truongphan commited on
Commit
3ae7bf4
1 Parent(s): 0ccaf92

UIT-VLU vn tourism NER

Browse files
config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31",
44
+ "32": "LABEL_32",
45
+ "33": "LABEL_33",
46
+ "34": "LABEL_34",
47
+ "35": "LABEL_35",
48
+ "36": "LABEL_36",
49
+ "37": "LABEL_37",
50
+ "38": "LABEL_38",
51
+ "39": "LABEL_39",
52
+ "40": "LABEL_40",
53
+ "41": "LABEL_41",
54
+ "42": "LABEL_42",
55
+ "43": "LABEL_43",
56
+ "44": "LABEL_44",
57
+ "45": "LABEL_45",
58
+ "46": "LABEL_46",
59
+ "47": "LABEL_47",
60
+ "48": "LABEL_48",
61
+ "49": "LABEL_49",
62
+ "50": "LABEL_50",
63
+ "51": "LABEL_51",
64
+ "52": "LABEL_52",
65
+ "53": "LABEL_53",
66
+ "54": "LABEL_54",
67
+ "55": "LABEL_55",
68
+ "56": "LABEL_56",
69
+ "57": "LABEL_57",
70
+ "58": "LABEL_58",
71
+ "59": "LABEL_59",
72
+ "60": "LABEL_60",
73
+ "61": "LABEL_61",
74
+ "62": "LABEL_62",
75
+ "63": "LABEL_63",
76
+ "64": "LABEL_64",
77
+ "65": "LABEL_65",
78
+ "66": "LABEL_66"
79
+ },
80
+ "initializer_range": 0.02,
81
+ "intermediate_size": 3072,
82
+ "label2id": {
83
+ "LABEL_0": 0,
84
+ "LABEL_1": 1,
85
+ "LABEL_10": 10,
86
+ "LABEL_11": 11,
87
+ "LABEL_12": 12,
88
+ "LABEL_13": 13,
89
+ "LABEL_14": 14,
90
+ "LABEL_15": 15,
91
+ "LABEL_16": 16,
92
+ "LABEL_17": 17,
93
+ "LABEL_18": 18,
94
+ "LABEL_19": 19,
95
+ "LABEL_2": 2,
96
+ "LABEL_20": 20,
97
+ "LABEL_21": 21,
98
+ "LABEL_22": 22,
99
+ "LABEL_23": 23,
100
+ "LABEL_24": 24,
101
+ "LABEL_25": 25,
102
+ "LABEL_26": 26,
103
+ "LABEL_27": 27,
104
+ "LABEL_28": 28,
105
+ "LABEL_29": 29,
106
+ "LABEL_3": 3,
107
+ "LABEL_30": 30,
108
+ "LABEL_31": 31,
109
+ "LABEL_32": 32,
110
+ "LABEL_33": 33,
111
+ "LABEL_34": 34,
112
+ "LABEL_35": 35,
113
+ "LABEL_36": 36,
114
+ "LABEL_37": 37,
115
+ "LABEL_38": 38,
116
+ "LABEL_39": 39,
117
+ "LABEL_4": 4,
118
+ "LABEL_40": 40,
119
+ "LABEL_41": 41,
120
+ "LABEL_42": 42,
121
+ "LABEL_43": 43,
122
+ "LABEL_44": 44,
123
+ "LABEL_45": 45,
124
+ "LABEL_46": 46,
125
+ "LABEL_47": 47,
126
+ "LABEL_48": 48,
127
+ "LABEL_49": 49,
128
+ "LABEL_5": 5,
129
+ "LABEL_50": 50,
130
+ "LABEL_51": 51,
131
+ "LABEL_52": 52,
132
+ "LABEL_53": 53,
133
+ "LABEL_54": 54,
134
+ "LABEL_55": 55,
135
+ "LABEL_56": 56,
136
+ "LABEL_57": 57,
137
+ "LABEL_58": 58,
138
+ "LABEL_59": 59,
139
+ "LABEL_6": 6,
140
+ "LABEL_60": 60,
141
+ "LABEL_61": 61,
142
+ "LABEL_62": 62,
143
+ "LABEL_63": 63,
144
+ "LABEL_64": 64,
145
+ "LABEL_65": 65,
146
+ "LABEL_66": 66,
147
+ "LABEL_7": 7,
148
+ "LABEL_8": 8,
149
+ "LABEL_9": 9
150
+ },
151
+ "layer_norm_eps": 1e-12,
152
+ "max_position_embeddings": 512,
153
+ "model_type": "bert",
154
+ "num_attention_heads": 12,
155
+ "num_hidden_layers": 12,
156
+ "pad_token_id": 0,
157
+ "position_embedding_type": "absolute",
158
+ "transformers_version": "4.8.2",
159
+ "type_vocab_size": 2,
160
+ "use_cache": true,
161
+ "vocab_size": 28996
162
+ }
model_args.json ADDED
@@ -0,0 +1 @@
 
1
+ {"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 16, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "bert-base-cased", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 30, "optimizer": "AdamW", "output_dir": "bert-ner-model_new", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 10, "quantized_model": false, "reprocess_input_data": true, "save_best_model": "bert-ner-model_new", "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 96, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["O", "B-TA", "I-TA", "B-PRO", "I-PRO", "B-TEM", "I-TEM", "B-COM", "I-COM", "B-PAR", "I-PAR", "B-CIT", "I-CIT", "B-MOU", "I-MOU", "B-HAM", "I-HAM", "B-AWA", "I-AWA", "B-VIS", "I-VIS", "B-FES", "I-FES", "B-ISL", "I-ISL", "B-TOW", "I-TOW", "B-VIL", "I-VIL", "B-CHU", "I-CHU", "B-PAG", "I-PAG", "B-BEA", "I-BEA", "B-WAR", "I-WAR", "B-WAT", "I-WAT", "B-SA", "I-SA", "B-SER", "I-SER", "B-STR", "I-STR", "B-NUN", "I-NUN", "B-PAL", "I-PAL", "B-VOL", "I-VOL", "B-HIL", "I-HIL", "B-MAR", "I-MAR", "B-VAL", "I-VAL", "B-PROD", "I-PROD", "B-DIS", "I-DIS", "B-FOO", "I-FOO", "B-DISH", "I-DISH", "B-DRI", "I-DRI"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f012659d18b3dc5fe01318aa61a647115c0ae33c890050c5a5e9b758b656649
3
+ size 431168241
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "C:\\Users\\Admin/.cache\\huggingface\\transformers\\226a307193a9f4344264cdc76a12988448a25345ba172f2c7421f3b6810fddad.3dab63143af66769bbb35e3811f75f7e16b2320e12b7935e216bd6159ce6d9a6", "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45eac75582c4587bc90f5575cfb414119bcbb0764b7ee5606b41c94ee668ddd2
3
+ size 3695
vocab.txt ADDED
The diff for this file is too large to render. See raw diff