judithrosell
commited on
Commit
•
df725a1
1
Parent(s):
a3c405f
Training in progress epoch 0
Browse files- README.md +53 -0
- added_tokens.json +7 -0
- config.json +147 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: dmis-lab/biobert-v1.1
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: judithrosell/biobert-ft-ner
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# judithrosell/biobert-ft-ner
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.4049
|
18 |
+
- Validation Loss: 0.3010
|
19 |
+
- Epoch: 0
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 23335, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
39 |
+
- training_precision: mixed_float16
|
40 |
+
|
41 |
+
### Training results
|
42 |
+
|
43 |
+
| Train Loss | Validation Loss | Epoch |
|
44 |
+
|:----------:|:---------------:|:-----:|
|
45 |
+
| 0.4049 | 0.3010 | 0 |
|
46 |
+
|
47 |
+
|
48 |
+
### Framework versions
|
49 |
+
|
50 |
+
- Transformers 4.34.0
|
51 |
+
- TensorFlow 2.13.0
|
52 |
+
- Datasets 2.14.5
|
53 |
+
- Tokenizers 0.14.1
|
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CLS]": 101,
|
3 |
+
"[MASK]": 103,
|
4 |
+
"[PAD]": 0,
|
5 |
+
"[SEP]": 102,
|
6 |
+
"[UNK]": 100
|
7 |
+
}
|
config.json
ADDED
@@ -0,0 +1,147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dmis-lab/biobert-v1.1",
|
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": "I-Disease",
|
14 |
+
"1": "B-SO",
|
15 |
+
"2": "B-Pathological_formation",
|
16 |
+
"3": "B-Immaterial_anatomical_entity",
|
17 |
+
"4": "B-Amino_acid",
|
18 |
+
"5": "I-GO",
|
19 |
+
"6": "B-cell_line",
|
20 |
+
"7": "I-cell_line",
|
21 |
+
"8": "B-Anatomical_system",
|
22 |
+
"9": "I-CL",
|
23 |
+
"10": "I-Tissue",
|
24 |
+
"11": "I-Organism_subdivision",
|
25 |
+
"12": "I-GGP",
|
26 |
+
"13": "I-cell_type",
|
27 |
+
"14": "I-Pathological_formation",
|
28 |
+
"15": "B-Gene_or_gene_product",
|
29 |
+
"16": "B-Organism",
|
30 |
+
"17": "I-Anatomical_system",
|
31 |
+
"18": "B-Organism_subdivision",
|
32 |
+
"19": "B-Chemical",
|
33 |
+
"20": "B-Tissue",
|
34 |
+
"21": "I-RNA",
|
35 |
+
"22": "O",
|
36 |
+
"23": "I-Organism",
|
37 |
+
"24": "B-Taxon",
|
38 |
+
"25": "B-Multi-tissue_structure",
|
39 |
+
"26": "I-Cellular_component",
|
40 |
+
"27": "I-protein",
|
41 |
+
"28": "B-Simple_chemical",
|
42 |
+
"29": "B-Organ",
|
43 |
+
"30": "I-SO",
|
44 |
+
"31": "B-protein",
|
45 |
+
"32": "I-Taxon",
|
46 |
+
"33": "B-Cancer",
|
47 |
+
"34": "I-Gene_or_gene_product",
|
48 |
+
"35": "B-CHEBI",
|
49 |
+
"36": "I-Multi-tissue_structure",
|
50 |
+
"37": "B-cell_type",
|
51 |
+
"38": "I-DNA",
|
52 |
+
"39": "I-Simple_chemical",
|
53 |
+
"40": "I-Organism_substance",
|
54 |
+
"41": "I-Organ",
|
55 |
+
"42": "I-Cancer",
|
56 |
+
"43": "B-Disease",
|
57 |
+
"44": "B-GO",
|
58 |
+
"45": "I-CHEBI",
|
59 |
+
"46": "B-Developing_anatomical_structure",
|
60 |
+
"47": "I-Immaterial_anatomical_entity",
|
61 |
+
"48": "I-Amino_acid",
|
62 |
+
"49": "B-RNA",
|
63 |
+
"50": "I-Cell",
|
64 |
+
"51": "B-GGP",
|
65 |
+
"52": "B-Cellular_component",
|
66 |
+
"53": "I-Developing_anatomical_structure",
|
67 |
+
"54": "I-Chemical",
|
68 |
+
"55": "B-CL",
|
69 |
+
"56": "B-Organism_substance",
|
70 |
+
"57": "B-Cell",
|
71 |
+
"58": "B-DNA"
|
72 |
+
},
|
73 |
+
"initializer_range": 0.02,
|
74 |
+
"intermediate_size": 3072,
|
75 |
+
"label2id": {
|
76 |
+
"B-Amino_acid": 4,
|
77 |
+
"B-Anatomical_system": 8,
|
78 |
+
"B-CHEBI": 35,
|
79 |
+
"B-CL": 55,
|
80 |
+
"B-Cancer": 33,
|
81 |
+
"B-Cell": 57,
|
82 |
+
"B-Cellular_component": 52,
|
83 |
+
"B-Chemical": 19,
|
84 |
+
"B-DNA": 58,
|
85 |
+
"B-Developing_anatomical_structure": 46,
|
86 |
+
"B-Disease": 43,
|
87 |
+
"B-GGP": 51,
|
88 |
+
"B-GO": 44,
|
89 |
+
"B-Gene_or_gene_product": 15,
|
90 |
+
"B-Immaterial_anatomical_entity": 3,
|
91 |
+
"B-Multi-tissue_structure": 25,
|
92 |
+
"B-Organ": 29,
|
93 |
+
"B-Organism": 16,
|
94 |
+
"B-Organism_subdivision": 18,
|
95 |
+
"B-Organism_substance": 56,
|
96 |
+
"B-Pathological_formation": 2,
|
97 |
+
"B-RNA": 49,
|
98 |
+
"B-SO": 1,
|
99 |
+
"B-Simple_chemical": 28,
|
100 |
+
"B-Taxon": 24,
|
101 |
+
"B-Tissue": 20,
|
102 |
+
"B-cell_line": 6,
|
103 |
+
"B-cell_type": 37,
|
104 |
+
"B-protein": 31,
|
105 |
+
"I-Amino_acid": 48,
|
106 |
+
"I-Anatomical_system": 17,
|
107 |
+
"I-CHEBI": 45,
|
108 |
+
"I-CL": 9,
|
109 |
+
"I-Cancer": 42,
|
110 |
+
"I-Cell": 50,
|
111 |
+
"I-Cellular_component": 26,
|
112 |
+
"I-Chemical": 54,
|
113 |
+
"I-DNA": 38,
|
114 |
+
"I-Developing_anatomical_structure": 53,
|
115 |
+
"I-Disease": 0,
|
116 |
+
"I-GGP": 12,
|
117 |
+
"I-GO": 5,
|
118 |
+
"I-Gene_or_gene_product": 34,
|
119 |
+
"I-Immaterial_anatomical_entity": 47,
|
120 |
+
"I-Multi-tissue_structure": 36,
|
121 |
+
"I-Organ": 41,
|
122 |
+
"I-Organism": 23,
|
123 |
+
"I-Organism_subdivision": 11,
|
124 |
+
"I-Organism_substance": 40,
|
125 |
+
"I-Pathological_formation": 14,
|
126 |
+
"I-RNA": 21,
|
127 |
+
"I-SO": 30,
|
128 |
+
"I-Simple_chemical": 39,
|
129 |
+
"I-Taxon": 32,
|
130 |
+
"I-Tissue": 10,
|
131 |
+
"I-cell_line": 7,
|
132 |
+
"I-cell_type": 13,
|
133 |
+
"I-protein": 27,
|
134 |
+
"O": 22
|
135 |
+
},
|
136 |
+
"layer_norm_eps": 1e-12,
|
137 |
+
"max_position_embeddings": 512,
|
138 |
+
"model_type": "bert",
|
139 |
+
"num_attention_heads": 12,
|
140 |
+
"num_hidden_layers": 12,
|
141 |
+
"pad_token_id": 0,
|
142 |
+
"position_embedding_type": "absolute",
|
143 |
+
"transformers_version": "4.34.0",
|
144 |
+
"type_vocab_size": 2,
|
145 |
+
"use_cache": true,
|
146 |
+
"vocab_size": 28996
|
147 |
+
}
|
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 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2244c62876b9491d67d18b3fcd8c3673ea8fd28205184afa6210ff8d008824a9
|
3 |
+
size 431333556
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_basic_tokenize": true,
|
48 |
+
"do_lower_case": false,
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|