vineetsharma commited on
Commit
78e90f0
1 Parent(s): 6f0f066

Training complete

Browse files
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: BioMedical_NER-maccrobat-bert
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # BioMedical_NER-maccrobat-bert
15
+
16
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 2e-05
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 15
42
+
43
+ ### Framework versions
44
+
45
+ - Transformers 4.32.1
46
+ - Pytorch 2.0.1+cu118
47
+ - Datasets 2.14.4
48
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-Activity",
15
+ "2": "B-Administration",
16
+ "3": "B-Age",
17
+ "4": "B-Area",
18
+ "5": "B-Biological_attribute",
19
+ "6": "B-Biological_structure",
20
+ "7": "B-Clinical_event",
21
+ "8": "B-Color",
22
+ "9": "B-Coreference",
23
+ "10": "B-Date",
24
+ "11": "B-Detailed_description",
25
+ "12": "B-Diagnostic_procedure",
26
+ "13": "B-Disease_disorder",
27
+ "14": "B-Distance",
28
+ "15": "B-Dosage",
29
+ "16": "B-Duration",
30
+ "17": "B-Family_history",
31
+ "18": "B-Frequency",
32
+ "19": "B-Height",
33
+ "20": "B-History",
34
+ "21": "B-Lab_value",
35
+ "22": "B-Mass",
36
+ "23": "B-Medication",
37
+ "24": "B-Nonbiological_location",
38
+ "25": "B-Occupation",
39
+ "26": "B-Other_entity",
40
+ "27": "B-Other_event",
41
+ "28": "B-Outcome",
42
+ "29": "B-Personal_background",
43
+ "30": "B-Qualitative_concept",
44
+ "31": "B-Quantitative_concept",
45
+ "32": "B-Severity",
46
+ "33": "B-Sex",
47
+ "34": "B-Shape",
48
+ "35": "B-Sign_symptom",
49
+ "36": "B-Subject",
50
+ "37": "B-Texture",
51
+ "38": "B-Therapeutic_procedure",
52
+ "39": "B-Time",
53
+ "40": "B-Volume",
54
+ "41": "B-Weight",
55
+ "42": "I-Activity",
56
+ "43": "I-Administration",
57
+ "44": "I-Age",
58
+ "45": "I-Area",
59
+ "46": "I-Biological_attribute",
60
+ "47": "I-Biological_structure",
61
+ "48": "I-Clinical_event",
62
+ "49": "I-Color",
63
+ "50": "I-Coreference",
64
+ "51": "I-Date",
65
+ "52": "I-Detailed_description",
66
+ "53": "I-Diagnostic_procedure",
67
+ "54": "I-Disease_disorder",
68
+ "55": "I-Distance",
69
+ "56": "I-Dosage",
70
+ "57": "I-Duration",
71
+ "58": "I-Family_history",
72
+ "59": "I-Frequency",
73
+ "60": "I-Height",
74
+ "61": "I-History",
75
+ "62": "I-Lab_value",
76
+ "63": "I-Mass",
77
+ "64": "I-Medication",
78
+ "65": "I-Nonbiological_location",
79
+ "66": "I-Occupation",
80
+ "67": "I-Other_entity",
81
+ "68": "I-Other_event",
82
+ "69": "I-Outcome",
83
+ "70": "I-Personal_background",
84
+ "71": "I-Qualitative_concept",
85
+ "72": "I-Quantitative_concept",
86
+ "73": "I-Severity",
87
+ "74": "I-Shape",
88
+ "75": "I-Sign_symptom",
89
+ "76": "I-Subject",
90
+ "77": "I-Texture",
91
+ "78": "I-Therapeutic_procedure",
92
+ "79": "I-Time",
93
+ "80": "I-Volume",
94
+ "81": "I-Weight"
95
+ },
96
+ "initializer_range": 0.02,
97
+ "intermediate_size": 3072,
98
+ "label2id": {
99
+ "B-Activity": 1,
100
+ "B-Administration": 2,
101
+ "B-Age": 3,
102
+ "B-Area": 4,
103
+ "B-Biological_attribute": 5,
104
+ "B-Biological_structure": 6,
105
+ "B-Clinical_event": 7,
106
+ "B-Color": 8,
107
+ "B-Coreference": 9,
108
+ "B-Date": 10,
109
+ "B-Detailed_description": 11,
110
+ "B-Diagnostic_procedure": 12,
111
+ "B-Disease_disorder": 13,
112
+ "B-Distance": 14,
113
+ "B-Dosage": 15,
114
+ "B-Duration": 16,
115
+ "B-Family_history": 17,
116
+ "B-Frequency": 18,
117
+ "B-Height": 19,
118
+ "B-History": 20,
119
+ "B-Lab_value": 21,
120
+ "B-Mass": 22,
121
+ "B-Medication": 23,
122
+ "B-Nonbiological_location": 24,
123
+ "B-Occupation": 25,
124
+ "B-Other_entity": 26,
125
+ "B-Other_event": 27,
126
+ "B-Outcome": 28,
127
+ "B-Personal_background": 29,
128
+ "B-Qualitative_concept": 30,
129
+ "B-Quantitative_concept": 31,
130
+ "B-Severity": 32,
131
+ "B-Sex": 33,
132
+ "B-Shape": 34,
133
+ "B-Sign_symptom": 35,
134
+ "B-Subject": 36,
135
+ "B-Texture": 37,
136
+ "B-Therapeutic_procedure": 38,
137
+ "B-Time": 39,
138
+ "B-Volume": 40,
139
+ "B-Weight": 41,
140
+ "I-Activity": 42,
141
+ "I-Administration": 43,
142
+ "I-Age": 44,
143
+ "I-Area": 45,
144
+ "I-Biological_attribute": 46,
145
+ "I-Biological_structure": 47,
146
+ "I-Clinical_event": 48,
147
+ "I-Color": 49,
148
+ "I-Coreference": 50,
149
+ "I-Date": 51,
150
+ "I-Detailed_description": 52,
151
+ "I-Diagnostic_procedure": 53,
152
+ "I-Disease_disorder": 54,
153
+ "I-Distance": 55,
154
+ "I-Dosage": 56,
155
+ "I-Duration": 57,
156
+ "I-Family_history": 58,
157
+ "I-Frequency": 59,
158
+ "I-Height": 60,
159
+ "I-History": 61,
160
+ "I-Lab_value": 62,
161
+ "I-Mass": 63,
162
+ "I-Medication": 64,
163
+ "I-Nonbiological_location": 65,
164
+ "I-Occupation": 66,
165
+ "I-Other_entity": 67,
166
+ "I-Other_event": 68,
167
+ "I-Outcome": 69,
168
+ "I-Personal_background": 70,
169
+ "I-Qualitative_concept": 71,
170
+ "I-Quantitative_concept": 72,
171
+ "I-Severity": 73,
172
+ "I-Shape": 74,
173
+ "I-Sign_symptom": 75,
174
+ "I-Subject": 76,
175
+ "I-Texture": 77,
176
+ "I-Therapeutic_procedure": 78,
177
+ "I-Time": 79,
178
+ "I-Volume": 80,
179
+ "I-Weight": 81,
180
+ "O": 0
181
+ },
182
+ "layer_norm_eps": 1e-12,
183
+ "max_position_embeddings": 512,
184
+ "model_type": "bert",
185
+ "num_attention_heads": 12,
186
+ "num_hidden_layers": 12,
187
+ "pad_token_id": 0,
188
+ "position_embedding_type": "absolute",
189
+ "torch_dtype": "float32",
190
+ "transformers_version": "4.32.1",
191
+ "type_vocab_size": 2,
192
+ "use_cache": true,
193
+ "vocab_size": 30522
194
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304055f10bff806baaea13c43dbe2455eda95895ea29e334097ce4cf47fb1d72
3
+ size 435886569
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3f1ccb98c59c6d18d2f6accd413fdbfa5035035e98fb2074ba57d41337c952
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff