{
  "_name_or_path": "../proxy_training_results/RoBERTa-ks/cebab.alpha.1.0.beta.1.0.gemma.3.0.lr.8e-05.dim.192.hightype.roberta-base.CEBaB.cls.dropout.0.1.enc.dropout.0.1.counter.type.true.k.19684.int.layer.8.seed_42/",
  "architectures": [
    "IITRobertaForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": 0.1,
  "eos_token_id": 2,
  "finetuning_task": "cebab",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "0",
    "1": "1",
    "2": "2",
    "3": "3",
    "4": "4"
  },
  "initializer_range": 0.02,
  "interchange_hidden_layer": 8,
  "intermediate_size": 3072,
  "intervention_h_dim": 192,
  "label2id": {
    "0": 0,
    "1": 1,
    "2": 2,
    "3": 3,
    "4": 4
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "problem_type": "single_label_classification",
  "torch_dtype": "float32",
  "transformers_version": "4.22.2",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 50265
}