hungphongtrn
commited on
Commit
•
a642688
1
Parent(s):
0c98d0a
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- bpe.codes +0 -0
- config.json +110 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +12 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
bpe.codes
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/phobert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "I-UNITCALIBRATOR",
|
16 |
+
"2": "I-TREATMENT",
|
17 |
+
"3": "I-TRANSPORTATION",
|
18 |
+
"4": "I-SURGERY",
|
19 |
+
"5": "I-PREVENTIVEMED",
|
20 |
+
"6": "I-PERSONALCARE",
|
21 |
+
"7": "I-ORGANIZATION",
|
22 |
+
"8": "I-ORGAN",
|
23 |
+
"9": "I-OCCUPATION",
|
24 |
+
"10": "I-NAME",
|
25 |
+
"11": "I-MEDDEVICETECHNIQUE",
|
26 |
+
"12": "I-LOCATION",
|
27 |
+
"13": "I-GENDER",
|
28 |
+
"14": "I-FOODDRINK",
|
29 |
+
"15": "I-DRUGCHEMICAL",
|
30 |
+
"16": "I-DISEASESYMTOM",
|
31 |
+
"17": "I-DIAGNOSTICS",
|
32 |
+
"18": "I-DATETIME",
|
33 |
+
"19": "I-AGE",
|
34 |
+
"20": "B-UNITCALIBRATOR",
|
35 |
+
"21": "B-TREATMENT",
|
36 |
+
"22": "B-TRANSPORTATION",
|
37 |
+
"23": "B-SURGERY",
|
38 |
+
"24": "B-PREVENTIVEMED",
|
39 |
+
"25": "B-PERSONALCARE",
|
40 |
+
"26": "B-ORGANIZATION",
|
41 |
+
"27": "B-ORGAN",
|
42 |
+
"28": "B-OCCUPATION",
|
43 |
+
"29": "B-NAME",
|
44 |
+
"30": "B-MEDDEVICETECHNIQUE",
|
45 |
+
"31": "B-LOCATION",
|
46 |
+
"32": "B-GENDER",
|
47 |
+
"33": "B-FOODDRINK",
|
48 |
+
"34": "B-DRUGCHEMICAL",
|
49 |
+
"35": "B-DISEASESYMTOM",
|
50 |
+
"36": "B-DIAGNOSTICS",
|
51 |
+
"37": "B-DATETIME",
|
52 |
+
"38": "B-AGE"
|
53 |
+
},
|
54 |
+
"initializer_range": 0.02,
|
55 |
+
"intermediate_size": 3072,
|
56 |
+
"label2id": {
|
57 |
+
"B-AGE": 38,
|
58 |
+
"B-DATETIME": 37,
|
59 |
+
"B-DIAGNOSTICS": 36,
|
60 |
+
"B-DISEASESYMTOM": 35,
|
61 |
+
"B-DRUGCHEMICAL": 34,
|
62 |
+
"B-FOODDRINK": 33,
|
63 |
+
"B-GENDER": 32,
|
64 |
+
"B-LOCATION": 31,
|
65 |
+
"B-MEDDEVICETECHNIQUE": 30,
|
66 |
+
"B-NAME": 29,
|
67 |
+
"B-OCCUPATION": 28,
|
68 |
+
"B-ORGAN": 27,
|
69 |
+
"B-ORGANIZATION": 26,
|
70 |
+
"B-PERSONALCARE": 25,
|
71 |
+
"B-PREVENTIVEMED": 24,
|
72 |
+
"B-SURGERY": 23,
|
73 |
+
"B-TRANSPORTATION": 22,
|
74 |
+
"B-TREATMENT": 21,
|
75 |
+
"B-UNITCALIBRATOR": 20,
|
76 |
+
"I-AGE": 19,
|
77 |
+
"I-DATETIME": 18,
|
78 |
+
"I-DIAGNOSTICS": 17,
|
79 |
+
"I-DISEASESYMTOM": 16,
|
80 |
+
"I-DRUGCHEMICAL": 15,
|
81 |
+
"I-FOODDRINK": 14,
|
82 |
+
"I-GENDER": 13,
|
83 |
+
"I-LOCATION": 12,
|
84 |
+
"I-MEDDEVICETECHNIQUE": 11,
|
85 |
+
"I-NAME": 10,
|
86 |
+
"I-OCCUPATION": 9,
|
87 |
+
"I-ORGAN": 8,
|
88 |
+
"I-ORGANIZATION": 7,
|
89 |
+
"I-PERSONALCARE": 6,
|
90 |
+
"I-PREVENTIVEMED": 5,
|
91 |
+
"I-SURGERY": 4,
|
92 |
+
"I-TRANSPORTATION": 3,
|
93 |
+
"I-TREATMENT": 2,
|
94 |
+
"I-UNITCALIBRATOR": 1,
|
95 |
+
"O": 0
|
96 |
+
},
|
97 |
+
"layer_norm_eps": 1e-05,
|
98 |
+
"max_position_embeddings": 258,
|
99 |
+
"model_type": "roberta",
|
100 |
+
"num_attention_heads": 12,
|
101 |
+
"num_hidden_layers": 12,
|
102 |
+
"pad_token_id": 1,
|
103 |
+
"position_embedding_type": "absolute",
|
104 |
+
"tokenizer_class": "PhobertTokenizer",
|
105 |
+
"torch_dtype": "float32",
|
106 |
+
"transformers_version": "4.32.0.dev0",
|
107 |
+
"type_vocab_size": 1,
|
108 |
+
"use_cache": true,
|
109 |
+
"vocab_size": 64001
|
110 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47eecae9fd5746579b13cb544ce3821ac6ee56c06462927b26e517a76092fe74
|
3 |
+
size 537819430
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": "<mask>",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"sep_token": "</s>",
|
10 |
+
"tokenizer_class": "PhobertTokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdc4ed66cd285bb5a677d6a91e07a9dbccb9d62c2830bf31af7ffc6bd7910b29
|
3 |
+
size 4408
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|