exp-model-parameter-similarity/results/qwen35-2b/analysis/inventory.csv

1	name	shape	ndim	dtype	numel	bytes	role	layer	mean	rms	max_abs
2	model.language_model.layers.0.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	0	-2.5419921875	2.8428578077590725	5.90625
3	model.language_model.layers.0.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	0	0.9159862995147705	0.9217019394932431	1.0107421875
4	model.language_model.layers.1.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	1	-0.766021728515625	1.562546486163045	2.75
5	model.language_model.layers.1.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	1	0.8760199546813965	0.882772150804847	1.024658203125
6	model.language_model.layers.10.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	10	-1.208251953125	1.4532067060572578	2.046875
7	model.language_model.layers.10.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	10	1.0112952142953873	1.0144369416249537	1.16796875
8	model.language_model.layers.12.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	12	-1.6552734375	1.8625297390400493	3.015625
9	model.language_model.layers.12.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	12	0.9601620733737946	0.9634251107082851	1.130859375
10	model.language_model.layers.13.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	13	-1.4144287109375	1.510479954237702	2.265625
11	model.language_model.layers.13.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	13	0.9877877533435822	0.9899024920840337	1.11474609375
12	model.language_model.layers.14.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	14	-1.09912109375	1.533638473223965	2.59375
13	model.language_model.layers.14.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	14	0.9645823240280151	0.9672255993966286	1.10595703125
14	model.language_model.layers.16.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	16	-1.7109375	1.7936473218924704	2.453125
15	model.language_model.layers.16.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	16	0.8653912842273712	0.8692723927344954	1.040771484375
16	model.language_model.layers.17.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	17	-1.768798828125	1.8086773253671764	2.40625
17	model.language_model.layers.17.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	17	0.7928063869476318	0.7980471928645709	0.993194580078125
18	model.language_model.layers.18.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	18	-1.69677734375	1.7212882979155513	2.234375
19	model.language_model.layers.18.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	18	0.7872825860977173	0.7911254701787153	0.9977569580078125
20	model.language_model.layers.2.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	2	-1.2023239135742188	1.5029171827885457	3.25
21	model.language_model.layers.2.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	2	0.8907453417778015	0.9000626793352592	1.0537109375
22	model.language_model.layers.20.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	20	-1.664794921875	1.7204063064264483	2.25
23	model.language_model.layers.20.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	20	0.8415859341621399	0.8442340143169718	1.0244140625
24	model.language_model.layers.21.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	21	-1.83447265625	1.8661585570389687	2.265625
25	model.language_model.layers.21.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	21	0.9078961908817291	0.9098948839174701	1.04296875
26	model.language_model.layers.22.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	22	-1.749267578125	1.814547993096487	2.15625
27	model.language_model.layers.22.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	22	1.0633795857429504	1.0649380921373046	1.2373046875
28	model.language_model.layers.4.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	4	-1.1160888671875	1.573153454807781	3.078125
29	model.language_model.layers.4.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	4	0.8434299230575562	0.8544616726903967	1.0498046875
30	model.language_model.layers.5.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	5	-1.345733642578125	1.9737311918644171	3.328125
31	model.language_model.layers.5.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	5	0.8853708505630493	0.8928125777319282	1.0703125
32	model.language_model.layers.6.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	6	-0.924560546875	1.1713577146067924	2.671875
33	model.language_model.layers.6.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	6	0.937565041705966	0.9418680396820469	1.10302734375
34	model.language_model.layers.8.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	8	-1.4276123046875	1.5802849067268956	3.265625
35	model.language_model.layers.8.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	8	0.9574419558048248	0.9634701406436879	1.17578125
36	model.language_model.layers.9.linear_attn.A_log	(16,)	1	F32	16	64	model.language_model.layers.*.linear_attn.A_log	9	-1.752166748046875	1.8962492752891067	2.703125
37	model.language_model.layers.9.linear_attn.norm.weight	(128,)	1	F32	128	512	model.language_model.layers.*.linear_attn.norm.weight	9	0.97660231590271	0.9809916884875952	1.1455078125
38	model.language_model.embed_tokens.weight	(248320, 2048)	2	BF16	508559360	1017118720	model.language_model.embed_tokens.weight	-1	9.87077120664951e-06	0.015007928633636286	0.197265625
39	model.language_model.layers.0.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	0	0.09555475553497672	0.15187859860523678	1.0859375
40	model.language_model.layers.0.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	0	0.0006016545487265527	0.06308888776276214	1.5234375
41	model.language_model.layers.0.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	0	-1.1572265625	6.370118909172119	12.3125
42	model.language_model.layers.0.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	0	0.00020052339823450893	0.029087606938219022	0.2216796875
43	model.language_model.layers.0.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	0	9.180475922221376e-05	0.013443365387314386	0.119140625
44	model.language_model.layers.0.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	0	5.650052049559669e-06	0.014758352047841181	0.39453125
45	model.language_model.layers.0.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	0	-1.2114403831961496e-06	0.013986197489437876	0.37109375
46	model.language_model.layers.0.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	0	-1.682266086777684e-05	0.01201362947529297	0.388671875
47	model.language_model.layers.0.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	0	-4.579636075247954e-07	0.008271090674254746	0.330078125
48	model.language_model.layers.0.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	0	1.0803703818374153e-05	0.009989848530660638	0.1875
49	model.language_model.layers.0.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	0	1.2639582468662918e-06	0.008215167992998686	0.11474609375
50	model.language_model.layers.0.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	0	-0.0067373557249084115	0.1086428965479044	0.99609375
51	model.language_model.layers.1.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	1	0.20870919525623322	0.22850867473342584	0.61328125
52	model.language_model.layers.1.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	1	0.00030097006485145056	0.05669035503528881	1.5625
53	model.language_model.layers.1.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	1	-1.052734375	3.073152660208929	6.65625
54	model.language_model.layers.1.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	1	1.4156091936001758e-05	0.024413679152183832	0.220703125
55	model.language_model.layers.1.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	1	-0.00014877098203669448	0.014451269033729877	0.15234375
56	model.language_model.layers.1.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	1	-4.853525533118445e-06	0.01482576287583218	0.255859375
57	model.language_model.layers.1.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	1	-4.412525976188464e-06	0.014568041830426256	0.2001953125
58	model.language_model.layers.1.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	1	2.332247853726113e-06	0.012184268600894286	0.455078125
59	model.language_model.layers.1.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	1	5.54108184586682e-07	0.00810784551122672	0.2734375
60	model.language_model.layers.1.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	1	9.073857168912883e-06	0.010212754570926883	0.142578125
61	model.language_model.layers.1.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	1	-2.3373373599722483e-06	0.008126413449240725	0.11865234375
62	model.language_model.layers.1.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	1	-0.005656745750457048	0.09427294029637952	0.54296875
63	model.language_model.layers.10.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	10	0.15872192569077015	0.27164572436102286	0.6171875
64	model.language_model.layers.10.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	10	-0.0007379838181596673	0.06830613403695973	1.25
65	model.language_model.layers.10.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	10	-2.16278076171875	3.041065340609617	7.28125
66	model.language_model.layers.10.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	10	-8.714331785597551e-05	0.017147214192356434	0.11767578125
67	model.language_model.layers.10.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	10	-0.00015136123823822345	0.011674008729477254	0.0859375
68	model.language_model.layers.10.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	10	-6.512366322017754e-06	0.015292003408611508	0.2431640625
69	model.language_model.layers.10.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	10	-8.52498674149371e-05	0.011903205521723808	0.150390625
70	model.language_model.layers.10.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	10	6.316189763831519e-06	0.011903507511222908	0.30859375
71	model.language_model.layers.10.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	10	-6.106724749141423e-08	0.008299914236029136	0.208984375
72	model.language_model.layers.10.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	10	-2.324051282595954e-06	0.009179932401653506	0.13671875
73	model.language_model.layers.10.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	10	-1.564070842671623e-06	0.008727795095731869	0.12255859375
74	model.language_model.layers.10.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	10	-0.011391313164494932	0.16650153545868948	0.63671875
75	model.language_model.layers.11.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	11	0.032779622822999954	0.1692437174974945	0.65625
76	model.language_model.layers.11.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	11	1.4238889311427056e-06	0.008395161732559041	0.2421875
77	model.language_model.layers.11.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	11	1.4327512621274453e-06	0.009103386394159245	0.1748046875
78	model.language_model.layers.11.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	11	2.078183690977046e-06	0.00884748655359451	0.140625
79	model.language_model.layers.11.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	11	0.01722284685820341	0.15380996823531595	0.58203125
80	model.language_model.layers.11.self_attn.k_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.k_norm.weight	11	0.6151275634765625	0.6597999706103095	1.4375
