PyTorch
roberta
Generated from Trainer
File size: 1,200 Bytes
d0071a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
{
  "_name_or_path": "EriBERTa-clinical-trials-temp-ents",
  "architectures": [
    "RobertaForTokenClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "B-Age",
    "1": "I-Age",
    "2": "B-Date",
    "3": "I-Date",
    "4": "B-Duration",
    "5": "I-Duration",
    "6": "B-Frequency",
    "7": "I-Frequency",
    "8": "B-Time",
    "9": "I-Time",
    "10": "O"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "B-Age": 0,
    "B-Date": 2,
    "B-Duration": 4,
    "B-Frequency": 6,
    "B-Time": 8,
    "I-Age": 1,
    "I-Date": 3,
    "I-Duration": 5,
    "I-Frequency": 7,
    "I-Time": 9,
    "O": 10
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.28.0",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 64000
}