tommitt commited on
Commit
c53fb23
·
verified ·
1 Parent(s): c394092

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -7
README.md CHANGED
@@ -10,16 +10,19 @@ metrics:
10
  - f1
11
  - accuracy
12
  model-index:
13
- - name: test-ner
14
  results: []
 
 
 
 
15
  ---
16
 
17
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
- should probably proofread and complete it, then remove this comment. -->
19
-
20
  # financial_bert
21
 
22
- This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 
 
23
  It achieves the following results on the evaluation set:
24
  - Loss: 0.0201
25
  - Precision: 0.7977
@@ -37,7 +40,25 @@ More information needed
37
 
38
  ## Training and evaluation data
39
 
40
- More information needed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
 
42
  ## Training procedure
43
 
@@ -61,4 +82,4 @@ The following hyperparameters were used during training:
61
  - Transformers 4.48.0.dev0
62
  - Pytorch 2.5.1
63
  - Datasets 3.1.0
64
- - Tokenizers 0.21.0
 
10
  - f1
11
  - accuracy
12
  model-index:
13
+ - name: whataboutyou-ai/financial_bert
14
  results: []
15
+ language:
16
+ - en
17
+ datasets:
18
+ - expertai/BUSTER
19
  ---
20
 
 
 
 
21
  # financial_bert
22
 
23
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the [BUSTER](https://huggingface.co/datasets/expertai/BUSTER) dataset.
24
+ This model is ready to use for **Named Entity Recognition** (NER).
25
+
26
  It achieves the following results on the evaluation set:
27
  - Loss: 0.0201
28
  - Precision: 0.7977
 
40
 
41
  ## Training and evaluation data
42
 
43
+ This model was fine-tuned on the [BUSTER](https://huggingface.co/datasets/expertai/BUSTER) dataset.
44
+
45
+ The training dataset distinguishes between the beginning and continuation of an entity so that if there are back-to-back entities of the same type, the model can output where the second entity begins. As in the dataset, each token will be classified as one of the following classes:
46
+
47
+ Entity|Description
48
+ -|-
49
+ O|Outside of a named entity
50
+ B-Generic_Info.ANNUAL_REVENUES|Beginning of annual revenues entity
51
+ I-Generic_Info.ANNUAL_REVENUES|Continuation of annual revenues entity
52
+ B-Parties.ACQUIRED_COMPANY|Beginning of acquired company entity
53
+ I-Parties.ACQUIRED_COMPANY|Continuation of acquired company entity
54
+ B-Parties.BUYING_COMPANY|Beginning of buying company entity
55
+ I-Parties.BUYING_COMPANY|Continuation of buying company entity
56
+ B-Parties.SELLING_COMPANY|Beginning of selling company entity
57
+ I-Parties.SELLING_COMPANY|Continuation of selling company entity
58
+ B-Advisors.GENERIC_CONSULTING_COMPANY|Beginning of generic consulting company entity
59
+ I-Advisors.GENERIC_CONSULTING_COMPANY|Continuation of generic consulting company entity
60
+ B-Advisors.LEGAL_CONSULTING_COMPANY|Beginning of legal consulting company entity
61
+ I-Advisors.LEGAL_CONSULTING_COMPANY|Continuation of legal consulting company entity
62
 
63
  ## Training procedure
64
 
 
82
  - Transformers 4.48.0.dev0
83
  - Pytorch 2.5.1
84
  - Datasets 3.1.0
85
+ - Tokenizers 0.21.0