81	model.language_model.layers.11.self_attn.k_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.k_proj.weight	11	-4.683068861480871e-06	0.01174463372349867	0.1396484375
82	model.language_model.layers.11.self_attn.o_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.self_attn.o_proj.weight	11	-6.131917740882786e-06	0.012295249513636653	0.240234375
83	model.language_model.layers.11.self_attn.q_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.q_norm.weight	11	0.6161422729492188	0.6511713445577767	1.1328125
84	model.language_model.layers.11.self_attn.q_proj.weight	(4096, 2048)	2	BF16	8388608	16777216	model.language_model.layers.*.self_attn.q_proj.weight	11	-2.9925813798232885e-05	0.012163861956325002	0.2412109375
85	model.language_model.layers.11.self_attn.v_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.v_proj.weight	11	7.5102475781685385e-06	0.014888869682307635	0.1552734375
86	model.language_model.layers.12.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	12	0.26889727637171745	0.3292817300709189	0.62890625
87	model.language_model.layers.12.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	12	0.00032632781884700535	0.09772404322550603	1.234375
88	model.language_model.layers.12.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	12	-3.496551513671875	4.058185988311173	7.46875
89	model.language_model.layers.12.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	12	-0.00018116199635187513	0.020444603965792407	0.1484375
90	model.language_model.layers.12.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	12	-4.0317171379200545e-05	0.010743962668614463	0.0791015625
91	model.language_model.layers.12.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	12	7.781599651781679e-06	0.016665809696906838	0.26953125
92	model.language_model.layers.12.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	12	-4.675414117657258e-05	0.012616807270715447	0.1826171875
93	model.language_model.layers.12.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	12	1.4729152200219225e-06	0.011476801540265865	0.298828125
94	model.language_model.layers.12.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	12	1.0457843859524678e-06	0.008423235529643944	0.1884765625
95	model.language_model.layers.12.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	12	8.18576424821083e-06	0.009472447824563206	0.23828125
96	model.language_model.layers.12.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	12	1.0104942249453304e-06	0.008791148082624213	0.11376953125
97	model.language_model.layers.12.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	12	0.031112442025914788	0.12879091431054787	0.4765625
98	model.language_model.layers.13.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	13	0.232861602678895	0.28740931489560884	0.6328125
99	model.language_model.layers.13.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	13	-0.0012397262783755043	0.0771414825749899	0.67578125
100	model.language_model.layers.13.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	13	-1.475341796875	2.39097532809558	5.375
101	model.language_model.layers.13.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	13	-0.0002199913735694281	0.016203232395463157	0.1455078125
102	model.language_model.layers.13.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	13	-0.00017839931808794063	0.009952179504275616	0.10009765625
103	model.language_model.layers.13.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	13	2.9179273165786993e-06	0.015835845289678272	0.2158203125
104	model.language_model.layers.13.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	13	5.881411352340327e-06	0.012331320856281865	0.1787109375
105	model.language_model.layers.13.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	13	-4.353393460746098e-06	0.011825279279174	0.31640625
106	model.language_model.layers.13.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	13	2.896835891259483e-07	0.008557289286997264	0.271484375
107	model.language_model.layers.13.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	13	1.0580261440249853e-05	0.009664119005780037	0.1962890625
108	model.language_model.layers.13.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	13	-1.8727934769265098e-06	0.008881907189765451	0.119140625
109	model.language_model.layers.13.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	13	0.04897372436244041	0.10805549733912552	0.380859375
110	model.language_model.layers.14.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	14	0.21899888664484024	0.24888835819250885	0.515625
111	model.language_model.layers.14.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	14	0.00037967084426782094	0.08331865162655389	0.734375
112	model.language_model.layers.14.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	14	-2.2860107421875	3.3004761684662856	7.40625
113	model.language_model.layers.14.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	14	-0.0001371101245695172	0.016105199807047717	0.154296875
114	model.language_model.layers.14.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	14	-9.110311782478675e-05	0.01034784269424491	0.10986328125
115	model.language_model.layers.14.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	14	-2.1270679876183446e-06	0.016039110546304334	0.314453125
116	model.language_model.layers.14.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	14	-8.110897876532214e-06	0.012852117255934343	0.1728515625
117	model.language_model.layers.14.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	14	2.762643928013028e-06	0.011928614818943932	0.421875
118	model.language_model.layers.14.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	14	-3.7334664855249535e-06	0.008537178745857807	0.279296875
119	model.language_model.layers.14.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	14	7.169518554585423e-06	0.01050483670409655	0.263671875
120	model.language_model.layers.14.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	14	-8.076213993245956e-07	0.009027392030954798	0.13671875
121	model.language_model.layers.14.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	14	0.09636163339018822	0.11019530606933525	0.328125
122	model.language_model.layers.15.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	15	0.10911215841770172	0.12466131555593847	0.486328125
123	model.language_model.layers.15.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	15	-1.7299953231148084e-06	0.009031443773640731	0.1962890625
124	model.language_model.layers.15.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	15	1.3207215079648569e-05	0.010797157880584657	0.2451171875
125	model.language_model.layers.15.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	15	-5.836836459302668e-07	0.009495428068480694	0.1826171875
126	model.language_model.layers.15.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	15	0.160281787160784	0.17411452277120051	0.427734375
127	model.language_model.layers.15.self_attn.k_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.k_norm.weight	15	0.6101093292236328	0.6606615117915355	1.390625
128	model.language_model.layers.15.self_attn.k_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.k_proj.weight	15	1.0313123176453054e-05	0.011781971940935327	0.171875
129	model.language_model.layers.15.self_attn.o_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.self_attn.o_proj.weight	15	3.2290907635151855e-06	0.01443958574981722	0.201171875
130	model.language_model.layers.15.self_attn.q_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.q_norm.weight	15	0.6063613891601562	0.6516914189821662	1.078125
131	model.language_model.layers.15.self_attn.q_proj.weight	(4096, 2048)	2	BF16	8388608	16777216	model.language_model.layers.*.self_attn.q_proj.weight	15	-2.080716491325088e-05	0.013066587205176929	0.2333984375
132	model.language_model.layers.15.self_attn.v_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.v_proj.weight	15	1.1813592924748637e-05	0.01702842388331824	0.392578125
133	model.language_model.layers.16.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	16	0.343410836532712	0.3555100649844507	0.71875
134	model.language_model.layers.16.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	16	-0.0010187850248257746	0.12131959888922034	1.25
135	model.language_model.layers.16.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	16	-1.6535491943359375	3.4306294710677805	5.28125
136	model.language_model.layers.16.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	16	-0.00040711706062879216	0.019010974147942117	0.1474609375
137	model.language_model.layers.16.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	16	-0.00016220749716922	0.011994693576622582	0.203125
138	model.language_model.layers.16.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	16	2.9395824504673215e-06	0.01839649067123788	0.279296875
139	model.language_model.layers.16.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	16	-1.3744430889505062e-05	0.013106653141967533	0.158203125
140	model.language_model.layers.16.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	16	-1.1683691683583852e-06	0.011435638427761064	0.326171875
141	model.language_model.layers.16.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	16	-1.4952454272538357e-06	0.009066413695231633	0.353515625
142	model.language_model.layers.16.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	16	4.156314234681659e-05	0.011800534597486789	0.2578125
143	model.language_model.layers.16.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	16	-1.4486515269278531e-06	0.009458331855335966	0.11572265625
144	model.language_model.layers.16.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	16	0.22678589820861816	0.24283223012121077	0.546875
145	model.language_model.layers.17.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	17	0.40909794718027115	0.41420397619623966	0.8515625
146	model.language_model.layers.17.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	17	-0.0007928749170484176	0.1427199131150052	0.84375
147	model.language_model.layers.17.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	17	-1.5863037109375	3.145992001369952	5.8125
148	model.language_model.layers.17.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	17	-0.0002446489017984277	0.019432861311383113	0.2216796875
149	model.language_model.layers.17.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	17	-0.00028408583852979064	0.011455641742157624	0.11669921875
150	model.language_model.layers.17.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	17	-6.122790621556258e-06	0.018850718521384917	0.361328125
151	model.language_model.layers.17.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	17	1.7430077882997497e-05	0.013284800321653467	0.1337890625
152	model.language_model.layers.17.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	17	-1.8784842093881593e-06	0.011016520359717747	0.26171875
153	model.language_model.layers.17.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	17	1.6134364031145907e-06	0.009095506394657166	0.26953125
154	model.language_model.layers.17.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	17	6.465429543157655e-05	0.012932345230835652	0.396484375
155	model.language_model.layers.17.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	17	-4.222612684595094e-06	0.009451093364267178	0.140625
156	model.language_model.layers.17.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	17	0.2981297969818115	0.31212707224811526	0.58203125
157	model.language_model.layers.18.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	18	0.4494924545288086	0.4545845805845828	0.87109375
158	model.language_model.layers.18.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	18	0.000160603896650476	0.14188962547118888	0.9453125
159	model.language_model.layers.18.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	18	-1.5224609375	4.044787719211163	5.46875
160	model.language_model.layers.18.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	18	-0.000354912899865667	0.018177394584053246	0.1865234375
161	model.language_model.layers.18.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	18	-0.000348121350555175	0.011650516406628657	0.1474609375
162	model.language_model.layers.18.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	18	-2.801285425906771e-06	0.01932307704334137	0.302734375
163	model.language_model.layers.18.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	18	3.0413390159751696e-05	0.013580282672648016	0.2099609375
164	model.language_model.layers.18.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	18	5.721753637381866e-07	0.010791681091114965	0.396484375
165	model.language_model.layers.18.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	18	-6.59695743752906e-07	0.009220799866825103	0.376953125
166	model.language_model.layers.18.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	18	8.449190781037264e-05	0.013813956126686252	0.2734375
167	model.language_model.layers.18.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	18	-3.3797074411766443e-06	0.00960778958739809	0.10302734375
168	model.language_model.layers.18.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	18	0.3679823362035677	0.38049220561196123	0.67578125
169	model.language_model.layers.19.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	19	0.1011038941796869	0.2188507118664161	0.7421875
170	model.language_model.layers.19.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	19	2.4411962869774297e-06	0.009416140657580934	0.38671875
171	model.language_model.layers.19.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	19	6.661238714663713e-05	0.01359737914612424	0.349609375
172	model.language_model.layers.19.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	19	-9.332812076388979e-07	0.00973094482190661	0.1240234375
173	model.language_model.layers.19.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	19	0.3443268625997007	0.3526435167969441	0.546875
174	model.language_model.layers.19.self_attn.k_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.k_norm.weight	19	0.43672245740890503	0.5101940111828327	1.2421875
175	model.language_model.layers.19.self_attn.k_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.k_proj.weight	19	-2.6758214080602194e-07	0.01115193103746146	0.1806640625
176	model.language_model.layers.19.self_attn.o_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.self_attn.o_proj.weight	19	-8.259318417455641e-07	0.017919884244499158	0.341796875
177	model.language_model.layers.19.self_attn.q_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.q_norm.weight	19	0.4400367736816406	0.5185481967268359	1.0625
178	model.language_model.layers.19.self_attn.q_proj.weight	(4096, 2048)	2	BF16	8388608	16777216	model.language_model.layers.*.self_attn.q_proj.weight	19	6.793664314847653e-05	0.012547566379924864	0.15234375
179	model.language_model.layers.19.self_attn.v_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.v_proj.weight	19	-3.25356766062157e-05	0.021533393668245943	0.546875
180	model.language_model.layers.2.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	2	0.2333534136414528	0.25578013108533854	0.7421875
181	model.language_model.layers.2.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	2	-0.0009711920154131803	0.0699787295154593	1.203125
182	model.language_model.layers.2.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	2	-1.531646728515625	2.7997863603942768	5.28125
183	model.language_model.layers.2.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	2	0.00012737364886561409	0.020580835741280747	0.1904296875
184	model.language_model.layers.2.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	2	-0.00021474828716350203	0.012867150783559326	0.1494140625
185	model.language_model.layers.2.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	2	-7.305419878167231e-06	0.015296609635115742	0.2353515625
186	model.language_model.layers.2.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	2	1.8538136823925688e-05	0.014831222973712392	0.1708984375
187	model.language_model.layers.2.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	2	6.226499901958605e-06	0.012155681350565658	0.396484375
188	model.language_model.layers.2.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	2	-4.951895974369495e-07	0.007964106725808892	0.3671875
189	model.language_model.layers.2.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	2	6.107943125547091e-05	0.012312766730790738	0.1728515625
190	model.language_model.layers.2.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	2	-2.1764107683565404e-06	0.007951716538597723	0.14453125
191	model.language_model.layers.2.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	2	0.10721788182854652	0.14926779821439945	0.6171875
192	model.language_model.layers.20.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	20	0.39076799154281616	0.4001752339553643	0.9609375
193	model.language_model.layers.20.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	20	9.075260383421362e-05	0.1398477462038532	0.9609375
194	model.language_model.layers.20.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	20	-1.0079345703125	3.4398750076762483	5.3125
195	model.language_model.layers.20.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	20	-0.0004249333025541091	0.020555450330303295	0.2314453125
196	model.language_model.layers.20.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	20	-0.00038497815725691	0.013473339189517963	0.1669921875
197	model.language_model.layers.20.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	20	1.3699399179049887e-06	0.01875879440105595	0.3984375
198	model.language_model.layers.20.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	20	1.5797673497242037e-05	0.013929090997023318	0.27734375
199	model.language_model.layers.20.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	20	3.4517880942476487e-06	0.011156345981577036	0.39453125
200	model.language_model.layers.20.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	20	-1.2719515250439694e-06	0.00957307701852322	0.373046875
201	model.language_model.layers.20.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	20	4.00437334413904e-05	0.013427776388924359	0.265625
202	model.language_model.layers.20.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	20	-3.335567268344132e-07	0.00994430727183077	0.1455078125
203	model.language_model.layers.20.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	20	0.3715863972902298	0.37970192231618044	0.62109375
204	model.language_model.layers.21.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	21	0.44352924823760986	0.44916903078759246	1.203125
205	model.language_model.layers.21.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	21	0.0006429380024049655	0.14050966017891983	1.0234375
206	model.language_model.layers.21.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	21	0.08379364013671875	3.303196151328201	5.34375
207	model.language_model.layers.21.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	21	-0.00030593817302815296	0.021425148318092637	0.234375
208	model.language_model.layers.21.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	21	-0.0002982664101409682	0.012089513394843168	0.11767578125
209	model.language_model.layers.21.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	21	-2.9257048916112027e-06	0.018411063099048608	0.39453125
210	model.language_model.layers.21.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	21	-3.6805679609420387e-05	0.01427042687438596	0.2119140625
211	model.language_model.layers.21.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	21	1.0814873818025582e-05	0.011783994920447497	0.3359375
212	model.language_model.layers.21.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	21	3.7257452291522553e-06	0.009740438269728707	0.283203125
213	model.language_model.layers.21.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	21	4.347164541715296e-05	0.01366394178359644	0.376953125
214	model.language_model.layers.21.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	21	-1.9860518428394557e-06	0.010192647161382656	0.2001953125
215	model.language_model.layers.21.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	21	0.39837953448295593	0.4037610412929416	0.65234375
216	model.language_model.layers.22.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	22	0.31986570358276367	0.3279013006012118	1.0234375
217	model.language_model.layers.22.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	22	0.0008979494676661185	0.12143289672117986	0.98828125
218	model.language_model.layers.22.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	22	0.264739990234375	3.6225085020426246	8.0625
219	model.language_model.layers.22.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	22	-0.0006314610018307576	0.023313385449278027	0.25390625
220	model.language_model.layers.22.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	22	-0.0002720628299357486	0.013776980313481728	0.1943359375
221	model.language_model.layers.22.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	22	3.8010201965493298e-06	0.016764196896689124	0.4296875
222	model.language_model.layers.22.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	22	-4.9468020722115424e-05	0.014891482667100319	0.248046875
223	model.language_model.layers.22.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	22	1.3340557990845076e-06	0.012518738787194348	0.55078125
224	model.language_model.layers.22.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	22	-3.2801688128341906e-06	0.0096870165213663	0.39453125
225	model.language_model.layers.22.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	22	6.999503861985796e-05	0.013968549839218811	0.396484375
226	model.language_model.layers.22.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	22	3.97610155118804e-06	0.010452139908499549	0.1513671875
227	model.language_model.layers.22.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	22	0.38950735330581665	0.3927199440840361	0.65234375
228	model.language_model.layers.23.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	23	0.16185743268579245	0.22320587027448527	0.87890625
229	model.language_model.layers.23.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	23	2.200153014944121e-06	0.009198179693873125	0.9140625
230	model.language_model.layers.23.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	23	5.746251235838462e-05	0.01555093104020481	0.4296875
231	model.language_model.layers.23.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	23	-1.4030004445502939e-06	0.01144567089869159	0.255859375
232	model.language_model.layers.23.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	23	0.2778373658657074	0.28538803537333535	0.796875
233	model.language_model.layers.23.self_attn.k_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.k_norm.weight	23	0.3784341812133789	0.45290137200158004	1.296875
234	model.language_model.layers.23.self_attn.k_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.k_proj.weight	23	-3.258974928144198e-06	0.010211249530655503	0.1923828125
235	model.language_model.layers.23.self_attn.o_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.self_attn.o_proj.weight	23	4.249854031940226e-06	0.014946339830350153	0.36328125
236	model.language_model.layers.23.self_attn.q_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.q_norm.weight	23	0.3749351501464844	0.4735104392931629	0.9921875
237	model.language_model.layers.23.self_attn.q_proj.weight	(4096, 2048)	2	BF16	8388608	16777216	model.language_model.layers.*.self_attn.q_proj.weight	23	2.8210594946158612e-05	0.013931200188097417	0.3046875
238	model.language_model.layers.23.self_attn.v_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.v_proj.weight	23	-4.7418587849623606e-06	0.0201368708703942	0.365234375
239	model.language_model.layers.3.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	3	0.14525676146149635	0.1640384010422585	0.7109375
240	model.language_model.layers.3.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	3	-3.666761125140459e-07	0.007925089389266608	0.322265625
241	model.language_model.layers.3.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	3	-7.894271173424181e-06	0.011534900694163063	0.158203125
242	model.language_model.layers.3.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	3	2.630765779604652e-06	0.008013811534961623	0.11865234375
243	model.language_model.layers.3.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	3	0.046131135895848274	0.12433499188529953	0.51171875
244	model.language_model.layers.3.self_attn.k_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.k_norm.weight	3	0.4114065170288086	0.46410242264785667	1.59375
245	model.language_model.layers.3.self_attn.k_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.k_proj.weight	3	-1.2478612181981985e-05	0.012234452222983938	0.142578125
246	model.language_model.layers.3.self_attn.o_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.self_attn.o_proj.weight	3	7.17851804013514e-07	0.011753633554238597	0.380859375
247	model.language_model.layers.3.self_attn.q_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.q_norm.weight	3	0.4230690002441406	0.4549413197073127	1.1796875
248	model.language_model.layers.3.self_attn.q_proj.weight	(4096, 2048)	2	BF16	8388608	16777216	model.language_model.layers.*.self_attn.q_proj.weight	3	4.508237743732629e-05	0.016050479790290943	0.3203125
249	model.language_model.layers.3.self_attn.v_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.v_proj.weight	3	4.0868584337827585e-06	0.011898094706242741	0.1396484375
250	model.language_model.layers.4.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	4	0.2650436982512474	0.28638167705127865	0.71875
251	model.language_model.layers.4.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	4	3.396201100258622e-05	0.09066321443526168	0.8125
252	model.language_model.layers.4.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	4	-2.729248046875	3.8747778798092267	5.96875
253	model.language_model.layers.4.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	4	-0.00011186926542450237	0.02038835749963588	0.1728515625
254	model.language_model.layers.4.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	4	-0.00019476671903717602	0.010351199541655327	0.1259765625
255	model.language_model.layers.4.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	4	1.2304641167435136e-06	0.01636563283090178	0.29296875
256	model.language_model.layers.4.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	4	2.0802682229954816e-05	0.013888945005603458	0.166015625
257	model.language_model.layers.4.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	4	-2.994475370804439e-06	0.011735409435323977	0.396484375
258	model.language_model.layers.4.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	4	-4.1091264927226615e-06	0.00801339942052328	0.2451171875
259	model.language_model.layers.4.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	4	1.6863014756946307e-05	0.011355842511871286	0.2080078125
260	model.language_model.layers.4.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	4	1.027859200892813e-06	0.008108758248932731	0.10302734375
261	model.language_model.layers.4.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	4	0.0494824443012476	0.12864073061216597	0.5234375
262	model.language_model.layers.5.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	5	0.22753581404685974	0.2630511444050265	0.67578125
263	model.language_model.layers.5.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	5	0.00038598675951107	0.08068910936433069	1.1015625
264	model.language_model.layers.5.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	5	-2.72894287109375	3.6278404173514955	6.6875
265	model.language_model.layers.5.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	5	-0.0001803523750822933	0.018341404674334767	0.1455078125
266	model.language_model.layers.5.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	5	-0.00022759488123824667	0.010625336231416064	0.10400390625
267	model.language_model.layers.5.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	5	3.021544299360978e-06	0.01587561641265017	0.3046875
268	model.language_model.layers.5.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	5	1.619939023567163e-05	0.013311542875305954	0.1533203125
269	model.language_model.layers.5.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	5	7.180698611445463e-06	0.011705867874160678	0.404296875
270	model.language_model.layers.5.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	5	-3.832363420119428e-06	0.008129977884391225	0.25390625
271	model.language_model.layers.5.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	5	9.510474803579592e-06	0.011259738864004266	0.1318359375
272	model.language_model.layers.5.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	5	4.334927638522066e-08	0.008256794109219937	0.08349609375
273	model.language_model.layers.5.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	5	0.0527042793110013	0.15491478237820172	0.578125
274	model.language_model.layers.6.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	6	0.18705136142671108	0.23969713140560028	0.609375
275	model.language_model.layers.6.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	6	0.0003755964487671311	0.07146913561403648	0.75390625
276	model.language_model.layers.6.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	6	-1.911773681640625	2.9807612149394664	6.15625
277	model.language_model.layers.6.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	6	-0.0002217653484422044	0.016199257108442264	0.1337890625
278	model.language_model.layers.6.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	6	-0.0002016041112824496	0.011786386085972541	0.1455078125
279	model.language_model.layers.6.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	6	3.843747654041589e-06	0.015354747770723804	0.21484375
280	model.language_model.layers.6.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	6	-9.215484209998404e-06	0.013138127645844377	0.193359375
281	model.language_model.layers.6.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	6	4.4970565675102325e-06	0.012014377201321634	0.310546875
282	model.language_model.layers.6.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	6	1.5256064373652192e-06	0.008180750870201545	0.2373046875
283	model.language_model.layers.6.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	6	1.2075660691879235e-05	0.010919152343969056	0.2333984375
284	model.language_model.layers.6.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	6	2.4837448766669578e-06	0.008417535304985934	0.09814453125
285	model.language_model.layers.6.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	6	0.04677234560949728	0.14343473354286257	0.56640625
286	model.language_model.layers.7.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	7	0.01859602495096624	0.09770610871894504	0.53515625
287	model.language_model.layers.7.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	7	-2.069178868239751e-06	0.008313764288599495	0.30859375
288	model.language_model.layers.7.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	7	-5.941976052590073e-06	0.010130333371973213	0.1865234375
289	model.language_model.layers.7.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	7	-1.921608185482948e-06	0.008620142534023984	0.10791015625
290	model.language_model.layers.7.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	7	0.03399748355150223	0.17481274831958912	0.625
291	model.language_model.layers.7.self_attn.k_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.k_norm.weight	7	0.5165120363235474	0.5423433220393242	1.09375
292	model.language_model.layers.7.self_attn.k_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.k_proj.weight	7	6.845853454978679e-06	0.011321329966324158	0.12353515625
293	model.language_model.layers.7.self_attn.o_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.self_attn.o_proj.weight	7	1.0774090243398544e-05	0.011294127412937538	0.236328125
294	model.language_model.layers.7.self_attn.q_norm.weight	(256,)	1	BF16	256	512	model.language_model.layers.*.self_attn.q_norm.weight	7	0.5257186889648438	0.5454621661599409	1.1953125
295	model.language_model.layers.7.self_attn.q_proj.weight	(4096, 2048)	2	BF16	8388608	16777216	model.language_model.layers.*.self_attn.q_proj.weight	7	1.3410202473564982e-06	0.013098970846866802	0.26171875
296	model.language_model.layers.7.self_attn.v_proj.weight	(512, 2048)	2	BF16	1048576	2097152	model.language_model.layers.*.self_attn.v_proj.weight	7	-4.638805624887499e-06	0.011705499680617187	0.1376953125
297	model.language_model.layers.8.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	8	0.21140070259571075	0.29139364044388155	0.60546875
298	model.language_model.layers.8.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	8	-0.0008830481529571443	0.07194979471045664	0.734375
299	model.language_model.layers.8.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	8	-2.32696533203125	3.1389153700014405	5.40625
300	model.language_model.layers.8.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	8	-7.89401556176017e-05	0.01640450978485818	0.1240234375
301	model.language_model.layers.8.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	8	-0.00019124166351502936	0.009413019985098999	0.0830078125
302	model.language_model.layers.8.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	8	-1.0459140759450092e-06	0.01570452643614291	0.2265625
303	model.language_model.layers.8.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	8	6.922933192797694e-06	0.012484979769894367	0.2275390625
304	model.language_model.layers.8.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	8	2.282237288962069e-07	0.011714720270195043	0.3515625
305	model.language_model.layers.8.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	8	1.9946693415948355e-06	0.008243732742036089	0.29296875
306	model.language_model.layers.8.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	8	-1.3840076219445603e-06	0.009590909948543426	0.15625
307	model.language_model.layers.8.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	8	3.841095268237252e-06	0.00861522200030427	0.09130859375
308	model.language_model.layers.8.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	8	0.010415758239105344	0.18284911199552537	0.66015625
309	model.language_model.layers.9.input_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.input_layernorm.weight	9	0.19137806724756956	0.296521861015528	0.57421875
310	model.language_model.layers.9.linear_attn.conv1d.weight	(6144, 1, 4)	3	BF16	24576	49152	model.language_model.layers.*.linear_attn.conv1d.weight	9	-0.000410568358773844	0.06652172297471458	1.3359375
311	model.language_model.layers.9.linear_attn.dt_bias	(16,)	1	BF16	16	32	model.language_model.layers.*.linear_attn.dt_bias	9	-2.45068359375	3.1450531520506346	4.90625
312	model.language_model.layers.9.linear_attn.in_proj_a.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_a.weight	9	-0.00011285979962849524	0.018485456249646506	0.251953125
313	model.language_model.layers.9.linear_attn.in_proj_b.weight	(16, 2048)	2	BF16	32768	65536	model.language_model.layers.*.linear_attn.in_proj_b.weight	9	-0.00012505355687153497	0.012157132620716115	0.10009765625
314	model.language_model.layers.9.linear_attn.in_proj_qkv.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.linear_attn.in_proj_qkv.weight	9	-1.83865233245677e-06	0.015200480417789385	0.30078125
315	model.language_model.layers.9.linear_attn.in_proj_z.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.in_proj_z.weight	9	-2.0241770911732723e-05	0.012578215645634584	0.1982421875
316	model.language_model.layers.9.linear_attn.out_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	model.language_model.layers.*.linear_attn.out_proj.weight	9	-4.150400907093621e-06	0.01150305952966105	0.30078125
317	model.language_model.layers.9.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.down_proj.weight	9	-2.7189171275125937e-06	0.008310183109864908	0.181640625
318	model.language_model.layers.9.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.gate_proj.weight	9	-9.032502292217909e-06	0.00903253707533701	0.1669921875
319	model.language_model.layers.9.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	model.language_model.layers.*.mlp.up_proj.weight	9	-5.926681719845353e-07	0.008713214518297324	0.0927734375
320	model.language_model.layers.9.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	model.language_model.layers.*.post_attention_layernorm.weight	9	0.0009866869077086449	0.17870262924322744	0.6484375
321	model.language_model.norm.weight	(2048,)	1	BF16	2048	4096	model.language_model.norm.weight	-1	2.536298483610153	2.5765266808418485	5.375
322	model.visual.blocks.0.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	0	0.0056819673627614975	0.4223296682397815	3.515625
323	model.visual.blocks.0.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	0	2.8629653116164083e-05	0.013697778976293876	0.353515625
324	model.visual.blocks.0.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	0	-0.0006211028861192366	0.8058543942936214	6.3125
325	model.visual.blocks.0.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	0	2.288061551664981e-05	0.02266044393425182	0.640625
326	model.visual.blocks.0.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	0	-2.248420387506485	2.785209948019622	9.25
327	model.visual.blocks.0.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	0	-1.672273021108577e-05	0.01791097511042567	0.2890625
328	model.visual.blocks.0.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	0	-0.010476455092430115	0.8661675219608709	10.875
329	model.visual.blocks.0.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	0	7.985690316429744e-05	0.01681887613844911	0.26171875
330	model.visual.blocks.0.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	0	-0.0007249293848872185	0.21335208117994894	3.8125
331	model.visual.blocks.0.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	0	0.5173702943138778	0.9214386100936024	4.03125
332	model.visual.blocks.0.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	0	0.002009127005294431	0.26724968567574725	4.90625
333	model.visual.blocks.0.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	0	2.059753055276815	3.6960545327961047	16.875
334	model.visual.blocks.1.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	1	0.03787066414952278	0.7577770028883627	7.6875
335	model.visual.blocks.1.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	1	1.0665584427915764e-05	0.013909349158950824	0.35546875
336	model.visual.blocks.1.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	1	0.005118881289187509	0.6554565198492014	6.96875
337	model.visual.blocks.1.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	1	-2.2588287930780382e-05	0.022658501611919644	0.50390625
338	model.visual.blocks.1.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	1	-1.8916514813899994	2.255432446216723	4.78125
339	model.visual.blocks.1.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	1	-0.00015137788937700248	0.018427025670974255	0.384765625
340	model.visual.blocks.1.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	1	-0.02125891763716936	0.48354598792262593	8.8125
341	model.visual.blocks.1.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	1	4.1878749072722654e-05	0.016416665982819812	0.59375
342	model.visual.blocks.1.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	1	-0.006031324039213359	0.20026363711287062	3.125
343	model.visual.blocks.1.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	1	0.5489383637905121	0.676293812386044	2.015625
344	model.visual.blocks.1.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	1	-0.0010115213226526976	0.226877326061835	2.875
345	model.visual.blocks.1.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	1	0.9165963572449982	1.1850193608703092	3.484375
346	model.visual.blocks.10.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	10	0.0013865428045392036	0.3155090787478211	4.96875
347	model.visual.blocks.10.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	10	-4.397379537918189e-06	0.012832670932776341	0.1201171875
348	model.visual.blocks.10.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	10	-0.00729733055535083	0.4923193573431798	6.5
349	model.visual.blocks.10.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	10	2.8232800771503066e-06	0.01617202900396593	0.234375
350	model.visual.blocks.10.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	10	-1.645782470703125	1.7657915613666026	7.8125
351	model.visual.blocks.10.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	10	-5.362843342912593e-05	0.01571570549852373	0.28125
352	model.visual.blocks.10.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	10	-0.002808693330734968	0.20955213395129205	2.609375
353	model.visual.blocks.10.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	10	-4.729164932659735e-06	0.012869168141970897	0.62109375
354	model.visual.blocks.10.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	10	0.003513883682899177	0.19258665385120421	2.375
355	model.visual.blocks.10.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	10	0.9836215972900391	1.0083027671073959	1.8125
356	model.visual.blocks.10.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	10	0.000604923814535141	0.2915448741855378	3.953125
357	model.visual.blocks.10.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	10	1.1706929206848145	1.1883884565165725	2.40625
358	model.visual.blocks.11.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	11	-0.0005531555507332087	0.27908196456952605	4.96875
359	model.visual.blocks.11.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	11	-3.6013991529804112e-06	0.012820869846561344	0.0986328125
360	model.visual.blocks.11.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	11	0.00846743700094521	0.48997687252328	6.90625
361	model.visual.blocks.11.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	11	9.277315033732561e-06	0.015729353782592298	0.1767578125
362	model.visual.blocks.11.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	11	-1.6464985609054565	1.722120238661639	6.03125
363	model.visual.blocks.11.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	11	-3.589357073445487e-05	0.015698389546222692	0.328125
364	model.visual.blocks.11.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	11	-0.00445837527513504	0.2281571578445295	3.03125
365	model.visual.blocks.11.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	11	-8.2175139034385e-07	0.014062640336574176	0.5390625
366	model.visual.blocks.11.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	11	0.0063120657578110695	0.19104643837290222	3.1875
367	model.visual.blocks.11.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	11	1.0900201797485352	1.11257957339	1.890625
368	model.visual.blocks.11.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	11	0.02426927164196968	0.38187088189437013	4.46875
369	model.visual.blocks.11.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	11	1.3532802313566208	1.381797140286228	3.578125
370	model.visual.blocks.12.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	12	-0.0026703281328082085	0.1916711651620828	2.046875
371	model.visual.blocks.12.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	12	4.0955608962556234e-07	0.012925623041989713	0.1455078125
372	model.visual.blocks.12.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	12	0.008885961996080974	0.5122118241036924	6.5
373	model.visual.blocks.12.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	12	-9.870303735948216e-06	0.01573086232798125	0.16015625
374	model.visual.blocks.12.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	12	-1.675450623035431	1.7334162851669006	3.453125
375	model.visual.blocks.12.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	12	-8.740557205228275e-06	0.014830930647847022	0.408203125
376	model.visual.blocks.12.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	12	-0.005204610526561737	0.26138935010758596	2.9375
377	model.visual.blocks.12.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	12	1.7673791958203178e-05	0.01386013349041631	0.40234375
378	model.visual.blocks.12.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	12	0.010884693590924144	0.2269366679227373	4.4375
379	model.visual.blocks.12.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	12	1.1681642532348633	1.1884347634813108	2.390625
380	model.visual.blocks.12.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	12	0.01296179462224245	0.4114089854061476	5.6875
381	model.visual.blocks.12.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	12	1.344668447971344	1.3677649716188205	2.328125
382	model.visual.blocks.13.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	13	-0.0028251297771930695	0.24074961333040454	2.34375
383	model.visual.blocks.13.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	13	2.5278697873831746e-06	0.01285373134719242	0.1064453125
384	model.visual.blocks.13.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	13	0.004933949753952523	0.508857160517705	7.15625
385	model.visual.blocks.13.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	13	1.9118003685703044e-07	0.015042486712391608	0.1669921875
386	model.visual.blocks.13.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	13	-1.7249782234430313	1.7699195917996853	3.46875
387	model.visual.blocks.13.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	13	-3.6795391052404924e-05	0.014446679506643701	0.416015625
388	model.visual.blocks.13.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	13	-0.0022364631295204163	0.27349516648220606	3.859375
389	model.visual.blocks.13.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	13	5.478725110724669e-06	0.013285561268431308	0.341796875
390	model.visual.blocks.13.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	13	0.015306847577448934	0.27487751521193093	6.1875
391	model.visual.blocks.13.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	13	1.268209457397461	1.287942725109198	2.359375
392	model.visual.blocks.13.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	13	-0.003963736351579428	0.42726025831730696	5.21875
393	model.visual.blocks.13.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	13	1.3601853847503662	1.3767604243470128	2.015625
394	model.visual.blocks.14.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	14	-0.003052172716706991	0.21088079614630725	3.375
395	model.visual.blocks.14.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	14	-1.1134785495858779e-06	0.012735885919582902	0.1611328125
396	model.visual.blocks.14.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	14	0.003906862887864311	0.5396591512615192	7.15625
397	model.visual.blocks.14.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	14	1.169477530685766e-05	0.015290766734037807	0.154296875
398	model.visual.blocks.14.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	14	-1.36743825674057	1.416465957664333	3.328125
399	model.visual.blocks.14.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	14	-0.00016947123852519008	0.013272032998930029	0.1474609375
400	model.visual.blocks.14.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	14	-0.0021008243784308434	0.17204831815289337	2.734375
401	model.visual.blocks.14.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	14	2.1631967396136542e-06	0.013681268914449974	0.44921875
402	model.visual.blocks.14.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	14	0.01591563131660223	0.312620166366634	8.25
403	model.visual.blocks.14.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	14	1.3175182342529297	1.3302436689183337	2.015625
404	model.visual.blocks.14.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	14	0.1486361138522625	1.1076539753453722	4.25
405	model.visual.blocks.14.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	14	3.054824598133564	3.133953286674968	5.03125
406	model.visual.blocks.15.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	15	-0.003838975913822651	0.17870155036895466	2.046875
407	model.visual.blocks.15.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	15	2.1557483374512465e-06	0.012738003993849507	0.1748046875
408	model.visual.blocks.15.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	15	-0.0070781482791062444	0.5481550569364706	8.1875
409	model.visual.blocks.15.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	15	1.8805244741589473e-06	0.015028560293926872	0.138671875
410	model.visual.blocks.15.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	15	-1.2592892870306969	1.3363415167024717	3.828125
411	model.visual.blocks.15.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	15	-0.0001719071445260706	0.013613661762691076	0.150390625
412	model.visual.blocks.15.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	15	-0.004280758090317249	0.22024041578351156	1.3203125
413	model.visual.blocks.15.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	15	-1.4436593793638874e-05	0.0138859545324591	0.4375
414	model.visual.blocks.15.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	15	0.01718392875045538	0.3302859808392976	8.375
415	model.visual.blocks.15.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	15	1.3481388092041016	1.357684000352654	2.09375
416	model.visual.blocks.15.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	15	0.21574118733406067	1.6791112424771022	4.59375
417	model.visual.blocks.15.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	15	4.459657579660416	4.584192991018382	6.90625
418	model.visual.blocks.16.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	16	-0.001141368702519685	0.17187718118886977	1.4765625
419	model.visual.blocks.16.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	16	-9.010508974505171e-07	0.013030151340051142	0.11572265625
420	model.visual.blocks.16.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	16	-0.003146370562414328	0.5747692983747378	7.875
421	model.visual.blocks.16.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	16	7.913643638816451e-06	0.014997625709589514	0.19140625
422	model.visual.blocks.16.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	16	-1.254018947482109	1.3324690973240458	4.0625
423	model.visual.blocks.16.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	16	-0.0001544157969156773	0.01342578177786983	0.1455078125
424	model.visual.blocks.16.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	16	-0.002572661265730858	0.2296740317693101	2.046875
425	model.visual.blocks.16.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	16	-1.2149443716483188e-05	0.013883817502173138	0.345703125
426	model.visual.blocks.16.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	16	0.022709594340994954	0.37735895627898264	9.8125
427	model.visual.blocks.16.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	16	1.4540157318115234	1.4634179653266648	2.1875
428	model.visual.blocks.16.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	16	0.18935611844062805	2.0355711199787074	6.0
429	model.visual.blocks.16.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	16	5.341764807701111	5.473404786269683	7.90625
430	model.visual.blocks.17.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	17	0.0010246038436889648	0.2094856224874406	1.5859375
431	model.visual.blocks.17.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	17	-2.305236045496706e-06	0.013429564136500571	0.2001953125
432	model.visual.blocks.17.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	17	0.0007098486336568991	0.5673033733273393	7.84375
433	model.visual.blocks.17.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	17	-1.9605784129887263e-06	0.014858123558947355	0.1181640625
434	model.visual.blocks.17.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	17	-1.2608060913626105	1.3344331944274648	4.96875
435	model.visual.blocks.17.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	17	-0.00024945183689631736	0.01327430448006607	0.1513671875
436	model.visual.blocks.17.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	17	-0.0037037022411823273	0.3233218477507246	3.640625
437	model.visual.blocks.17.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	17	-1.5574131797709e-05	0.013947912596998567	0.2890625
438	model.visual.blocks.17.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	17	0.02418094128370285	0.36228133811509267	8.8125
439	model.visual.blocks.17.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	17	1.5454788208007812	1.5540872689932543	2.34375
440	model.visual.blocks.17.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	17	0.3789477199316025	2.3624701748229344	7.46875
441	model.visual.blocks.17.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	17	6.084241628646851	6.227228139512012	8.4375
442	model.visual.blocks.18.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	18	-0.0002320706844329834	0.2934008246430531	1.1953125
443	model.visual.blocks.18.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	18	-6.532082189314448e-07	0.013284318756608127	0.158203125
444	model.visual.blocks.18.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	18	-0.0057055339954483015	0.5908193339357068	9.25
445	model.visual.blocks.18.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	18	4.928585952967968e-06	0.014708558443394285	0.2216796875
446	model.visual.blocks.18.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	18	-1.2480670548975468	1.3291303175041957	5.0625
447	model.visual.blocks.18.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	18	-0.00021408203113450902	0.013495977011313135	0.150390625
448	model.visual.blocks.18.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	18	-0.006308715790510178	0.3856628539897182	4.3125
449	model.visual.blocks.18.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	18	-3.2339109456755444e-05	0.014627635036042322	0.318359375
450	model.visual.blocks.18.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	18	0.02438737452030182	0.412171430074191	9.875
451	model.visual.blocks.18.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	18	1.5765914916992188	1.582837659856145	2.3125
452	model.visual.blocks.18.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	18	0.4297136813402176	3.1746328527745495	10.125
453	model.visual.blocks.18.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	18	8.43129649758339	8.632484963591324	12.0625
454	model.visual.blocks.19.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	19	-0.004621189087629318	0.3139398128022543	1.328125
455	model.visual.blocks.19.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	19	2.4595190205589645e-06	0.013508958055272125	0.1337890625
456	model.visual.blocks.19.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	19	0.005580020369961858	0.5351795263988486	8.1875
457	model.visual.blocks.19.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	19	-8.630430732773734e-06	0.014762091303607939	0.1318359375
458	model.visual.blocks.19.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	19	-1.2422089144820347	1.3163568037560458	4.5625
459	model.visual.blocks.19.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	19	-0.00018224952321353738	0.013614127660122474	0.16796875
460	model.visual.blocks.19.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	19	-0.007145557086914778	0.4602625036781678	4.1875
461	model.visual.blocks.19.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	19	-4.168556236101156e-05	0.014827426301555785	0.1640625
462	model.visual.blocks.19.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	19	0.024289263412356377	0.38014348627552946	6.5625
463	model.visual.blocks.19.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	19	1.5708999633789062	1.5778643421156753	2.46875
464	model.visual.blocks.19.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	19	0.33808582834899426	3.3086580127585967	10.4375
465	model.visual.blocks.19.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	19	10.046417891979218	10.27741256232265	14.5625
466	model.visual.blocks.2.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	2	0.020055142042110674	0.3886311638709507	4.28125
467	model.visual.blocks.2.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	2	-2.695733576807413e-06	0.013976514875259815	0.255859375
468	model.visual.blocks.2.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	2	-0.013754264956029752	0.657041102431288	8.4375
469	model.visual.blocks.2.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	2	2.5094986518444293e-06	0.020591849089717593	0.302734375
470	model.visual.blocks.2.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	2	-2.050982117652893	2.5296018322840883	4.78125
471	model.visual.blocks.2.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	2	3.021457652678636e-06	0.01653758038173641	0.35546875
472	model.visual.blocks.2.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	2	-0.01768375840038061	0.3234429143823406	5.59375
473	model.visual.blocks.2.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	2	2.5083720841499735e-06	0.014604041553001833	0.58203125
474	model.visual.blocks.2.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	2	-0.0018650367856025696	0.1970889226403788	3.3125
475	model.visual.blocks.2.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	2	0.6477055847644806	0.705977945861401	1.734375
476	model.visual.blocks.2.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	2	0.0044156142976135015	0.1629384723954203	2.28125
477	model.visual.blocks.2.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	2	1.049049954948714	1.2132500636992718	3.0
478	model.visual.blocks.20.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	20	-0.007338074967265129	0.3249699629246988	1.9296875
479	model.visual.blocks.20.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	20	3.2072206779254486e-07	0.014146542579561038	0.142578125
480	model.visual.blocks.20.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	20	-0.0014855863992124796	0.5315386037202189	7.8125
481	model.visual.blocks.20.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	20	-3.534431219938868e-06	0.01480353550453723	0.134765625
482	model.visual.blocks.20.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	20	-1.2434953674674034	1.323903681900149	4.15625
483	model.visual.blocks.20.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	20	-6.702584891227908e-05	0.013731709166772268	0.150390625
484	model.visual.blocks.20.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	20	-0.0063021189998835325	0.5291946069594037	4.625
485	model.visual.blocks.20.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	20	-4.8746930603832395e-05	0.01500120652131212	0.1533203125
486	model.visual.blocks.20.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	20	0.0250953808426857	0.44610627333196545	6.28125
487	model.visual.blocks.20.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	20	1.6392402648925781	1.6461320049763404	2.8125
488	model.visual.blocks.20.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	20	0.0293462872505188	3.1623750669665887	10.25
489	model.visual.blocks.20.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	20	11.327821254730225	11.56503368296681	15.75
490	model.visual.blocks.21.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	21	-0.005094312131404877	0.3524695004655374	2.953125
491	model.visual.blocks.21.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	21	-1.5384484597091852e-06	0.014542213556737195	0.1357421875
492	model.visual.blocks.21.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	21	0.002228708937764168	0.5125241811949673	7.375
493	model.visual.blocks.21.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	21	1.0859385383884165e-05	0.014994967131387578	0.173828125
494	model.visual.blocks.21.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	21	-1.2665919363498688	1.3450251529553447	3.46875
495	model.visual.blocks.21.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	21	7.30989772137064e-05	0.013954792610339387	0.2578125
496	model.visual.blocks.21.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	21	0.003942374140024185	0.8887231783004025	5.4375
497	model.visual.blocks.21.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	21	-5.30296018196319e-05	0.015118207294661507	0.20703125
498	model.visual.blocks.21.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	21	0.03733087331056595	0.4753083526711642	5.8125
499	model.visual.blocks.21.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	21	1.5873088836669922	1.595838376433378	3.1875
500	model.visual.blocks.21.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	21	-0.07360374182462692	3.0850272367238394	17.125
501	model.visual.blocks.21.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	21	12.204975128173828	12.389441211741739	15.875
502	model.visual.blocks.22.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	22	0.005250638350844383	0.5808595524391316	3.5
503	model.visual.blocks.22.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	22	2.0765462032112936e-06	0.014772226332934188	0.18359375
504	model.visual.blocks.22.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	22	0.014487470247937987	0.4916721195343452	6.28125
505	model.visual.blocks.22.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	22	-5.31823748935641e-06	0.01523024465727359	0.166015625
506	model.visual.blocks.22.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	22	-1.2670710682868958	1.3412129116547036	3.875
507	model.visual.blocks.22.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	22	0.0004379041676110876	0.014189801218711325	0.23828125
508	model.visual.blocks.22.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	22	0.011957859620451927	0.7787687092193024	4.3125
509	model.visual.blocks.22.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	22	-2.478536209907234e-05	0.014944462334069182	0.15234375
510	model.visual.blocks.22.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	22	0.022316202521324158	0.533177673147604	6.6875
511	model.visual.blocks.22.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	22	1.5854969024658203	1.5964364161053683	3.34375
512	model.visual.blocks.22.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	22	-0.5513232499361038	2.664964048785582	17.875
513	model.visual.blocks.22.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	22	10.946296691894531	11.013918537503798	14.5
514	model.visual.blocks.23.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	23	0.004559919238090515	1.1180409459483411	6.09375
515	model.visual.blocks.23.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	23	-1.3123207243115331e-08	0.018186976140920567	0.244140625
516	model.visual.blocks.23.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	23	-0.0045881786694129305	0.4793571911685673	6.375
517	model.visual.blocks.23.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	23	-1.0563681768512486e-05	0.0164637041064667	0.1484375
518	model.visual.blocks.23.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	23	-1.1823353916406631	1.2596480183914525	3.390625
519	model.visual.blocks.23.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	23	0.0006163056673373288	0.014160105140531405	0.84765625
520	model.visual.blocks.23.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	23	-0.007630281150341034	0.7601651155732886	9.0
521	model.visual.blocks.23.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	23	2.5521093651711957e-05	0.014476899120657829	0.69921875
522	model.visual.blocks.23.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	23	0.01085265725851059	0.4646660501895986	7.125
523	model.visual.blocks.23.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	23	1.530099868774414	1.5427840122256975	3.28125
524	model.visual.blocks.23.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	23	-0.547552265226841	2.1320240363512677	9.1875
525	model.visual.blocks.23.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	23	7.73004150390625	7.794828769449906	16.625
526	model.visual.blocks.3.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	3	0.0055896323174238205	0.22725533239644694	4.21875
527	model.visual.blocks.3.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	3	-8.324880100274434e-06	0.014204998605310243	0.306640625
528	model.visual.blocks.3.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	3	-0.010611735711184641	0.6356958380251622	9.5
529	model.visual.blocks.3.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	3	3.0863008081573794e-05	0.018493728387148186	0.26171875
530	model.visual.blocks.3.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	3	-2.4899610206484795	2.8378251598762203	4.8125
531	model.visual.blocks.3.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	3	0.00012417413540886414	0.016658970395077077	0.37109375
532	model.visual.blocks.3.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	3	-0.0060559650883078575	0.2120297601458163	4.625
533	model.visual.blocks.3.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	3	1.6447852463617762e-05	0.016438568045283906	0.55078125
534	model.visual.blocks.3.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	3	0.0005567893385887146	0.21667533989354099	4.25
535	model.visual.blocks.3.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	3	0.7782039642333984	0.8228475783365038	1.671875
536	model.visual.blocks.3.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	3	0.007098435831721872	0.19464676342919898	3.40625
537	model.visual.blocks.3.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	3	0.9266856936737895	0.974532049879689	2.0625
538	model.visual.blocks.4.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	4	0.006985343061387539	0.16223469691833878	1.296875
539	model.visual.blocks.4.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	4	1.8378288352272065e-07	0.01442967947584689	0.298828125
540	model.visual.blocks.4.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	4	0.018887083482695743	0.5794811256502446	9.1875
541	model.visual.blocks.4.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	4	-7.655587233305894e-06	0.018059560768096988	0.2109375
542	model.visual.blocks.4.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	4	-2.366614764323458	2.6965073178001546	4.625
543	model.visual.blocks.4.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	4	0.00016276028306286966	0.016659989978346723	0.283203125
544	model.visual.blocks.4.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	4	-0.004570281831547618	0.14836421255117274	1.6796875
545	model.visual.blocks.4.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	4	1.3213413660478901e-05	0.01714581722997102	0.58203125
546	model.visual.blocks.4.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	4	0.0012555653520394117	0.20431990398495709	3.8125
547	model.visual.blocks.4.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	4	0.7098050117492676	0.7350691020181069	1.390625
548	model.visual.blocks.4.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	4	0.008271024329587817	0.1808966163691234	3.484375
549	model.visual.blocks.4.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	4	0.9531378536485136	0.986081198167738	2.234375
550	model.visual.blocks.5.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	5	0.005363904405385256	0.15417362578206295	1.453125
551	model.visual.blocks.5.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	5	1.138475018258589e-06	0.01455602676419094	0.2021484375
552	model.visual.blocks.5.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	5	-0.0042238371291508274	0.5847475682637407	9.0
553	model.visual.blocks.5.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	5	-5.719098949252821e-06	0.017454819217105327	0.2451171875
554	model.visual.blocks.5.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	5	-2.2070916444063187	2.5344800306111703	4.6875
