,layer_id,layer_type,param_type,shape,nparam,nnz,sparsity 5,bert.encoder.layer.0.attention.self.query,Linear,weight,"[320, 768]",245760,135168,0.44999998807907104 7,bert.encoder.layer.0.attention.self.key,Linear,weight,"[320, 768]",245760,149504,0.3916666507720947 9,bert.encoder.layer.0.attention.self.value,Linear,weight,"[320, 768]",245760,173056,0.2958332896232605 11,bert.encoder.layer.0.attention.output.dense,Linear,weight,"[768, 320]",245760,181248,0.26249998807907104 15,bert.encoder.layer.0.intermediate.dense,Linear,weight,"[185, 768]",142080,142080,0.0 17,bert.encoder.layer.0.output.dense,Linear,weight,"[768, 185]",142080,142080,0.0 21,bert.encoder.layer.1.attention.self.query,Linear,weight,"[320, 768]",245760,175104,0.28749996423721313 23,bert.encoder.layer.1.attention.self.key,Linear,weight,"[320, 768]",245760,177152,0.27916663885116577 25,bert.encoder.layer.1.attention.self.value,Linear,weight,"[320, 768]",245760,166912,0.32083332538604736 27,bert.encoder.layer.1.attention.output.dense,Linear,weight,"[768, 320]",245760,167936,0.3166666030883789 31,bert.encoder.layer.1.intermediate.dense,Linear,weight,"[315, 768]",241920,241920,0.0 33,bert.encoder.layer.1.output.dense,Linear,weight,"[768, 315]",241920,241920,0.0 37,bert.encoder.layer.2.attention.self.query,Linear,weight,"[576, 768]",442368,285696,0.3541666865348816 39,bert.encoder.layer.2.attention.self.key,Linear,weight,"[576, 768]",442368,297984,0.3263888955116272 41,bert.encoder.layer.2.attention.self.value,Linear,weight,"[576, 768]",442368,226304,0.4884259104728699 43,bert.encoder.layer.2.attention.output.dense,Linear,weight,"[768, 576]",442368,237568,0.4629629850387573 47,bert.encoder.layer.2.intermediate.dense,Linear,weight,"[339, 768]",260352,260352,0.0 49,bert.encoder.layer.2.output.dense,Linear,weight,"[768, 339]",260352,260352,0.0 53,bert.encoder.layer.3.attention.self.query,Linear,weight,"[576, 768]",442368,277504,0.37268519401550293 55,bert.encoder.layer.3.attention.self.key,Linear,weight,"[576, 768]",442368,303104,0.31481480598449707 57,bert.encoder.layer.3.attention.self.value,Linear,weight,"[576, 768]",442368,297984,0.3263888955116272 59,bert.encoder.layer.3.attention.output.dense,Linear,weight,"[768, 576]",442368,308224,0.30324071645736694 63,bert.encoder.layer.3.intermediate.dense,Linear,weight,"[368, 768]",282624,282624,0.0 65,bert.encoder.layer.3.output.dense,Linear,weight,"[768, 368]",282624,282624,0.0 69,bert.encoder.layer.4.attention.self.query,Linear,weight,"[576, 768]",442368,291840,0.3402777910232544 71,bert.encoder.layer.4.attention.self.key,Linear,weight,"[576, 768]",442368,310272,0.2986111044883728 73,bert.encoder.layer.4.attention.self.value,Linear,weight,"[576, 768]",442368,272384,0.38425928354263306 75,bert.encoder.layer.4.attention.output.dense,Linear,weight,"[768, 576]",442368,263168,0.40509259700775146 79,bert.encoder.layer.4.intermediate.dense,Linear,weight,"[386, 768]",296448,296448,0.0 81,bert.encoder.layer.4.output.dense,Linear,weight,"[768, 386]",296448,296448,0.0 85,bert.encoder.layer.5.attention.self.query,Linear,weight,"[384, 768]",294912,171008,0.4201388955116272 87,bert.encoder.layer.5.attention.self.key,Linear,weight,"[384, 768]",294912,205824,0.3020833134651184 89,bert.encoder.layer.5.attention.self.value,Linear,weight,"[384, 768]",294912,217088,0.2638888955116272 91,bert.encoder.layer.5.attention.output.dense,Linear,weight,"[768, 384]",294912,223232,0.243055522441864 95,bert.encoder.layer.5.intermediate.dense,Linear,weight,"[336, 768]",258048,258048,0.0 97,bert.encoder.layer.5.output.dense,Linear,weight,"[768, 336]",258048,258048,0.0 