{ "architectures": [ "NewBertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "decompose_qk": false, "decompose_vo": false, "do_distill": true, "do_emb_distill": false, "do_layer_distill": true, "do_mha_distill": false, "do_mha_layer_distill": false, "finetuning_task": "mnli", "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "output_attentions": true, "output_hidden_states": true, "pad_token_id": 0, "pruned_heads": { "0": [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 11 ], "1": [ 0, 2, 3, 5, 6, 7, 8, 9 ], "2": [ 0, 1, 2, 3, 4, 5, 7, 8, 10, 11 ], "3": [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 ], "4": [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 ], "5": [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 ], "6": [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 ], "7": [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 ], "8": [ 0, 1, 2, 3, 4, 6, 7, 8, 10, 11 ], "9": [ 0, 1, 2, 3, 4, 5, 6, 7, 9 ], "10": [ 0, 1, 2, 4, 5, 6, 7, 8, 9, 10 ], "11": [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 ] }, "qk_denominator": "ori", "sephidden_pruned": false, "total_flos": 176256166470389760, "transform_embedding": false, "type_vocab_size": 2, "vocab_size": 30522 }