[ { "layer_name": "lm_head", "sensitivities": { "4": 0.0, "8": 0.00546584720723331 }, "param_count": 311164928, "metadata": {} }, { "layer_name": "model.layers.47.mlp.shared_expert_gate", "sensitivities": { "4": 0.0001811789904119602, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.47.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.00087689898039874 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.47.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.0015896713763747055 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.47.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.00044233594720329467 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.47.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0003866669740091311 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.47.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.000519902074302081 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.47.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.00046726479376957286 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.47.mlp.gate", "sensitivities": { "4": 0.0015319683431395485, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.47.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.0009970010384373988 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.47.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.0006898588944750372 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.47.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.000378026442679887 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.47.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.0009673482066621849 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.46.mlp.shared_expert_gate", "sensitivities": { "4": 0.00043826462933793664, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.46.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0005482422323742261 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.46.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.000585554851568304 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.46.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0005205812140047783 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.46.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0005259119376811819 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.46.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0005636888490698766 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.46.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0005691807382390834 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.46.mlp.gate", "sensitivities": { "4": 0.0016299924997535224, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.46.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.0013121363129660797 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.46.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.0004549955301627051 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.46.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.001232918316721528 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.45.mlp.shared_expert_gate", "sensitivities": { "4": 0.0004910269999527372, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.45.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0006056272814021213 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.45.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.000662573301572896 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.45.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0005977782335927865 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.45.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0007479680231578337 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.45.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0007716155766199032 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.45.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0007242341719878217 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.45.mlp.gate", "sensitivities": { "4": 0.002146355339694613, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.45.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.0011942335452962045 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.45.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.0005906730202696053 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.45.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.0012439823755509376 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.44.mlp.shared_expert_gate", "sensitivities": { "4": 0.0007133473106174885, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.44.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0007204592196406642 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.44.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.0008755783965170849 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.44.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0006210746008340114 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.44.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.000983773055243849 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.44.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0010371999160270207 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.44.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0009049700092873536 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.44.mlp.gate", "sensitivities": { "4": 0.0024624387491106368, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.44.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.0015454338014630291 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.44.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.0007653660904907156 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.44.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.0014417152075717847 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.43.mlp.shared_expert_gate", "sensitivities": { "4": 0.0007744313740355816, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.43.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0009393947063169131 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.43.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.0010768429419840686 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.43.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0008377297441863144 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.43.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0010964083982495747 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.43.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0010202171264002875 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.43.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0011413340374322918 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.43.mlp.gate", "sensitivities": { "4": 0.0033793977951669754, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.43.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.002702764031710103 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.43.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.0017084380015148781 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.43.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.0011191138861856114 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.43.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.0014598523788057112 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.42.mlp.shared_expert_gate", "sensitivities": { "4": 0.0009925571054433628, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.42.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0011605675669367581 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.42.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.0018117218254095253 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.42.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.001172308443832056 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.42.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0015623406288796104 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.42.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.00130574569387439 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.42.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0013518400919565465 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.42.mlp.gate", "sensitivities": { "4": 0.0029391975913313217, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.42.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.0017956645048495072 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.42.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.0011235147382346138 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.42.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.002219276189862285 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.41.mlp.shared_expert_gate", "sensitivities": { "4": 0.0011014955040688317, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.41.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.001253751875386418 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.41.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.0012832630854973104 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.41.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0012258604571494895 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.41.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0015417903002041082 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.41.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0016429382061081317 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.41.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0015326397333410569 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.41.mlp.gate", "sensitivities": { "4": 0.0030040774484708286, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.41.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.0017300844774581492 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.41.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.0013138200107884284 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.41.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.0019365232534861814 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.40.mlp.shared_expert_gate", "sensitivities": { "4": 0.0012782128954616685, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.40.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0014563855996433024 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.40.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.0014926813782949466 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.40.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0013535707779131674 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.40.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0017617459622366975 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.40.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0016695782178430818 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.40.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0016951369301144343 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.40.mlp.gate", "sensitivities": { "4": 0.0033831604887382127, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.40.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.002003027924123065 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.40.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.0014643894125280592 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.40.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.002364053131411007 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.39.mlp.shared_expert_gate", "sensitivities": { "4": 0.001446501639293274, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.39.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.001575188147398876 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.39.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.001775789626359862 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.39.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0015565581913203157 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.39.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0019679781325976364 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.39.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.001903772181928313 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.39.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.001958755795688679 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.39.mlp.gate", "sensitivities": { "4": 0.0034947048746592677, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.39.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.0022330831889121328 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.39.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.0020966503264692924 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.39.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.0017853173170199927 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.39.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.002157975022176591 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.38.mlp.shared_expert_gate", "sensitivities": { "4": 0.0016617042371459927, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.38.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.001788420772451597 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.38.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.0018763207917800173 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.38.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0018028927515842952 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.38.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.00211460222756917 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.38.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0020056302140195235 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.38.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.002035529483691789 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.38.mlp.gate", "sensitivities": { "4": 0.003621493626269512, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.38.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.0020221223191280537 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.38.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.0017770422612860177 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.38.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.0024485136527800933 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.37.mlp.shared_expert_gate", "sensitivities": { "4": 0.0017955446419364307, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.37.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.00191835029302941 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.37.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.002024596572785716 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.37.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0018729715350976524 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.37.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0022996737267628 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.37.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0021713513148521693 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.37.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0021041337956072916 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.37.mlp.gate", "sensitivities": { "4": 0.004091399455016169, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.37.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.002346425324503798 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.37.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.0018104871329948462 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.37.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.002669086587654116 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.36.mlp.shared_expert_gate", "sensitivities": { "4": 0.0018940380444594969, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.36.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.002158472236866752 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.36.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.002250783230313876 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.36.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.002060351244532891 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.36.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.002607721893582493 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.36.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0025067820267092125 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.36.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0025180679634407475 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.36.mlp.gate", "sensitivities": { "4": 0.0041634838610965135, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.36.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.002644306846680896 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.36.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.002127183021608895 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.36.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.003041435554526591 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.35.mlp.shared_expert_gate", "sensitivities": { "4": 0.0021315743118369332, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.35.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0023513569540227763 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.35.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.00261818288709037 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.35.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0022630117625036896 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.35.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0029103495204860033 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.35.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0026857099728658795 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.35.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0027523967655724846 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.35.mlp.gate", "sensitivities": { "4": 0.004539914623213311, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.35.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.003231826927124833 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.35.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.0032008243239639946 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.35.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.0025570961685540774 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.35.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.002896230924913349 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.34.mlp.shared_expert_gate", "sensitivities": { "4": 0.002297268777814073, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.34.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0026993594292434864 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.34.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.0027452579136782638 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.34.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0024244497229422755 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.34.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0029562374596328786 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.34.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.00277543455013074 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.34.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.00286523503503607 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.34.mlp.gate", "sensitivities": { "4": 0.00521997369651217, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.34.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.003193213837221265 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.34.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.002630184574324327 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.34.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.0036525255200103857 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.33.mlp.shared_expert_gate", "sensitivities": { "4": 0.002746699678633983, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.33.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0027895902336846725 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.33.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.0029053816663993834 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.33.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.002501191748403168 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.33.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0031272211781470105 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.33.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0031219236722487644 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.33.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0032260748290961296 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.33.mlp.gate", "sensitivities": { "4": 0.005147328270444025, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.33.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.0033409177121939138 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.33.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.002774385551068311 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.33.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.0038971262256382033 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.32.mlp.shared_expert_gate", "sensitivities": { "4": 0.0028969740136138475, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.32.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0031035247181231775 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.32.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.002979815437962922 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.32.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.002915382935801366 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.32.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.003368606465907457 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.32.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0036279306029124805 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.32.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.00359268567020384 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.32.mlp.gate", "sensitivities": { "4": 0.0054580638752668165, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.32.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.0036926528555341065 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.32.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.0031067129117824757 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.32.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.004197506471731079 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.31.mlp.shared_expert_gate", "sensitivities": { "4": 0.0030901972932042554, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.31.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0033126247726613656 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.31.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.00331102798130208 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.31.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0028822653912357055 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.31.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.003875695178673292 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.31.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0038103191618574783 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.31.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0038147873856360093 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.31.mlp.gate", "sensitivities": { "4": 0.00543140152876731, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.31.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.003964414742464821 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.31.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.004204695069347508 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.31.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.0034591444976589023 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.31.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.004151555299661898 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.30.mlp.shared_expert_gate", "sensitivities": { "4": 0.003191108728060499, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.30.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.003548390481834455 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.30.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.0036089261120650917 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.30.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0034522233545430936 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.30.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.003841529044924149 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.30.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.003770305927901063 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.30.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0038622769401020682 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.30.mlp.gate", "sensitivities": { "4": 0.005873478900563593, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.30.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.004227041160144533 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.30.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.003324077117819494 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.30.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.004752254715034117 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.29.mlp.shared_expert_gate", "sensitivities": { "4": 0.0035896663054397018, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.29.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0035883158537520408 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.29.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.003742401638495115 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.29.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0034946068941887156 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.29.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.004219321068376303 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.29.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.004259144703003888 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.29.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.004165746400152178 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.29.mlp.gate", "sensitivities": { "4": 0.006541496540497367, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.29.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.0044880598967817304 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.29.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.0036810627813489796 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.29.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.004826595235499553 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.28.mlp.shared_expert_gate", "sensitivities": { "4": 0.00362065994219544, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.28.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.003921926690964028 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.28.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.0039680428671999834 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.28.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0036683329550821022 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.28.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0043618389148226315 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.28.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.004315103074380507 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.28.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.004349304557157059 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.28.mlp.gate", "sensitivities": { "4": 0.006787006728700362, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.28.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.004702370313073819 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.28.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.0037491704545876323 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.28.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.0051801369748621555 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.27.mlp.shared_expert_gate", "sensitivities": { "4": 0.003750991881436979, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.27.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.004106528702929306 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.27.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.004144503269344568 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.27.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.004088555853134797 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.27.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.004885390294172491 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.27.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.00455872366001131 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.27.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0049130060215247795 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.27.mlp.gate", "sensitivities": { "4": 0.007291974553178686, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.27.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.00555882364763723 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.27.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.005674804478379277 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.27.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.004737999302354486 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.27.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.005359278341832881 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.26.mlp.shared_expert_gate", "sensitivities": { "4": 0.004103830414048086, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.26.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.004563357242053219 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.26.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.004600786213510825 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.26.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.004448893041020104 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.26.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.00518409363576211 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.26.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.004802735384146217 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.26.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.005048779246862978 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.26.mlp.gate", "sensitivities": { "4": 0.008079974698678901, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.26.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.00514275149422853 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.26.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.004920122419813803 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.26.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.005918499732312436 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.25.mlp.shared_expert_gate", "sensitivities": { "4": 0.004627415449552548, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.25.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.004856845213604781 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.25.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.004881828169648846 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.25.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.004638931318671287 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.25.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.005686172774100366 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.25.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0053267386635222165 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.25.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.005722651037406952 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.25.mlp.gate", "sensitivities": { "4": 0.009340248730344078, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.25.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.006284646408554788 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.25.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.005060244996760351 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.25.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.006544227498428275 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.24.mlp.shared_expert_gate", "sensitivities": { "4": 0.005057090580521617, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.24.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.005316806911044599 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.24.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.005873421080953752 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.24.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.005097836023196578 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.24.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.006277923326706514 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.24.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.005662061237671878 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.24.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.005897963734848115 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.24.mlp.gate", "sensitivities": { "4": 0.009583479351325272, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.24.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.006754006913979538 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.24.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.005299228282334904 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.24.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.007472097684512846 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.23.mlp.shared_expert_gate", "sensitivities": { "4": 0.005364448579105859, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.23.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.005531614619637064 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.23.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.005941575296067943 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.23.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.005747957458273352 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.23.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.006524281270685606 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.23.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.006318350400154789 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.23.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.006365798185773504 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.23.mlp.gate", "sensitivities": { "4": 0.010608130556647666, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.23.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.008208236598875374 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.23.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.00739130225944488 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.23.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.006829266402443561 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.23.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.007633909597643651 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.22.mlp.shared_expert_gate", "sensitivities": { "4": 0.00617599854740547, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.22.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.006110824887097503 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.22.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.006009446524937327 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.22.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.006198184875150521 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.22.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0070419801292397706 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.22.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.0064737989838855965 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.22.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.006815817270156306 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.22.mlp.gate", "sensitivities": { "4": 0.010461516358191147, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.22.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.007974229263102947 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.22.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.006750545023047986 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.22.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.009198193957369464 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.21.mlp.shared_expert_gate", "sensitivities": { "4": 0.006172639778621185, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.21.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.006532026910766338 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.21.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.00721957237207486 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.21.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.006716253750103836 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.21.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.007162697574434181 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.21.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.006981045803210388 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.21.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.007448724689311348 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.21.mlp.gate", "sensitivities": { "4": 0.011110041804689294, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.21.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.008667696058788957 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.21.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.006610841888080661 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.21.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.00952446710531755 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.20.mlp.shared_expert_gate", "sensitivities": { "4": 0.0069478996738325804, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.20.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0074366811362172784 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.20.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.006943494290074644 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.20.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.0067551254711967585 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.20.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.008092523431211399 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.20.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.007611915270293442 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.20.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.008078320082859136 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.20.mlp.gate", "sensitivities": { "4": 0.011131369343881184, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.20.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.00876020211338376 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.20.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.007388061237482664 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.20.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.0099560285161715 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.19.mlp.shared_expert_gate", "sensitivities": { "4": 0.007256736600538716, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.19.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.0075626892648870125 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.19.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.007552810381942739 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.19.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.00718522864432695 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.19.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.008595826366217807 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.19.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.00823559146859528 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.19.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.008514910165104084 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.19.mlp.gate", "sensitivities": { "4": 0.011962555969754854, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.19.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.009170711811748333 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.19.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.00948034289952678 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.19.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.00827406374446582 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.19.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.009781325609462025 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.18.mlp.shared_expert_gate", "sensitivities": { "4": 0.007757856593040439, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.18.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.008020264431252144 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.18.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.007868040115378486 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.18.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.008096922431529189 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.18.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.008891638106433675 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.18.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.008893419241455073 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.18.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.008583348394798426 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.18.mlp.gate", "sensitivities": { "4": 0.012067314916445563, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.18.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.009313053917139769 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.18.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.00792201085035534 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.18.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.010337958544065865 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.17.mlp.shared_expert_gate", "sensitivities": { "4": 0.00800801339210011, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.17.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.008354605146450922 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.17.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.008346605425079664 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.17.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.00789218878101868 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.17.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0096804217416017 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.17.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.009081653120423047 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.17.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.00961258050908024 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.17.mlp.gate", "sensitivities": { "4": 0.012435313129875189, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.17.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.00969749286499185 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.17.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.008220665801976187 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.17.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.01077947385783773 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.16.mlp.shared_expert_gate", "sensitivities": { "4": 0.00898167995425562, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.16.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.008234198758145794 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.16.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.00856234620732721 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.16.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.008658537199759545 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.16.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.009765561121942786 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.16.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.00955390140976912 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.16.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.00922697524462516 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.16.mlp.gate", "sensitivities": { "4": 0.011782195152287992, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.16.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.010321959528179528 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.16.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.008864662149183763 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.16.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.010752089612651616 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.15.mlp.shared_expert_gate", "sensitivities": { "4": 0.009154927955629924, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.15.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.009189329032475749 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.15.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.009195887905661948 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.15.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.009162585886466937 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.15.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.010390287488310909 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.15.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.009711528284242377 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.15.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.010309005903157717 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.15.mlp.gate", "sensitivities": { "4": 0.013503166526788846, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.15.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.011138641464640386 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.15.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.011259745757949228 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.15.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.009398004641601196 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.15.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.0112590963835828 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.14.mlp.shared_expert_gate", "sensitivities": { "4": 0.009654443934171772, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.14.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.009863078341974566 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.14.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.00967700000910554 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.14.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.009742690696536252 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.14.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.010233040569194904 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.14.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.01022266013508973 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.14.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.010732679739400433 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.14.mlp.gate", "sensitivities": { "4": 0.01367227423179429, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.14.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.01100488739515034 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.14.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.01022967364891277 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.14.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.01245528188883327 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.13.mlp.shared_expert_gate", "sensitivities": { "4": 0.010582786043717837, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.13.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.010168050968786702 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.13.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.01001773014528832 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.13.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.009968309891216146 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.13.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.011261625166904802 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.13.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.010767707319852585 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.13.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.010916094227771586 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.13.mlp.gate", "sensitivities": { "4": 0.01399673714574116, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.13.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.011629761046303125 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.13.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.010364441375713795 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.13.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.012238817202160135 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.12.mlp.shared_expert_gate", "sensitivities": { "4": 0.010277952591422945, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.12.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.010277141176629812 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.12.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.010602660113363527 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.12.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.010807378469811132 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.12.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.012377719894478409 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.12.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.011131742144546783 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.12.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.010933864900531868 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.12.mlp.gate", "sensitivities": { "4": 0.014976006457194066, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.12.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.011991277909449613 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.12.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.010463360308979949 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.12.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.013422283062633747 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.11.mlp.shared_expert_gate", "sensitivities": { "4": 0.010844901742530055, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.11.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.011393746521207504 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.11.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.011229697129844377 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.11.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.010468666019733064 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.11.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.012109854117928384 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.11.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.011566853941379426 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.11.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.011979735451556431 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.11.mlp.gate", "sensitivities": { "4": 0.014990527405946827, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.11.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.01275160105433315 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.11.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.015201601044585308 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.11.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.012038252505590208 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.11.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.013188726123189554 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.10.mlp.shared_expert_gate", "sensitivities": { "4": 0.011288866294004643, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.10.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.011611835070652887 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.10.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.012178075737513913 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.10.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.011832942793262191 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.10.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.012095854433331018 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.10.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.01274094315400968 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.10.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.012829635612433776 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.10.mlp.gate", "sensitivities": { "4": 0.01626087084878236, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.10.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.013361044965373972 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.10.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.012351946274672324 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.10.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.015012034185929224 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.9.mlp.shared_expert_gate", "sensitivities": { "4": 0.011678688800505673, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.9.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.012375947214119757 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.9.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.012288592877060486 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.9.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.01256927099893801 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.9.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.01338555481925141 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.9.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.012540935538709164 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.9.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.012916975412129736 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.9.mlp.gate", "sensitivities": { "4": 0.01662118696064378, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.9.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.014035383860270182 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.9.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.012819181167287752 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.9.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.015574557250753665 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.8.mlp.shared_expert_gate", "sensitivities": { "4": 0.012599239038536325, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.8.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.013240655724075623 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.8.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.012855073883353422 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.8.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.013038330798735842 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.8.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.013493624350909764 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.8.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.013379455165704712 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.8.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.013178177721177539 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.8.mlp.gate", "sensitivities": { "4": 0.01652742245156939, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.8.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.014525910800633332 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.8.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.014052762446226552 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.8.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.01691254019776049 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.7.mlp.shared_expert_gate", "sensitivities": { "4": 0.01293456334193858, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.7.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.013468108120529601 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.7.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.013862467652264362 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.7.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.013406028689738983 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.7.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.013866370340110734 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.7.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.014211450363897407 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.7.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.013236384809715673 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.7.mlp.gate", "sensitivities": { "4": 0.01609512370972273, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.7.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.015192151438289633 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.7.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.01611088200782736 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.7.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.014883832996323084 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.7.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.014775762363569811 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.6.mlp.shared_expert_gate", "sensitivities": { "4": 0.013842910673702136, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.6.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.01374226551464138 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.6.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.015329888090491295 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.6.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.013457816676236689 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.6.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.014617457006049031 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.6.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.014744472709329179 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.6.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.013872471987269819 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.6.mlp.gate", "sensitivities": { "4": 0.016978700946007546, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.6.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.015879868374516565 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.6.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.014073359741208455 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.6.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.016584908017345395 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.5.mlp.shared_expert_gate", "sensitivities": { "4": 0.013318267408370351, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.5.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.013795014693945026 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.5.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.014510109923624745 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.5.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.014729883502392719 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.5.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.014678579987958074 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.5.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.014759288256755099 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.5.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.014945248481429493 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.5.mlp.gate", "sensitivities": { "4": 0.01711107642040588, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.5.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.014898032823111862 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.5.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.014382564753759652 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.5.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.017053854671151687 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.4.mlp.shared_expert_gate", "sensitivities": { "4": 0.014288380965202426, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.4.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.014899879752192646 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.4.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.015110610518604517 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.4.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.01435574131513325 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.4.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.016535441546390455 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.4.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.015712454575502004 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.4.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.01456842960518164 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.4.mlp.gate", "sensitivities": { "4": 0.018017263452444848, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.4.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.015937547102415312 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.4.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.015152021961209053 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.4.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.01661324539842705 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.3.mlp.shared_expert_gate", "sensitivities": { "4": 0.01538781247412165, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.3.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.015848533192183822 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.3.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.015900589545102168 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.3.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.014709234674228355 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.3.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.0161793943552766 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.3.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.015927003318211064 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.3.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.016266208646508556 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.3.mlp.gate", "sensitivities": { "4": 0.018574310747984175, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.3.self_attn.o_proj", "sensitivities": { "4": 0.0, "8": 0.017166202393127605 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.3.self_attn.v_proj", "sensitivities": { "4": 0.0, "8": 0.02210300312920784 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.3.self_attn.k_proj", "sensitivities": { "4": 0.0, "8": 0.01649043273452359 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.3.self_attn.q_proj", "sensitivities": { "4": 0.0, "8": 0.017937579153416056 }, "param_count": 16777216, "metadata": {} }, { "layer_name": "model.layers.2.mlp.shared_expert_gate", "sensitivities": { "4": 0.015848530747462064, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.2.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.017437926658506814 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.2.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.016578349061698344 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.2.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.016357797489035875 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.2.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.01727279481322815 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.2.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.016195804220236216 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.2.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.01615279316320084 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.2.mlp.gate", "sensitivities": { "4": 0.01900803267684144, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.2.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.017819210469800357 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.2.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.017294775665504858 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.2.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.020012144804544125 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.1.mlp.shared_expert_gate", "sensitivities": { "4": 0.016524562825604033, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.1.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.016842761435934033 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.1.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.016998056855906423 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.1.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.01661954979257037 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.1.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.017476482074319694 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.1.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.01659977853220577 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.1.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.016613098239758983 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.1.mlp.gate", "sensitivities": { "4": 0.01898803311632946, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.1.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.01730258480529301 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.1.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.018019680787498753 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.1.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.01960670785047114 }, "param_count": 25165824, "metadata": {} }, { "layer_name": "model.layers.0.mlp.shared_expert_gate", "sensitivities": { "4": 0.016866121945592265, "8": 0.0 }, "param_count": 2048, "metadata": {} }, { "layer_name": "model.layers.0.mlp.shared_expert.up_proj", "sensitivities": { "4": 0.0, "8": 0.018234637934559334 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.0.mlp.shared_expert.down_proj", "sensitivities": { "4": 0.0, "8": 0.017515672865556553 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.0.mlp.shared_expert.gate_proj", "sensitivities": { "4": 0.0, "8": 0.016906839252139132 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.0.mlp.switch_mlp.down_proj", "sensitivities": { "4": 0.0, "8": 0.018159386556362733 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.0.mlp.switch_mlp.up_proj", "sensitivities": { "4": 0.0, "8": 0.016372410124555852 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.0.mlp.switch_mlp.gate_proj", "sensitivities": { "4": 0.0, "8": 0.01711415994213894 }, "param_count": 536870912, "metadata": {} }, { "layer_name": "model.layers.0.mlp.gate", "sensitivities": { "4": 0.01868543986347504, "8": 0.0 }, "param_count": 1048576, "metadata": {} }, { "layer_name": "model.layers.0.linear_attn.out_proj", "sensitivities": { "4": 0.0, "8": 0.019266100542154163 }, "param_count": 8388608, "metadata": {} }, { "layer_name": "model.layers.0.linear_attn.in_proj_ba", "sensitivities": { "4": 0.0, "8": 0.017209987262807164 }, "param_count": 131072, "metadata": {} }, { "layer_name": "model.layers.0.linear_attn.in_proj_qkvz", "sensitivities": { "4": 0.0, "8": 0.01821280693790565 }, "param_count": 25165824, "metadata": {} } ]