finetune/wsc/config.json

{
  "_name_or_path": "omarmomen/structformer_s2_final_with_pos",
  "architectures": [
    "StructformerModelForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "auto_map": {
    "AutoConfig": "structformer_as_hf.StructformerConfig",
    "AutoModelForMaskedLM": "structformer_as_hf.StructformerModel",
    "AutoModelForSequenceClassification": "structformer_as_hf.StructformerModelForSequenceClassification"
  },
  "bos_token_id": 0,
  "classifier_dropout": null,
  "conv_size": 9,
  "dropatt": 0.1,
  "dropout": 0.1,
  "eos_token_id": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": 0,
    "1": 1
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "0": 0,
    "1": 1
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "structformer",
  "n_context_layers": 4,
  "n_parser_layers": 4,
  "nhead": 12,
  "nlayers": 8,
  "ntokens": 32000,
  "num_attention_heads": 8,
  "num_hidden_layers": 8,
  "pad": 0,
  "pad_token_id": 1,
  "pos_emb": true,
  "position_embedding_type": "absolute",
  "problem_type": "single_label_classification",
  "relations": [
    "head",
    "child"
  ],
  "relative_bias": false,
  "torch_dtype": "float32",
  "transformers_version": "4.26.1",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 32000,
  "weight_act": "softmax"
}