{
  "_name_or_path": "./final-a100-model",
  "architectures": [
    "DebertaV2ForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1024,
  "id2label": {
    "0": "barely-true",
    "1": "false",
    "2": "half-true",
    "3": "mostly-true",
    "4": "pants-fire",
    "5": "true"
  },
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "barely-true": 0,
    "false": 1,
    "half-true": 2,
    "mostly-true": 3,
    "pants-fire": 4,
    "true": 5
  },
  "layer_norm_eps": 1e-07,
  "max_position_embeddings": 512,
  "max_relative_positions": -1,
  "model_type": "deberta-v2",
  "norm_rel_ebd": "layer_norm",
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "pad_token_id": 0,
  "pooler_dropout": 0,
  "pooler_hidden_act": "gelu",
  "pooler_hidden_size": 1024,
  "pos_att_type": [
    "p2c",
    "c2p"
  ],
  "position_biased_input": false,
  "position_buckets": 256,
  "problem_type": "single_label_classification",
  "relative_attention": true,
  "share_att_key": true,
  "torch_dtype": "float32",
  "transformers_version": "4.38.0",
  "type_vocab_size": 0,
  "vocab_size": 128100,
  "task_specific_params": {
    "text-classification": {
      "max_length": 384,
      "problem_type": "single_label_classification"
    }
  },
  "finetuning_task": "fact_checking",
  "custom_datasets": [
    "liar"
  ],
  "performance": {
    "validation_accuracy": 0.4081,
    "test_accuracy": 0.3757,
    "macro_f1": 0.3689
  }
}