0.493
2,mlp.up_proj,0.0399652019,0.01000,0.492
2,mlp.down_proj,0.0000188917,0.01000,1.279
3,self_attn.k_proj,0.0000121325,0.01000,1.189
3,self_attn.v_proj,0.0000140312,0.01000,1.265
3,self_attn.q_proj,0.0000485361,0.01000,1.268
3,self_attn.o_proj,0.0000064099,0.01000,0.475
3,mlp.up_proj,0.0229898521,0.01000,0.513
3,mlp.gate_proj,0.0432896917,0.01000,0.519
3,mlp.down_proj,0.0000312140,0.01000,1.293
4,self_attn.k_proj,0.0000203165,0.01000,1.230
4,self_attn.v_proj,0.0000225437,0.01000,1.298
4,self_attn.q_proj,0.0000789346,0.01000,1.301
4,self_attn.o_proj,0.0000093670,0.01000,0.477
4,mlp.gate_proj,0.0283964607,0.01000,0.494
4,mlp.up_proj,0.0121815261,0.01000,0.500
4,mlp.down_proj,0.0000747308,0.01000,1.285
5,self_attn.k_proj,0.0000210169,0.01000,1.247
5,self_attn.v_proj,0.0000244082,0.01000,1.309
5,self_attn.q_proj,0.0000862158,0.01000,1.317
5,self_attn.o_proj,0.0000174186,0.01000,0.493
5,mlp.gate_proj,0.0070649187,0.01000,0.500
5,mlp.up_proj,0.0038377688,0.01000,0.502
5,mlp.down_proj,0.0001043571,0.01000,1.307
6,self_attn.k_proj,0.0000382548,0.01000,1.178
6,self_attn.v_proj,0.0000452049,0.01000,1.251
6,self_attn.q_proj,0.0001667164,0.01000,1.254
6,self_attn.o_proj,0.0000618556,0.01000,0.484
6,mlp.gate_proj,0.0208873181,0.01000,0.508
6,mlp.up_proj,0.0131299609,0.01000,0.513
6,mlp.down_proj,1.7196569291,0.01000,1.326
7,self_attn.k_proj,0.0001069765,0.01000,1.254
7,self_attn.q_proj,0.0004238722,0.01000,1.328
7,self_attn.v_proj,0.0001388182,0.01000,1.332
7,self_attn.o_proj,0.0000394734,0.01000,0.480
7,mlp.up_proj,0.0064389091,0.01000,0.489
7,mlp.gate_proj,0.0096065109,0.01000,0.492
7,mlp.down_proj,0.0001875460,0.01000,1.308
8,self_attn.k_proj,0.0001589175,0.01000,1.206
8,self_attn.q_proj,0.0006495502,0.01000,1.289
8,self_attn.v_proj,0.0002020608,0.01000,1.294
8,self_attn.o_proj,0.0000611982,0.01000,0.477
8,mlp.up_proj,0.0040903711,0.01000,0.495
8,mlp.gate_proj,0.0048452819,0.01000,0.500
8,mlp.down_proj,0.0003011399,0.01000,1.290
9,self_attn.k_proj,0.0001653619,0.01000,1.269
9,self_attn.v_proj,0.0002250801,0.01000,1.339
9,self_attn.q_proj,0.0006603335,0.01000,1.345
9,self_attn.o_proj,0.0000563690,0.01000,0.486
9,mlp.gate_proj,0.0079523722,0.01000,0.513
9,mlp.up_proj,0.0051725483,0.01000,0.524
9,mlp.down_proj,0.0002682274,0.01000,1.313
10,self_attn.k_proj,0.0002867612,0.01000,1.361
10,self_attn.v_proj,0.0003790154,0.01000,1.423
10,self_attn.q_proj,0.0011800335,0.01000,1.427
10,self_attn.o_proj,0.0001283710,0.01000,0.481
10,mlp.up_proj,0.0043876445,0.01000,0.532
10,mlp.gate_proj,0.0062108608,0.01000,0.537
10,mlp.down_proj,0.0002892186,0.01000,1.303
11,self_attn.k_proj,0.0001393669,0.01000,1.304
11,self_attn.v_proj,0.0001875997,0.01000,1.358
11,self_attn.q_proj,0.0005598869,0.01000,1.360
11,self_attn.o_proj,0.0000809973,0.01000,0.484
11,mlp.gate_proj,0.0047059542,0.01000,0.507
11,mlp.up_proj,0.0037915674,0.01000,0.508
11,mlp.down_proj,0.0002492499,0.01000,1.331
12,self_attn.k_proj,0.0001717698,0.01000,1.254
12,self_attn.v_proj,0.0002277587,0.01000,1.318
12,self_attn.q_proj,0.0007066898,0.01000,1.324
12,self_attn.o_proj,0.0001166942,0.01000,0.482
12,mlp.up_proj,0.0038695690,0.01000,0.491
12,mlp.gate_proj,0.0043148625,0.01000,0.493
12,mlp.down_proj,0.0005404635,0.01000,1.299
13,self_attn.k_proj,0.0001592438,0.01000,1.291
13,self_attn.v_proj,0.0001897514,0.01000,1.354
13,self_attn.q_proj,0.0006534102,0.01000,1.356
13,self_attn.o_proj,0.0001213095,0.01000,0.477
13,mlp.up_proj,0.0042377209,0.01000,0.497
13,mlp.gate_proj,0.0043138781,0.01000,0.500
13,mlp.down_proj,0.0003069095,0.01000,1.314
14,self_attn.k_proj,0.0003266167,0.01000,1.221
14,self_attn.q_proj,0.0013301039,0.01000,1.301
14,self_attn.v_proj,0.0003819207,0.01000,1.303
14,self_attn.o_proj,0.0001634345,0.01000,0.479
14,mlp.up_proj,0.0053834470,0.01000,0.512
14,mlp.gate_proj,0.0056736725,0.01000,0.518
14,mlp.down_proj,0.0007855180,0.01000,1.309
15,self_attn.k_proj,0.0003553018,0.01000,1.237
15,self_attn.q_proj,0.0014730732,0.01000,1.306
15,self_attn.v_proj,0.0004013248,0.01000,1.308
15,self_attn.o_proj,0.0002431110,0.01000,0.478
15,mlp.up_proj,0.0059416275,0.01000,0.498
15,mlp.gate_proj,0.0059575822,0.01000,0.501
15,mlp.down_proj,0.0003562036,0.01000,1.311
16,self_attn.k_proj,0.0005082224,0.01000,1.300
16,self_attn.v_proj,0.0006589728,0.01000,1.365
16,self_attn.q_proj,0.0021814368,0.01000,1.369
16,self_attn.o_proj,0.0001983794,0.01000,0.481
16,mlp.up_proj,0.0054209251,0.01000,0.509
16,mlp.gate_proj,0.0056751650,0.01000,0.509
16,mlp.down_proj,0.0011731074,0.01000,1.290
17,self_attn.k_proj,0.0004462554,0.01000,1.348
17,self_attn.v_proj,0.0005303339,0.01000,1.437
17,self_attn.q_proj,0.0020060613,0.01000,1.444
17,self_attn.o_proj,0.0001166329,0.01000,0.478
17,mlp.up_proj,0.0049886439,0.01000,0.508
17,mlp.gate_proj,0.0051612258,0.01000,0.509
17,mlp.down_proj,0.0002152923,0.01000,1.323
18,self_attn.k_proj,0.0006229532,0.01000,1.192
18,self_attn.q_proj,0.0026864192,0.01000,1.265
18,self_attn.v_proj,0.0007913217,0.01000,1.267
18,self_attn.o_proj,0.0001359088,0.01000,0.485
18,mlp.gate_proj,0.0052619321,0.01000,0.501
18,mlp.up_proj,0.0052523481,0.01000,0.508
18,mlp.down_proj,0.0007878345,0.01000,1.296
19,self_attn.k_proj,0.0009542480,0.01000,1.282
19,self_attn.v_proj,0.0012455130,0.01000,1.378
19,self_attn.q_proj,0.0045475965,0.01000,1.381