555	model.visual.blocks.5.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	5	0.00016606873607712125	0.016482466770763107	0.1982421875
556	model.visual.blocks.5.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	5	-0.004116903990507126	0.14437497298756788	1.5390625
557	model.visual.blocks.5.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	5	-2.0686353935546464e-06	0.01632456835844649	0.455078125
558	model.visual.blocks.5.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	5	0.0018707644194364548	0.2150864657981796	4.1875
559	model.visual.blocks.5.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	5	0.7877235412597656	0.8056694065263549	1.7109375
560	model.visual.blocks.5.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	5	0.005293702706694603	0.21285220841568864	4.125
561	model.visual.blocks.5.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	5	0.9217546582221985	0.9412579347437405	2.3125
562	model.visual.blocks.6.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	6	-0.0002876807702705264	0.18460897803677073	1.8125
563	model.visual.blocks.6.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	6	-1.6337773984381743e-06	0.01408807292678129	0.1865234375
564	model.visual.blocks.6.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	6	0.0054503006394952536	0.5035026330586864	7.5625
565	model.visual.blocks.6.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	6	-2.637964617714187e-06	0.017114318284296055	0.185546875
566	model.visual.blocks.6.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	6	-2.073364906013012	2.3344424149697662	4.59375
567	model.visual.blocks.6.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	6	0.00012550517553477913	0.016654967329708652	0.259765625
568	model.visual.blocks.6.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	6	-0.0050590806640684605	0.16059811363634433	2.59375
569	model.visual.blocks.6.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	6	-8.25678072504353e-06	0.015881123862622196	0.59375
570	model.visual.blocks.6.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	6	-0.00010237316018901765	0.20565713205216193	4.15625
571	model.visual.blocks.6.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	6	0.9554309844970703	0.9669409615623171	1.75
572	model.visual.blocks.6.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	6	0.003839905373752117	0.23620944229480795	3.90625
573	model.visual.blocks.6.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	6	0.9070353507995605	0.9159196848385002	1.8203125
574	model.visual.blocks.7.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	7	-0.0023070083698257804	0.20943125114081082	2.859375
575	model.visual.blocks.7.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	7	8.261984775215225e-07	0.014035490681116675	0.119140625
576	model.visual.blocks.7.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	7	0.009815204190090299	0.49869548059937374	7.65625
577	model.visual.blocks.7.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	7	2.9990876174723624e-06	0.01649365033942753	0.251953125
578	model.visual.blocks.7.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	7	-1.6987448390573263	1.8391509676765594	3.9375
579	model.visual.blocks.7.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	7	0.00017219371261305294	0.016408897942078948	0.28125
580	model.visual.blocks.7.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	7	-0.008466638159006834	0.17516442409220903	1.9375
581	model.visual.blocks.7.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	7	2.340813741535941e-06	0.014372225294541803	0.255859375
582	model.visual.blocks.7.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	7	0.003123911563307047	0.1572316380772548	3.375
583	model.visual.blocks.7.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	7	0.9082684516906738	0.9232805356334663	1.7265625
584	model.visual.blocks.7.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	7	0.009727229364216328	0.24249418742314302	3.78125
585	model.visual.blocks.7.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	7	1.0042033195495605	1.019765058492056	1.5
586	model.visual.blocks.8.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	8	0.0016495957970619202	0.24097282912908569	3.96875
587	model.visual.blocks.8.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	8	-2.7905498484193103e-06	0.01345574124824084	0.283203125
588	model.visual.blocks.8.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	8	0.008241087314672768	0.47954093823312155	7.1875
589	model.visual.blocks.8.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	8	-1.5548966505463113e-05	0.01653429785702248	0.2275390625
590	model.visual.blocks.8.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	8	-1.6126111019402742	1.7683807290973117	3.9375
591	model.visual.blocks.8.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	8	0.0001252524039837416	0.01624719901557155	0.28515625
592	model.visual.blocks.8.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	8	-0.005296873860061169	0.2216358320198793	2.46875
593	model.visual.blocks.8.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	8	1.4216143319060667e-05	0.013571702866860212	0.2470703125
594	model.visual.blocks.8.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	8	0.0055080801248550415	0.20896838474609777	3.859375
595	model.visual.blocks.8.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	8	0.9037561416625977	0.9260690715493488	1.71875
596	model.visual.blocks.8.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	8	0.003971373429521918	0.310706905909723	3.921875
597	model.visual.blocks.8.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	8	1.0045695304870605	1.0178206173386362	1.5546875
598	model.visual.blocks.9.attn.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.attn.proj.bias	9	0.0010921573266386986	0.22680602547304463	3.265625
599	model.visual.blocks.9.attn.proj.weight	(1024, 1024)	2	BF16	1048576	2097152	model.visual.layers.*.attn.proj.weight	9	1.4016385481707694e-06	0.01288622156493415	0.1123046875
600	model.visual.blocks.9.attn.qkv.bias	(3072,)	1	BF16	3072	6144	model.visual.layers.*.attn.qkv.bias	9	0.001626015097523729	0.4891119861662029	7.25
601	model.visual.blocks.9.attn.qkv.weight	(3072, 1024)	2	BF16	3145728	6291456	model.visual.layers.*.attn.qkv.weight	9	-4.602129067709608e-06	0.016435399387831742	0.2119140625
602	model.visual.blocks.9.mlp.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.layers.*.mlp.linear_fc1.bias	9	-1.6456444784998894	1.7699452545615144	8.125
603	model.visual.blocks.9.mlp.linear_fc1.weight	(4096, 1024)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc1.weight	9	5.019114076590045e-05	0.015971322934801892	0.2734375
604	model.visual.blocks.9.mlp.linear_fc2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.mlp.linear_fc2.bias	9	-0.00503852404654026	0.2206179125090425	2.28125
605	model.visual.blocks.9.mlp.linear_fc2.weight	(1024, 4096)	2	BF16	4194304	8388608	model.visual.layers.*.mlp.linear_fc2.weight	9	2.0485118040584893e-05	0.013085999668089059	0.29296875
606	model.visual.blocks.9.norm1.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.bias	9	0.003136083483695984	0.18839499922526784	2.953125
607	model.visual.blocks.9.norm1.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm1.weight	9	0.9992551803588867	1.0213929426253632	1.8203125
608	model.visual.blocks.9.norm2.bias	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.bias	9	0.0005389824509620667	0.30238562581121287	2.90625
609	model.visual.blocks.9.norm2.weight	(1024,)	1	BF16	1024	2048	model.visual.layers.*.norm2.weight	9	1.1041545867919922	1.1208131568613	1.734375
610	model.visual.merger.linear_fc1.bias	(4096,)	1	BF16	4096	8192	model.visual.merger.linear_fc1.bias	-1	-0.0005523472136701457	0.01626457054117911	0.115234375
611	model.visual.merger.linear_fc1.weight	(4096, 4096)	2	BF16	16777216	33554432	model.visual.merger.linear_fc1.weight	-1	-0.00015279042523767844	0.011285763080892746	0.0947265625
612	model.visual.merger.linear_fc2.bias	(2048,)	1	BF16	2048	4096	model.visual.merger.linear_fc2.bias	-1	-0.00020432728342711926	0.022563638409818742	0.4921875
613	model.visual.merger.linear_fc2.weight	(2048, 4096)	2	BF16	8388608	16777216	model.visual.merger.linear_fc2.weight	-1	5.585822149016192e-07	0.009865405435281218	0.19921875
614	model.visual.merger.norm.bias	(1024,)	1	BF16	1024	2048	model.visual.merger.norm.bias	-1	0.049520475789904594	0.3246462954969724	3.453125
615	model.visual.merger.norm.weight	(1024,)	1	BF16	1024	2048	model.visual.merger.norm.weight	-1	1.4015541076660156	1.41604852572399	2.9375
616	model.visual.patch_embed.proj.bias	(1024,)	1	BF16	1024	2048	model.visual.patch_embed.proj.bias	-1	-0.009102825075387955	0.3202035696576827	3.1875
617	model.visual.patch_embed.proj.weight	(1024, 3, 2, 16, 16)	5	BF16	1572864	3145728	model.visual.patch_embed.proj.weight	-1	-0.0002164951033312712	0.007756875182799582	0.06884765625
618	model.visual.pos_embed.weight	(2304, 1024)	2	BF16	2359296	4718592	model.visual.pos_embed.weight	-1	0.003249331564613057	0.1360526766744249	7.21875
619	mtp.fc.weight	(2048, 4096)	2	BF16	8388608	16777216	mtp.fc.weight	-1	5.3096681990941023e-05	0.006383883815548282	0.3125
620	mtp.layers.0.input_layernorm.weight	(2048,)	1	BF16	2048	4096	mtp.layers.*.input_layernorm.weight	0	0.3319206237792969	0.3510988118095836	1.1328125
621	mtp.layers.0.mlp.down_proj.weight	(2048, 6144)	2	BF16	12582912	25165824	mtp.layers.*.mlp.down_proj.weight	0	-5.053560631807126e-06	0.010496220813270141	0.5
622	mtp.layers.0.mlp.gate_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	mtp.layers.*.mlp.gate_proj.weight	0	-2.054409559734451e-05	0.013481584415555293	0.23046875
623	mtp.layers.0.mlp.up_proj.weight	(6144, 2048)	2	BF16	12582912	25165824	mtp.layers.*.mlp.up_proj.weight	0	9.151307207333424e-07	0.01273030821065844	0.337890625
624	mtp.layers.0.post_attention_layernorm.weight	(2048,)	1	BF16	2048	4096	mtp.layers.*.post_attention_layernorm.weight	0	0.41015276312828064	0.42291990555998127	0.78125
625	mtp.layers.0.self_attn.k_norm.weight	(256,)	1	BF16	256	512	mtp.layers.*.self_attn.k_norm.weight	0	0.7713251113891602	0.8445900427746588	2.046875
626	mtp.layers.0.self_attn.k_proj.weight	(512, 2048)	2	BF16	1048576	2097152	mtp.layers.*.self_attn.k_proj.weight	0	1.4686407705633009e-05	0.011793984318089815	0.1669921875
627	mtp.layers.0.self_attn.o_proj.weight	(2048, 2048)	2	BF16	4194304	8388608	mtp.layers.*.self_attn.o_proj.weight	0	2.4605430018389413e-06	0.01508009745888187	0.5234375
628	mtp.layers.0.self_attn.q_norm.weight	(256,)	1	BF16	256	512	mtp.layers.*.self_attn.q_norm.weight	0	0.8072891235351562	0.8754819538932436	2.4375
629	mtp.layers.0.self_attn.q_proj.weight	(4096, 2048)	2	BF16	8388608	16777216	mtp.layers.*.self_attn.q_proj.weight	0	1.1836838601198777e-05	0.015479120981825292	0.3203125
630	mtp.layers.0.self_attn.v_proj.weight	(512, 2048)	2	BF16	1048576	2097152	mtp.layers.*.self_attn.v_proj.weight	0	3.6436836885478385e-06	0.026195977141207714	0.30859375
631	mtp.norm.weight	(2048,)	1	BF16	2048	4096	mtp.norm.weight	-1	2.8050971627235413	2.8500763286553985	6.3125
632	mtp.pre_fc_norm_embedding.weight	(2048,)	1	BF16	2048	4096	mtp.pre_fc_norm_embedding.weight	-1	-0.43043196201324463	0.4398642357123278	0.640625
633	mtp.pre_fc_norm_hidden.weight	(2048,)	1	BF16	2048	4096	mtp.pre_fc_norm_hidden.weight	-1	-0.28146980330348015	0.2999654479966	0.69921875