{
  "architectures": [
    "RobertaForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "divide": "two_stage",
  "finetuning_task": "sst-2",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "is_decoder": false,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "num_labels": 2,
  "output_attentions": false,
  "output_hidden_states": false,
  "output_past": true,
  "pruned_heads": {},
  "torchscript": false,
  "type_vocab_size": 1,
  "use_bfloat16": false,
  "vocab_size": 50265
}