raulgdp commited on
Commit
2ab0a35
·
verified ·
1 Parent(s): e23877a

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "google-bert/bert-base-cased",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
@@ -10,39 +10,142 @@
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
- "0": "O",
14
- "1": "B-PER",
15
- "2": "I-PER",
16
- "3": "B-ORG",
17
- "4": "I-ORG",
18
- "5": "B-LOC",
19
- "6": "I-LOC",
20
- "7": "B-MISC",
21
- "8": "I-MISC"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  },
23
  "initializer_range": 0.02,
24
  "intermediate_size": 3072,
25
  "label2id": {
26
- "B-LOC": 5,
27
- "B-MISC": 7,
28
- "B-ORG": 3,
29
- "B-PER": 1,
30
- "I-LOC": 6,
31
- "I-MISC": 8,
32
- "I-ORG": 4,
33
- "I-PER": 2,
34
- "O": 0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  },
36
  "layer_norm_eps": 1e-12,
37
  "max_position_embeddings": 512,
38
  "model_type": "bert",
39
  "num_attention_heads": 12,
40
  "num_hidden_layers": 12,
41
- "pad_token_id": 0,
 
42
  "position_embedding_type": "absolute",
43
  "torch_dtype": "float32",
44
  "transformers_version": "4.46.2",
45
  "type_vocab_size": 2,
46
  "use_cache": true,
47
- "vocab_size": 28996
48
  }
 
1
  {
2
+ "_name_or_path": "NazaGara/NER-fine-tuned-BETO",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
 
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
+ "0": "AO",
14
+ "1": "AQ",
15
+ "2": "CC",
16
+ "3": "CS",
17
+ "4": "DA",
18
+ "5": "DE",
19
+ "6": "DD",
20
+ "7": "DI",
21
+ "8": "DN",
22
+ "9": "DP",
23
+ "10": "DT",
24
+ "11": "Faa",
25
+ "12": "Fat",
26
+ "13": "Fc",
27
+ "14": "Fd",
28
+ "15": "Fe",
29
+ "16": "Fg",
30
+ "17": "Fh",
31
+ "18": "Fia",
32
+ "19": "Fit",
33
+ "20": "Fp",
34
+ "21": "Fpa",
35
+ "22": "Fpt",
36
+ "23": "Fs",
37
+ "24": "Ft",
38
+ "25": "Fx",
39
+ "26": "Fz",
40
+ "27": "I",
41
+ "28": "NC",
42
+ "29": "NP",
43
+ "30": "P0",
44
+ "31": "PD",
45
+ "32": "PI",
46
+ "33": "PN",
47
+ "34": "PP",
48
+ "35": "PR",
49
+ "36": "PT",
50
+ "37": "PX",
51
+ "38": "RG",
52
+ "39": "RN",
53
+ "40": "SP",
54
+ "41": "VAI",
55
+ "42": "VAM",
56
+ "43": "VAN",
57
+ "44": "VAP",
58
+ "45": "VAS",
59
+ "46": "VMG",
60
+ "47": "VMI",
61
+ "48": "VMM",
62
+ "49": "VMN",
63
+ "50": "VMP",
64
+ "51": "VMS",
65
+ "52": "VSG",
66
+ "53": "VSI",
67
+ "54": "VSM",
68
+ "55": "VSN",
69
+ "56": "VSP",
70
+ "57": "VSS",
71
+ "58": "Y",
72
+ "59": "Z"
73
  },
74
  "initializer_range": 0.02,
75
  "intermediate_size": 3072,
76
  "label2id": {
77
+ "AO": 0,
78
+ "AQ": 1,
79
+ "CC": 2,
80
+ "CS": 3,
81
+ "DA": 4,
82
+ "DD": 6,
83
+ "DE": 5,
84
+ "DI": 7,
85
+ "DN": 8,
86
+ "DP": 9,
87
+ "DT": 10,
88
+ "Faa": 11,
89
+ "Fat": 12,
90
+ "Fc": 13,
91
+ "Fd": 14,
92
+ "Fe": 15,
93
+ "Fg": 16,
94
+ "Fh": 17,
95
+ "Fia": 18,
96
+ "Fit": 19,
97
+ "Fp": 20,
98
+ "Fpa": 21,
99
+ "Fpt": 22,
100
+ "Fs": 23,
101
+ "Ft": 24,
102
+ "Fx": 25,
103
+ "Fz": 26,
104
+ "I": 27,
105
+ "NC": 28,
106
+ "NP": 29,
107
+ "P0": 30,
108
+ "PD": 31,
109
+ "PI": 32,
110
+ "PN": 33,
111
+ "PP": 34,
112
+ "PR": 35,
113
+ "PT": 36,
114
+ "PX": 37,
115
+ "RG": 38,
116
+ "RN": 39,
117
+ "SP": 40,
118
+ "VAI": 41,
119
+ "VAM": 42,
120
+ "VAN": 43,
121
+ "VAP": 44,
122
+ "VAS": 45,
123
+ "VMG": 46,
124
+ "VMI": 47,
125
+ "VMM": 48,
126
+ "VMN": 49,
127
+ "VMP": 50,
128
+ "VMS": 51,
129
+ "VSG": 52,
130
+ "VSI": 53,
131
+ "VSM": 54,
132
+ "VSN": 55,
133
+ "VSP": 56,
134
+ "VSS": 57,
135
+ "Y": 58,
136
+ "Z": 59
137
  },
138
  "layer_norm_eps": 1e-12,
139
  "max_position_embeddings": 512,
140
  "model_type": "bert",
141
  "num_attention_heads": 12,
142
  "num_hidden_layers": 12,
143
+ "output_past": true,
144
+ "pad_token_id": 1,
145
  "position_embedding_type": "absolute",
146
  "torch_dtype": "float32",
147
  "transformers_version": "4.46.2",
148
  "type_vocab_size": 2,
149
  "use_cache": true,
150
+ "vocab_size": 31002
151
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f88cb5cfe5a7855be09be9d5a8b703bb3c6ef90e9e95eeb1edde3f78cc228895
3
- size 430929740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d4b659f97ed27b4a246f4d7df824ed794e264ffdc316c1ec2740e72b02d667
3
+ size 437249056
runs/Dec05_16-23-58_8695d2e2c9ca/events.out.tfevents.1733415844.8695d2e2c9ca.1134.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bf0c35d522c5d091bcdd4086bb3d79437ac6891ccd5ca3da531bc6f21749562
3
+ size 7897
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -2,39 +2,39 @@
2
  "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "[PAD]",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "100": {
13
- "content": "[UNK]",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
- "101": {
21
- "content": "[CLS]",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
- "102": {
29
- "content": "[SEP]",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
- "103": {
37
- "content": "[MASK]",
38
  "lstrip": false,
39
  "normalized": false,
40
  "rstrip": false,
@@ -44,12 +44,15 @@
44
  },
45
  "clean_up_tokenization_spaces": false,
46
  "cls_token": "[CLS]",
 
47
  "do_lower_case": false,
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
 
 
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
- "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
  "tokenizer_class": "BertTokenizer",
55
  "unk_token": "[UNK]"
 
2
  "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "[MASK]",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "1": {
13
+ "content": "[PAD]",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "3": {
21
+ "content": "[UNK]",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
+ "4": {
29
+ "content": "[CLS]",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "5": {
37
+ "content": "[SEP]",
38
  "lstrip": false,
39
  "normalized": false,
40
  "rstrip": false,
 
44
  },
45
  "clean_up_tokenization_spaces": false,
46
  "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
  "do_lower_case": false,
49
  "mask_token": "[MASK]",
50
  "model_max_length": 512,
51
+ "never_split": null,
52
+ "num_labels": 9,
53
  "pad_token": "[PAD]",
54
  "sep_token": "[SEP]",
55
+ "strip_accents": false,
56
  "tokenize_chinese_chars": true,
57
  "tokenizer_class": "BertTokenizer",
58
  "unk_token": "[UNK]"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30fc18e57782edca8fa0ffdc0c67571ee11a36b022e859117a3be12509303af6
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb1e50989db4d3d63312c70081ccd65b760dc44b910622d8692a272b2455e79
3
  size 5304
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff