research-dump/roberta-base_temp_classifier_bootstrapped_v2

1{2  "_name_or_path": "roberta-base",3  "architectures": [4    "RobertaForSequenceClassification"5  ],6  "attention_probs_dropout_prob": 0.1,7  "bos_token_id": 0,8  "classifier_dropout": null,9  "eos_token_id": 2,10  "hidden_act": "gelu",11  "hidden_dropout_prob": 0.1,12  "hidden_size": 768,13  "id2label": {14    "0": "LABEL_0",15    "1": "LABEL_1",16    "2": "LABEL_2"17  },18  "initializer_range": 0.02,19  "intermediate_size": 3072,20  "label2id": {21    "LABEL_0": 0,22    "LABEL_1": 1,23    "LABEL_2": 224  },25  "layer_norm_eps": 1e-05,26  "max_position_embeddings": 514,27  "model_type": "roberta",28  "num_attention_heads": 12,29  "num_hidden_layers": 12,30  "pad_token_id": 1,31  "position_embedding_type": "absolute",32  "problem_type": "single_label_classification",33  "torch_dtype": "float32",34  "transformers_version": "4.29.1",35  "type_vocab_size": 1,36  "use_cache": true,37  "vocab_size": 5026938}39