101,bert.encoder.layer.6.attention.self.query,Linear,weight,"[448, 768]",344064,192512,0.4404761791229248 103,bert.encoder.layer.6.attention.self.key,Linear,weight,"[448, 768]",344064,224256,0.3482142686843872 105,bert.encoder.layer.6.attention.self.value,Linear,weight,"[448, 768]",344064,209920,0.3898809552192688 107,bert.encoder.layer.6.attention.output.dense,Linear,weight,"[768, 448]",344064,199680,0.4196428656578064 111,bert.encoder.layer.6.intermediate.dense,Linear,weight,"[280, 768]",215040,215040,0.0 113,bert.encoder.layer.6.output.dense,Linear,weight,"[768, 280]",215040,215040,0.0 117,bert.encoder.layer.7.attention.self.query,Linear,weight,"[448, 768]",344064,201728,0.413690447807312 119,bert.encoder.layer.7.attention.self.key,Linear,weight,"[448, 768]",344064,237568,0.3095238208770752 121,bert.encoder.layer.7.attention.self.value,Linear,weight,"[448, 768]",344064,218112,0.3660714030265808 123,bert.encoder.layer.7.attention.output.dense,Linear,weight,"[768, 448]",344064,202752,0.4107142686843872 127,bert.encoder.layer.7.intermediate.dense,Linear,weight,"[211, 768]",162048,162048,0.0 129,bert.encoder.layer.7.output.dense,Linear,weight,"[768, 211]",162048,162048,0.0 133,bert.encoder.layer.8.attention.self.query,Linear,weight,"[448, 768]",344064,186368,0.4583333134651184 135,bert.encoder.layer.8.attention.self.key,Linear,weight,"[448, 768]",344064,197632,0.425595223903656 137,bert.encoder.layer.8.attention.self.value,Linear,weight,"[448, 768]",344064,154624,0.550595223903656 139,bert.encoder.layer.8.attention.output.dense,Linear,weight,"[768, 448]",344064,148480,0.5684523582458496 143,bert.encoder.layer.8.intermediate.dense,Linear,weight,"[108, 768]",82944,82944,0.0 145,bert.encoder.layer.8.output.dense,Linear,weight,"[768, 108]",82944,82944,0.0 149,bert.encoder.layer.9.attention.self.query,Linear,weight,"[320, 768]",245760,144384,0.41249996423721313 151,bert.encoder.layer.9.attention.self.key,Linear,weight,"[320, 768]",245760,155648,0.36666661500930786 153,bert.encoder.layer.9.attention.self.value,Linear,weight,"[320, 768]",245760,63488,0.7416666746139526 155,bert.encoder.layer.9.attention.output.dense,Linear,weight,"[768, 320]",245760,65536,0.7333333492279053 159,bert.encoder.layer.9.intermediate.dense,Linear,weight,"[53, 768]",40704,40704,5.960464477539063e-08 161,bert.encoder.layer.9.output.dense,Linear,weight,"[768, 53]",40704,40704,5.960464477539063e-08 165,bert.encoder.layer.10.attention.self.query,Linear,weight,"[384, 768]",294912,158720,0.461805522441864 167,bert.encoder.layer.10.attention.self.key,Linear,weight,"[384, 768]",294912,158720,0.461805522441864 169,bert.encoder.layer.10.attention.self.value,Linear,weight,"[384, 768]",294912,77824,0.7361111044883728 171,bert.encoder.layer.10.attention.output.dense,Linear,weight,"[768, 384]",294912,78848,0.7326388955116272 175,bert.encoder.layer.10.intermediate.dense,Linear,weight,"[86, 768]",66048,66048,0.0 177,bert.encoder.layer.10.output.dense,Linear,weight,"[768, 86]",66048,66048,0.0 181,bert.encoder.layer.11.attention.self.query,Linear,weight,"[384, 768]",294912,107520,0.6354166269302368 183,bert.encoder.layer.11.attention.self.key,Linear,weight,"[384, 768]",294912,118784,0.5972222089767456 185,bert.encoder.layer.11.attention.self.value,Linear,weight,"[384, 768]",294912,62464,0.7881944179534912 187,bert.encoder.layer.11.attention.output.dense,Linear,weight,"[768, 384]",294912,54272,0.8159722089767456 191,bert.encoder.layer.11.intermediate.dense,Linear,weight,"[105, 768]",80640,80640,0.0 193,bert.encoder.layer.11.output.dense,Linear,weight,"[768, 105]",80640,80640,0.0