19,self_attn.o_proj,0.0001672900,0.01000,0.486
19,mlp.up_proj,0.0050511493,0.01000,0.511
19,mlp.gate_proj,0.0050360939,0.01000,0.514
19,mlp.down_proj,0.0003712999,0.01000,1.317
20,self_attn.k_proj,0.0008443741,0.01000,1.343
20,self_attn.q_proj,0.0042821188,0.01000,1.428
20,self_attn.v_proj,0.0010767965,0.01000,1.433
20,self_attn.o_proj,0.0001526671,0.01000,0.503
20,mlp.up_proj,0.0052784710,0.01000,0.509
20,mlp.gate_proj,0.0051007328,0.01000,0.512
20,mlp.down_proj,0.0003054610,0.01000,1.294
21,self_attn.k_proj,0.0012950379,0.01000,1.278
21,self_attn.q_proj,0.0064368730,0.01000,1.332
21,self_attn.v_proj,0.0016259273,0.01000,1.335
21,self_attn.o_proj,0.0002060490,0.01000,0.484
21,mlp.gate_proj,0.0058044914,0.01000,0.510
21,mlp.up_proj,0.0061378763,0.01000,0.510
21,mlp.down_proj,0.0004504223,0.01000,1.338
22,self_attn.k_proj,0.0020577744,0.01000,1.301
22,self_attn.q_proj,0.0100419408,0.01000,1.379
22,self_attn.v_proj,0.0027564173,0.01000,1.384
22,self_attn.o_proj,0.0002675739,0.01000,0.499
22,mlp.up_proj,0.0072919632,0.01000,0.509
22,mlp.gate_proj,0.0070470695,0.01000,0.513
22,mlp.down_proj,0.0008198815,0.01000,1.339
23,self_attn.k_proj,0.0019562904,0.01000,1.312
23,self_attn.v_proj,0.0025251191,0.01000,1.369
23,self_attn.q_proj,0.0104050911,0.01000,1.371
23,self_attn.o_proj,0.0003305968,0.01000,0.493
23,mlp.up_proj,0.0083080322,0.01000,0.512
23,mlp.gate_proj,0.0084858508,0.01000,0.515
23,mlp.down_proj,0.0010405632,0.01000,1.360
24,self_attn.k_proj,0.0027949394,0.01000,1.215
24,self_attn.q_proj,0.0150839109,0.01000,1.280
24,self_attn.v_proj,0.0035930271,0.01000,1.284
24,self_attn.o_proj,0.0003496374,0.01000,0.492
24,mlp.up_proj,0.0094229674,0.01000,0.507
24,mlp.gate_proj,0.0099953924,0.01000,0.509
24,mlp.down_proj,0.0013343017,0.01000,1.315
25,self_attn.k_proj,0.0025533528,0.01000,1.288
25,self_attn.v_proj,0.0032622559,0.01000,1.357
25,self_attn.q_proj,0.0116228565,0.01000,1.361
25,self_attn.o_proj,0.0001955752,0.01000,0.493
25,mlp.gate_proj,0.0116411183,0.01000,0.570
25,mlp.up_proj,0.0108317761,0.01000,0.570
25,mlp.down_proj,0.0015249005,0.01000,1.336
26,self_attn.k_proj,0.0032796197,0.01000,1.326
26,self_attn.v_proj,0.0042699698,0.01000,1.387
26,self_attn.q_proj,0.0162144237,0.01000,1.390
26,self_attn.o_proj,0.0002253313,0.01000,0.494
26,mlp.gate_proj,0.0136242376,0.01000,0.512
26,mlp.up_proj,0.0129650916,0.01000,0.514
26,mlp.down_proj,0.0016110619,0.01000,1.334
27,self_attn.k_proj,0.0040074279,0.01000,1.279
27,self_attn.v_proj,0.0054609544,0.01000,1.350
27,self_attn.q_proj,0.0205908465,0.01000,1.354
27,self_attn.o_proj,0.0002938258,0.01000,0.484
27,mlp.up_proj,0.0144908778,0.01000,0.543
27,mlp.gate_proj,0.0147092834,0.01000,0.545
27,mlp.down_proj,0.0024236814,0.01000,1.320
28,self_attn.k_proj,0.0048778417,0.01000,1.355
28,self_attn.v_proj,0.0066800955,0.01000,1.456
28,self_attn.q_proj,0.0242249303,0.01000,1.464
28,self_attn.o_proj,0.0004610685,0.01000,0.496
28,mlp.gate_proj,0.0166787647,0.01000,0.511
28,mlp.up_proj,0.0170645222,0.01000,0.518
28,mlp.down_proj,0.0034561753,0.01000,1.308
29,self_attn.k_proj,0.0070168735,0.01000,1.298
29,self_attn.q_proj,0.0395570331,0.01000,1.370
29,self_attn.v_proj,0.0093023077,0.01000,1.373
29,self_attn.o_proj,0.0004645766,0.01000,0.509
29,mlp.up_proj,0.0200837037,0.01000,0.528
29,mlp.gate_proj,0.0190078209,0.01000,0.532
29,mlp.down_proj,0.0032601025,0.01000,1.348
30,self_attn.k_proj,0.0105585617,0.01000,1.249
30,self_attn.v_proj,0.0146309942,0.01000,1.309
30,self_attn.q_proj,0.0470731675,0.01000,1.308
30,self_attn.o_proj,0.0011352525,0.01000,0.493
30,mlp.gate_proj,0.0197234040,0.01000,0.515
30,mlp.up_proj,0.0216354113,0.01000,0.519
30,mlp.down_proj,0.0043736535,0.01000,1.317
31,self_attn.k_proj,0.0120084901,0.01000,1.323
31,self_attn.q_proj,0.0593664608,0.01000,1.400
31,self_attn.v_proj,0.0192128325,0.01000,1.403
31,self_attn.o_proj,0.0008263911,0.01000,0.493
31,mlp.gate_proj,0.0193317239,0.01000,0.512
31,mlp.up_proj,0.0222545824,0.01000,0.514
31,mlp.down_proj,0.0049848173,0.01000,1.333
32,self_attn.k_proj,0.0179800382,0.01000,1.279
32,self_attn.v_proj,0.0287196182,0.01000,1.361
32,self_attn.q_proj,0.0857272829,0.01000,1.364
32,self_attn.o_proj,0.0016304227,0.01000,0.491
32,mlp.gate_proj,0.0203395590,0.01000,0.533
32,mlp.up_proj,0.0240550571,0.01000,0.541
32,mlp.down_proj,0.0058856119,0.01000,1.317
33,self_attn.k_proj,0.0239110655,0.01000,1.289
33,self_attn.q_proj,0.1421808818,0.01000,1.358
33,self_attn.v_proj,0.0520250305,0.01000,1.361
33,self_attn.o_proj,0.0014791321,0.01000,0.485
33,mlp.up_proj,0.0292948863,0.01000,0.526
33,mlp.gate_proj,0.0242292711,0.01000,0.527
33,mlp.down_proj,0.0104857002,0.01000,1.334
34,self_attn.k_proj,0.0298355458,0.01000,1.306
34,self_attn.v_proj,0.0573808693,0.01000,1.382
34,self_attn.q_proj,0.1452999115,0.01000,1.385
34,self_attn.o_proj,0.0057286620,0.01000,0.486
34,mlp.up_proj,0.0397269574,0.01000,0.513
34,mlp.gate_proj,0.0358397507,0.01000,0.516
34,mlp.down_proj,0.0386086608,0.01000,1.307
35,self_attn.k_proj,0.0255499037,0.01000,1.304
35,self_attn.q_proj,0.1034257147,0.01000,1.363
35,self_attn.v_proj,0.0298863668,0.01000,1.373
35,self_attn.o_proj,0.0074356941,0.01000,0.498
35,mlp.up_proj,0.4033937000,0.01000,0.500
35,mlp.gate_proj,0.2946298387,0.01000,0.508
35,mlp.down_proj,0.3558737437,0.01000,1.328