hungphongtrn commited on
Commit
104106a
1 Parent(s): 667e549

Training in progress, epoch 1

Browse files
.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 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "I-ORGAN",
15
+ "1": "B-PREVENTIVEMED",
16
+ "2": "B-DISEASESYMTOM",
17
+ "3": "B-FOODDRINK",
18
+ "4": "B-ORGANIZATION",
19
+ "5": "B-OCCUPATION",
20
+ "6": "B-DRUGCHEMICAL",
21
+ "7": "I-FOODDRINK",
22
+ "8": "I-DISEASESYMTOM",
23
+ "9": "I-UNITCALIBRATOR",
24
+ "10": "I-DATETIME",
25
+ "11": "I-DIAGNOSTICS",
26
+ "12": "B-TRANSPORTATION",
27
+ "13": "B-GENDER",
28
+ "14": "B-AGE",
29
+ "15": "B-DATETIME",
30
+ "16": "B-LOCATION",
31
+ "17": "B-TREATMENT",
32
+ "18": "I-DRUGCHEMICAL",
33
+ "19": "I-PREVENTIVEMED",
34
+ "20": "I-TREATMENT",
35
+ "21": "I-ORGANIZATION",
36
+ "22": "O",
37
+ "23": "B-UNITCALIBRATOR",
38
+ "24": "B-MEDDEVICETECHNIQUE",
39
+ "25": "I-OCCUPATION",
40
+ "26": "B-PERSONALCARE",
41
+ "27": "I-PERSONALCARE",
42
+ "28": "I-GENDER",
43
+ "29": "I-SURGERY",
44
+ "30": "I-AGE",
45
+ "31": "I-LOCATION",
46
+ "32": "B-DIAGNOSTICS",
47
+ "33": "I-MEDDEVICETECHNIQUE",
48
+ "34": "B-ORGAN",
49
+ "35": "B-SURGERY",
50
+ "36": "I-TRANSPORTATION"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 3072,
54
+ "label2id": {
55
+ "B-AGE": 14,
56
+ "B-DATETIME": 15,
57
+ "B-DIAGNOSTICS": 32,
58
+ "B-DISEASESYMTOM": 2,
59
+ "B-DRUGCHEMICAL": 6,
60
+ "B-FOODDRINK": 3,
61
+ "B-GENDER": 13,
62
+ "B-LOCATION": 16,
63
+ "B-MEDDEVICETECHNIQUE": 24,
64
+ "B-OCCUPATION": 5,
65
+ "B-ORGAN": 34,
66
+ "B-ORGANIZATION": 4,
67
+ "B-PERSONALCARE": 26,
68
+ "B-PREVENTIVEMED": 1,
69
+ "B-SURGERY": 35,
70
+ "B-TRANSPORTATION": 12,
71
+ "B-TREATMENT": 17,
72
+ "B-UNITCALIBRATOR": 23,
73
+ "I-AGE": 30,
74
+ "I-DATETIME": 10,
75
+ "I-DIAGNOSTICS": 11,
76
+ "I-DISEASESYMTOM": 8,
77
+ "I-DRUGCHEMICAL": 18,
78
+ "I-FOODDRINK": 7,
79
+ "I-GENDER": 28,
80
+ "I-LOCATION": 31,
81
+ "I-MEDDEVICETECHNIQUE": 33,
82
+ "I-OCCUPATION": 25,
83
+ "I-ORGAN": 0,
84
+ "I-ORGANIZATION": 21,
85
+ "I-PERSONALCARE": 27,
86
+ "I-PREVENTIVEMED": 19,
87
+ "I-SURGERY": 29,
88
+ "I-TRANSPORTATION": 36,
89
+ "I-TREATMENT": 20,
90
+ "I-UNITCALIBRATOR": 9,
91
+ "O": 22
92
+ },
93
+ "layer_norm_eps": 1e-05,
94
+ "max_position_embeddings": 258,
95
+ "model_type": "roberta",
96
+ "num_attention_heads": 12,
97
+ "num_hidden_layers": 12,
98
+ "pad_token_id": 1,
99
+ "position_embedding_type": "absolute",
100
+ "tokenizer_class": "PhobertTokenizer",
101
+ "torch_dtype": "float32",
102
+ "transformers_version": "4.32.0.dev0",
103
+ "type_vocab_size": 1,
104
+ "use_cache": true,
105
+ "vocab_size": 64001
106
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a9f5d23ff506ebc1b60fe53314d85f4118462bc390a36301fe89c28da373fa4
3
+ size 537813286
runs/May28_16-22-40_labserver/events.out.tfevents.1716913366.labserver.987021.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eaea97e8a5919fba6a3a9bd3beea61973db36e271760e7dae3249387aca1467
3
+ size 7104
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:c247a2f0f7d78b3ebbdf70e56f0423b4d0e2ebca4ecc4202d4d23d8cbdef2100
3
+ size 4472
vocab.txt ADDED
The diff for this file is too large to render. See raw diff