xiazeng/sciverbinary-model_train_dev_data-biobertl-rationale_continue

1{2  "_num_labels": 2,3  "architectures": [4    "BertForSequenceClassification"5  ],6  "attention_probs_dropout_prob": 0.1,7  "bos_token_id": null,8  "decoder_start_token_id": null,9  "do_sample": false,10  "early_stopping": false,11  "eos_token_id": null,12  "finetuning_task": null,13  "hidden_act": "gelu",14  "hidden_dropout_prob": 0.1,15  "hidden_size": 1024,16  "id2label": {17    "0": "LABEL_0",18    "1": "LABEL_1"19  },20  "initializer_range": 0.02,21  "intermediate_size": 4096,22  "is_decoder": false,23  "is_encoder_decoder": false,24  "label2id": {25    "LABEL_0": 0,26    "LABEL_1": 127  },28  "layer_norm_eps": 1e-12,29  "length_penalty": 1.0,30  "max_length": 20,31  "max_position_embeddings": 512,32  "min_length": 0,33  "model_type": "bert",34  "no_repeat_ngram_size": 0,35  "num_attention_heads": 16,36  "num_beams": 1,37  "num_hidden_layers": 24,38  "num_return_sequences": 1,39  "output_attentions": false,40  "output_hidden_states": false,41  "output_past": true,42  "pad_token_id": 0,43  "prefix": null,44  "pruned_heads": {},45  "repetition_penalty": 1.0,46  "task_specific_params": null,47  "temperature": 1.0,48  "top_k": 50,49  "top_p": 1.0,50  "torchscript": false,51  "type_vocab_size": 2,52  "use_bfloat16": false,53  "vocab_size": 5899654}55