config.json

{
  "_name_or_path": "/mnt/data/device-aware-bert/token_pruning/teachers/MRPC",
  "architectures": [
    "ToPBertForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "do_layer_distill": false,
  "finetuning_task": "mrpc",
  "gradient_checkpointing": false,
  "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-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "output_attentions": true,
  "output_hidden_states": true,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "pruned_heads": {
    "0": [],
    "1": [],
    "2": [],
    "3": [],
    "4": [],
    "5": [],
    "6": [],
    "7": [],
    "8": [],
    "9": [],
    "10": [],
    "11": []
  },
  "torch_dtype": "float32",
  "transformers_version": "4.16.0",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 30522
}