eftnas-s1-bert-base-squadv2/nncf_config.json

{
    "input_info": [
        {
            "sample_size": [ 1, 384 ],
            "type": "long",
            "keyword": "input_ids"
        },
        {
            "sample_size": [ 1, 384 ],
            "type": "long",
            "keyword": "token_type_ids"
        },
        {
            "sample_size": [ 1, 384 ],
            "type": "long",
            "keyword": "attention_mask"
        }
    ],
    "bootstrapNAS": {
        "training": {
            "algorithm": "progressive_shrinking",
            "progressivity_of_elasticity": [ "width", ],
            "batchnorm_adaptation": {
                "num_bn_adaptation_samples": 0
            },
            "schedule": {
                "list_stage_descriptions": [
                    {
                        "train_dims": [ "width" ],
                        "epochs":5,
                        "depth_indicator": 1,
                        "width_indicator": 5,
                        "init_lr": 3e-05,
                        "epochs_lr": 5,
                        "sample_rate": 1
                    }
                ]
            },
            "elasticity": {
                "available_elasticity_dims": [ "width", ],
                "width": {
                    "overwrite_groups": [
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0",
                            "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0"
                        ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ],
                        [ "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0" ]
                    ],
                    "overwrite_groups_widths": [
                        [ 768, 576 ], [ 768, 512, 448 ], [ 768, 576 ], [ 768, 576 ],
                        [ 768, 704, 640, 576 ], [ 768, 512, 448 ], [ 768, 576 ], [ 768, 512 ],
                        [ 768, 576 ], [ 768, 320 ], [ 768, 384 ], [ 768, 384 ],
                        [ 3072, 3058, 2684, 1908, 966 ], [ 3072, 3050, 2674, 1898, 1052 ], [ 3072, 3041, 2670, 1940, 1040 ], [ 3072, 3043, 2662, 1926, 1007 ],
                        [ 3072, 3037, 2580, 1807, 989 ], [ 3072, 3018, 2521, 1759, 938 ], [ 3072, 3006, 2363, 1554, 789 ], [ 3072, 3009, 2291, 1421, 693 ],
                        [ 3072, 2995, 2078, 1175, 517 ], [ 3072, 2913, 1500, 653, 280 ], [ 3072, 2844, 1287, 665, 332 ], [ 3072, 2472, 1138, 752, 505 ]
                    ],
                    "add_dynamic_inputs": [
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0",
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0",
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0",
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0",
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0",
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0",
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0",
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0",
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0",
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0",
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0",
                        "BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0"
                    ]
                },
            }
        },
        "search": {
            "algorithm": "NSGA2",
            "batchnorm_adaptation": {
                "num_bn_adaptation_samples": 0
            },
            "num_evals": 1000,
            "population": 40,
            "ref_acc": 77.9
        }
    },
    "compression": [
        {
            "algorithm": "movement_sparsity",
            "params": {
                "warmup_start_epoch": 1,
                "warmup_end_epoch": 4,
                "importance_regularization_factor": 0.02,
                "enable_structured_masking": true
            },
            "sparse_structure_by_scopes": [
                {
                    "mode": "block",
                    "sparse_factors": [ 32, 32 ],
                    "target_scopes": "{re}.*BertAttention.*"
                },
                {
                    "mode": "per_dim",
                    "axis": 0,
                    "target_scopes": "{re}.*BertIntermediate.*"
                },
                {
                    "mode": "per_dim",
                    "axis": 1,
                    "target_scopes": "{re}.*BertOutput.*"
                }
            ],
            "ignored_scopes": [
                "{re}.*NNCFEmbedding.*",
                "{re}.*qa_outputs.*",
                "{re}.*LayerNorm.*"
            ]
        }
    ]
}