models/transformer/prediction-model/config.json

{
  "_name_or_path": "/kaggle/working/florabert/models/transformer/language-model",
  "alpha": 0.1,
  "architectures": [
    "RobertaForSequenceClassificationMeanPool"
  ],
  "attention_probs_dropout_prob": 0.1,
  "batch_norm": false,
  "block_size": 258,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "end_token_idx": 1,
  "eos_token_id": 2,
  "freeze_base": true,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.2,
  "hidden_size": 768,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4",
    "5": "LABEL_5",
    "6": "LABEL_6",
    "7": "LABEL_7"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4,
    "LABEL_5": 5,
    "LABEL_6": 6,
    "LABEL_7": 7
  },
  "layer_norm_eps": 1e-12,
  "log_offset": 1,
  "max_position_embeddings": 258,
  "max_seq_len": 1000,
  "model_type": "roberta",
  "num_attention_heads": 6,
  "num_hidden_layers": 6,
  "output_hidden_states": true,
  "output_mode": "regression",
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "start_token_idx": 0,
  "test_size": 0.2,
  "threshold": 1,
  "torch_dtype": "float32",
  "transformers_version": "4.33.0",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 5005
}