GuiTap commited on
Commit
744e40e
·
verified ·
1 Parent(s): 9600a7e

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-OTR",
14
+ "2": "I-OTR",
15
+ "3": "B-uniESTG",
16
+ "4": "I-uniESTG",
17
+ "5": "B-sedSLCT",
18
+ "6": "I-sedSLCT",
19
+ "7": "B-EPC",
20
+ "8": "I-EPC",
21
+ "9": "B-bacSED",
22
+ "10": "I-bacSED",
23
+ "11": "B-IDA",
24
+ "12": "I-IDA",
25
+ "13": "B-PRD",
26
+ "14": "I-PRD",
27
+ "15": "B-ctxGBAC",
28
+ "16": "I-ctxGBAC",
29
+ "17": "B-ERA",
30
+ "18": "I-ERA",
31
+ "19": "B-EON",
32
+ "20": "I-EON",
33
+ "21": "B-sedCARB",
34
+ "22": "I-sedCARB",
35
+ "23": "B-sedORGN",
36
+ "24": "I-sedORGN",
37
+ "25": "B-sedQUIM",
38
+ "26": "I-sedQUIM"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "label2id": {
42
+ "B-EON": 19,
43
+ "B-EPC": 7,
44
+ "B-ERA": 17,
45
+ "B-IDA": 11,
46
+ "B-OTR": 1,
47
+ "B-PRD": 13,
48
+ "B-bacSED": 9,
49
+ "B-ctxGBAC": 15,
50
+ "B-sedCARB": 21,
51
+ "B-sedORGN": 23,
52
+ "B-sedQUIM": 25,
53
+ "B-sedSLCT": 5,
54
+ "B-uniESTG": 3,
55
+ "I-EON": 20,
56
+ "I-EPC": 8,
57
+ "I-ERA": 18,
58
+ "I-IDA": 12,
59
+ "I-OTR": 2,
60
+ "I-PRD": 14,
61
+ "I-bacSED": 10,
62
+ "I-ctxGBAC": 16,
63
+ "I-sedCARB": 22,
64
+ "I-sedORGN": 24,
65
+ "I-sedQUIM": 26,
66
+ "I-sedSLCT": 6,
67
+ "I-uniESTG": 4,
68
+ "O": 0
69
+ },
70
+ "max_position_embeddings": 512,
71
+ "model_type": "distilbert",
72
+ "n_heads": 12,
73
+ "n_layers": 6,
74
+ "output_past": true,
75
+ "pad_token_id": 0,
76
+ "qa_dropout": 0.1,
77
+ "seq_classif_dropout": 0.2,
78
+ "sinusoidal_pos_embds": false,
79
+ "tie_weights_": true,
80
+ "torch_dtype": "float32",
81
+ "transformers_version": "4.41.1",
82
+ "vocab_size": 119547
83
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d626d1a60efcccc90685a29f2db49ee588fb06ce9ea521c4ef6a0f20444c284
3
+ size 539031732
runs/Oct04_02-25-30_42fd7d078cd7/events.out.tfevents.1728008753.42fd7d078cd7.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9379ac64ad59bc4c7dd981e79656aae1da8e8a7093b11fed85fb5fd27f5b026
3
+ size 6442
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
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,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "clean_up_tokenization_spaces": true,
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": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e74402393158008f7d187de1bbf2d635ad2728bc5fa2a101e2f06aea063cae
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff