Conrad747 commited on
Commit
43faf30
1 Parent(s): 08700ab

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. config.json +50 -50
  2. merges.txt +0 -0
  3. pytorch_model.bin +1 -1
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +6 -10
  6. training_args.bin +1 -1
  7. vocab.json +0 -0
config.json CHANGED
@@ -11,60 +11,60 @@
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
- "0": "LABEL_0",
15
- "1": "LABEL_1",
16
- "2": "LABEL_2",
17
- "3": "LABEL_3",
18
- "4": "LABEL_4",
19
- "5": "LABEL_5",
20
- "6": "LABEL_6",
21
- "7": "LABEL_7",
22
- "8": "LABEL_8",
23
- "9": "LABEL_9",
24
- "10": "LABEL_10",
25
- "11": "LABEL_11",
26
- "12": "LABEL_12",
27
- "13": "LABEL_13",
28
- "14": "LABEL_14",
29
- "15": "LABEL_15",
30
- "16": "LABEL_16",
31
- "17": "LABEL_17",
32
- "18": "LABEL_18",
33
- "19": "LABEL_19",
34
- "20": "LABEL_20",
35
- "21": "LABEL_21",
36
- "22": "LABEL_22",
37
- "23": "LABEL_23",
38
- "24": "LABEL_24"
39
  },
40
  "initializer_range": 0.02,
41
  "intermediate_size": 3072,
42
  "label2id": {
43
- "LABEL_0": 0,
44
- "LABEL_1": 1,
45
- "LABEL_10": 10,
46
- "LABEL_11": 11,
47
- "LABEL_12": 12,
48
- "LABEL_13": 13,
49
- "LABEL_14": 14,
50
- "LABEL_15": 15,
51
- "LABEL_16": 16,
52
- "LABEL_17": 17,
53
- "LABEL_18": 18,
54
- "LABEL_19": 19,
55
- "LABEL_2": 2,
56
- "LABEL_20": 20,
57
- "LABEL_21": 21,
58
- "LABEL_22": 22,
59
- "LABEL_23": 23,
60
- "LABEL_24": 24,
61
- "LABEL_3": 3,
62
- "LABEL_4": 4,
63
- "LABEL_5": 5,
64
- "LABEL_6": 6,
65
- "LABEL_7": 7,
66
- "LABEL_8": 8,
67
- "LABEL_9": 9
68
  },
69
  "layer_norm_eps": 1e-05,
70
  "max_position_embeddings": 514,
 
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
+ "0": "O",
15
+ "1": "B-PERSON",
16
+ "2": "I-PERSON",
17
+ "3": "L-PERSON",
18
+ "4": "U-PERSON",
19
+ "5": "B-NORP",
20
+ "6": "I-NORP",
21
+ "7": "L-NORP",
22
+ "8": "U-NORP",
23
+ "9": "B-DATE",
24
+ "10": "I-DATE",
25
+ "11": "L-DATE",
26
+ "12": "U-DATE",
27
+ "13": "B-USERID",
28
+ "14": "I-USERID",
29
+ "15": "L-USERID",
30
+ "16": "U-USERID",
31
+ "17": "B-ORG",
32
+ "18": "I-ORG",
33
+ "19": "L-ORG",
34
+ "20": "U-ORG",
35
+ "21": "B-LOCATION",
36
+ "22": "I-LOCATION",
37
+ "23": "L-LOCATION",
38
+ "24": "U-LOCATION"
39
  },
40
  "initializer_range": 0.02,
41
  "intermediate_size": 3072,
42
  "label2id": {
43
+ "B-DATE": 9,
44
+ "B-LOCATION": 21,
45
+ "B-NORP": 5,
46
+ "B-ORG": 17,
47
+ "B-PERSON": 1,
48
+ "B-USERID": 13,
49
+ "I-DATE": 10,
50
+ "I-LOCATION": 22,
51
+ "I-NORP": 6,
52
+ "I-ORG": 18,
53
+ "I-PERSON": 2,
54
+ "I-USERID": 14,
55
+ "L-DATE": 11,
56
+ "L-LOCATION": 23,
57
+ "L-NORP": 7,
58
+ "L-ORG": 19,
59
+ "L-PERSON": 3,
60
+ "L-USERID": 15,
61
+ "O": 0,
62
+ "U-DATE": 12,
63
+ "U-LOCATION": 24,
64
+ "U-NORP": 8,
65
+ "U-ORG": 20,
66
+ "U-PERSON": 4,
67
+ "U-USERID": 16
68
  },
69
  "layer_norm_eps": 1e-05,
70
  "max_position_embeddings": 514,
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88f5c41b730373bdd3adac66cc7fcb28f0304eae2fd2f4223331b0fcd8402286
3
  size 1109960177
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18d8fa3dbda2168aa5440582af1aea9df9d4e52fb8990545cd315a1df2b5db77
3
  size 1109960177
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
3
- size 17082758
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a60abad17917ed62a89b321bd425a54df25c2d9af89161f31a67bfefa04a9ac9
3
+ size 2108687
tokenizer_config.json CHANGED
@@ -1,20 +1,16 @@
1
  {
 
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
5
- "mask_token": {
6
- "__type": "AddedToken",
7
- "content": "<mask>",
8
- "lstrip": true,
9
- "normalized": true,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
  "model_max_length": 512,
14
- "name_or_path": "xlm-roberta-base",
15
  "pad_token": "<pad>",
16
  "sep_token": "</s>",
17
  "special_tokens_map_file": null,
18
- "tokenizer_class": "XLMRobertaTokenizer",
 
19
  "unk_token": "<unk>"
20
  }
 
1
  {
2
+ "add_prefix_space": true,
3
  "bos_token": "<s>",
4
  "cls_token": "<s>",
5
  "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
 
 
 
 
 
 
8
  "model_max_length": 512,
9
+ "name_or_path": "roberta-base",
10
  "pad_token": "<pad>",
11
  "sep_token": "</s>",
12
  "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
  "unk_token": "<unk>"
16
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7068b250c104b945908923011df8ab77c1a87a7c84d089f7f82b8a9e9167dea
3
  size 3375
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe24fb8aaa61229d684bec22bc06c6be972fc92317a2af95feee18649451e6e1
3
  size 3375
vocab.json ADDED
The diff for this file is too large to render. See raw diff