enoriega/rule_learning_margin_1mm_spanpred

1{2  "_name_or_path": "enoriega/rule_softmatching",3  "architectures": [4    "BertForRuleScoring"5  ],6  "attention_probs_dropout_prob": 0.1,7  "classifier_dropout": null,8  "gradient_checkpointing": false,9  "hidden_act": "gelu",10  "hidden_dropout_prob": 0.1,11  "hidden_size": 768,12  "initializer_range": 0.02,13  "intermediate_size": 3072,14  "layer_norm_eps": 1e-12,15  "loss_func": "margin",16  "margin": 1.0,17  "max_position_embeddings": 512,18  "model_type": "bert",19  "num_attention_heads": 12,20  "num_hidden_layers": 12,21  "pad_token_id": 0,22  "position_embedding_type": "absolute",23  "problem_type": "regression",24  "rule_sentence_encoding": "cls",25  "spec_dropout": 0.2,26  "spec_encoding": "avg",27  "torch_dtype": "float32",28  "transformers_version": "4.19.2",29  "type_vocab_size": 2,30  "use_cache": true,31  "vocab_size": 3052432}33