Training in progress, epoch 1
Browse files- config.json +83 -0
- model.safetensors +3 -0
- runs/Jan05_14-09-38_bfc47a776093/events.out.tfevents.1704463779.bfc47a776093.3811.0 +3 -0
- runs/Jan05_14-19-16_bfc47a776093/events.out.tfevents.1704464358.bfc47a776093.3811.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-INDIRIZZO",
|
14 |
+
"2": "I-INDIRIZZO",
|
15 |
+
"3": "B-LUOGO",
|
16 |
+
"4": "I-LUOGO",
|
17 |
+
"5": "B-IDPROC",
|
18 |
+
"6": "I-IDPROC",
|
19 |
+
"7": "B-IMPORTO",
|
20 |
+
"8": "I-IMPORTO",
|
21 |
+
"9": "B-IDSENT",
|
22 |
+
"10": "I-IDSENT",
|
23 |
+
"11": "B-DOTT",
|
24 |
+
"12": "I-DOTT",
|
25 |
+
"13": "B-DATA",
|
26 |
+
"14": "I-DATA",
|
27 |
+
"15": "B-PERSONA",
|
28 |
+
"16": "I-PERSONA",
|
29 |
+
"17": "B-ORGANIZZAZIONE",
|
30 |
+
"18": "I-ORGANIZZAZIONE",
|
31 |
+
"19": "B-NUMERO",
|
32 |
+
"20": "I-NUMERO",
|
33 |
+
"21": "B-AVV",
|
34 |
+
"22": "I-AVV",
|
35 |
+
"23": "B-CODFISC",
|
36 |
+
"24": "I-CODFISC",
|
37 |
+
"25": "B-LEGGE",
|
38 |
+
"26": "I-LEGGE"
|
39 |
+
},
|
40 |
+
"initializer_range": 0.02,
|
41 |
+
"intermediate_size": 3072,
|
42 |
+
"label2id": {
|
43 |
+
"B-AVV": 21,
|
44 |
+
"B-CODFISC": 23,
|
45 |
+
"B-DATA": 13,
|
46 |
+
"B-DOTT": 11,
|
47 |
+
"B-IDPROC": 5,
|
48 |
+
"B-IDSENT": 9,
|
49 |
+
"B-IMPORTO": 7,
|
50 |
+
"B-INDIRIZZO": 1,
|
51 |
+
"B-LEGGE": 25,
|
52 |
+
"B-LUOGO": 3,
|
53 |
+
"B-NUMERO": 19,
|
54 |
+
"B-ORGANIZZAZIONE": 17,
|
55 |
+
"B-PERSONA": 15,
|
56 |
+
"I-AVV": 22,
|
57 |
+
"I-CODFISC": 24,
|
58 |
+
"I-DATA": 14,
|
59 |
+
"I-DOTT": 12,
|
60 |
+
"I-IDPROC": 6,
|
61 |
+
"I-IDSENT": 10,
|
62 |
+
"I-IMPORTO": 8,
|
63 |
+
"I-INDIRIZZO": 2,
|
64 |
+
"I-LEGGE": 26,
|
65 |
+
"I-LUOGO": 4,
|
66 |
+
"I-NUMERO": 20,
|
67 |
+
"I-ORGANIZZAZIONE": 18,
|
68 |
+
"I-PERSONA": 16,
|
69 |
+
"O": 0
|
70 |
+
},
|
71 |
+
"layer_norm_eps": 1e-12,
|
72 |
+
"max_position_embeddings": 512,
|
73 |
+
"model_type": "bert",
|
74 |
+
"num_attention_heads": 12,
|
75 |
+
"num_hidden_layers": 12,
|
76 |
+
"pad_token_id": 0,
|
77 |
+
"position_embedding_type": "absolute",
|
78 |
+
"torch_dtype": "float32",
|
79 |
+
"transformers_version": "4.35.2",
|
80 |
+
"type_vocab_size": 2,
|
81 |
+
"use_cache": true,
|
82 |
+
"vocab_size": 31102
|
83 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9c5d952a36ab37c20c25083273908e187a74e9f2c40c1c011d653748c98cd44
|
3 |
+
size 437454748
|
runs/Jan05_14-09-38_bfc47a776093/events.out.tfevents.1704463779.bfc47a776093.3811.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe0d9b2d661bd8b7c12761246911b0734868ad05daf156d508726184a74cfede
|
3 |
+
size 7524
|
runs/Jan05_14-19-16_bfc47a776093/events.out.tfevents.1704464358.bfc47a776093.3811.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37d537883c174a06c26f206ce16a3a1225bbdc8c447c818df23d58decc2cb8e2
|
3 |
+
size 5912
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"101": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"102": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"103": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"104": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_len": 512,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bfbc115fa7ab450d42bca2b0935902f55ebe5c3f2a4a6b89c02bb3c4c09b7bb
|
3 |
+
size 4664
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|