nickprock commited on
Commit
00ad7f0
1 Parent(s): 8707b8f

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dbmdz/bert-base-italian-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-PER",
14
+ "2": "I-PER",
15
+ "3": "B-LOC",
16
+ "4": "I-LOC",
17
+ "5": "B-ORG",
18
+ "6": "I-ORG",
19
+ "7": "B-ANIM",
20
+ "8": "I-ANIM",
21
+ "9": "B-BIO",
22
+ "10": "I-BIO",
23
+ "11": "B-CEL",
24
+ "12": "I-CEL",
25
+ "13": "B-DIS",
26
+ "14": "I-DIS",
27
+ "15": "B-EVE",
28
+ "16": "I-EVE",
29
+ "17": "B-FOOD",
30
+ "18": "I-FOOD",
31
+ "19": "B-INST",
32
+ "20": "I-INST",
33
+ "21": "B-MEDIA",
34
+ "22": "I-MEDIA",
35
+ "23": "B-PLANT",
36
+ "24": "I-PLANT",
37
+ "25": "B-MYTH",
38
+ "26": "I-MYTH",
39
+ "27": "B-TIME",
40
+ "28": "I-TIME",
41
+ "29": "B-VEHI",
42
+ "30": "I-VEHI",
43
+ "31": "B-MISC",
44
+ "32": "I-MISC"
45
+ },
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 3072,
48
+ "label2id": {
49
+ "B-ANIM": 7,
50
+ "B-BIO": 9,
51
+ "B-CEL": 11,
52
+ "B-DIS": 13,
53
+ "B-EVE": 15,
54
+ "B-FOOD": 17,
55
+ "B-INST": 19,
56
+ "B-LOC": 3,
57
+ "B-MEDIA": 21,
58
+ "B-MISC": 31,
59
+ "B-MYTH": 25,
60
+ "B-ORG": 5,
61
+ "B-PER": 1,
62
+ "B-PLANT": 23,
63
+ "B-TIME": 27,
64
+ "B-VEHI": 29,
65
+ "I-ANIM": 8,
66
+ "I-BIO": 10,
67
+ "I-CEL": 12,
68
+ "I-DIS": 14,
69
+ "I-EVE": 16,
70
+ "I-FOOD": 18,
71
+ "I-INST": 20,
72
+ "I-LOC": 4,
73
+ "I-MEDIA": 22,
74
+ "I-MISC": 32,
75
+ "I-MYTH": 26,
76
+ "I-ORG": 6,
77
+ "I-PER": 2,
78
+ "I-PLANT": 24,
79
+ "I-TIME": 28,
80
+ "I-VEHI": 30,
81
+ "O": 0
82
+ },
83
+ "layer_norm_eps": 1e-12,
84
+ "max_position_embeddings": 512,
85
+ "model_type": "bert",
86
+ "num_attention_heads": 12,
87
+ "num_hidden_layers": 12,
88
+ "pad_token_id": 0,
89
+ "position_embedding_type": "absolute",
90
+ "torch_dtype": "float32",
91
+ "transformers_version": "4.27.3",
92
+ "type_vocab_size": 2,
93
+ "use_cache": true,
94
+ "vocab_size": 31102
95
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb025de30cc9ad33da5e665b166cad21020826ec51eca886ec19a9acbb95c74
3
+ size 437522029
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "max_len": 512,
7
+ "model_max_length": 512,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5489930ea5d2ab97465276437c3e6b0282d2d06faa55b57e0a02926eacf8411b
3
+ size 3579
vocab.txt ADDED
The diff for this file is too large to render. See raw diff