{
  "_name_or_path": "albert-xxlarge-v2",
  "architectures": [
    "AlbertForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0,
  "bos_token_id": 2,
  "classifier_dropout_prob": 0.1,
  "down_scale_factor": 1,
  "embedding_size": 128,
  "eos_token_id": 3,
  "gap_size": 0,
  "hidden_act": "gelu_new",
  "hidden_dropout_prob": 0,
  "hidden_size": 4096,
  "id2label": {
    "0": "NA",
    "1": "Main",
    "2": "Cause_Specific",
    "3": "Distant_Anecdotal",
    "4": "Distant_Evaluation",
    "5": "Main_Consequence",
    "6": "Distant_Historical",
    "7": "Cause_General",
    "8": "Distant_Expectations_Consequences"
  },
  "initializer_range": 0.02,
  "inner_group_num": 1,
  "intermediate_size": 16384,
  "label2id": {
    "Cause_General": 7,
    "Cause_Specific": 2,
    "Distant_Anecdotal": 3,
    "Distant_Evaluation": 4,
    "Distant_Expectations_Consequences": 8,
    "Distant_Historical": 6,
    "Main": 1,
    "Main_Consequence": 5,
    "NA": 0
  },
  "layer_norm_eps": 1e-12,
  "layers_to_keep": [],
  "max_position_embeddings": 512,
  "model_type": "albert",
  "net_structure_type": 0,
  "num_attention_heads": 64,
  "num_hidden_groups": 1,
  "num_hidden_layers": 12,
  "num_memory_blocks": 0,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "problem_type": "single_label_classification",
  "torch_dtype": "float32",
  "transformers_version": "4.36.0.dev0",
  "type_vocab_size": 2,
  "vocab_size": 30000
}