Update README.md
Browse files
README.md
CHANGED
@@ -11,14 +11,25 @@ metrics:
|
|
11 |
model-index:
|
12 |
- name: distilbert-base-uncased-finetuned-FiNER
|
13 |
results: []
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
|
16 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
-
should probably proofread and complete it, then remove this comment. -->
|
18 |
-
|
19 |
# distilbert-base-uncased-finetuned-FiNER
|
20 |
|
21 |
-
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 0.0336
|
24 |
- Precision: 0.9154
|
@@ -26,20 +37,28 @@ It achieves the following results on the evaluation set:
|
|
26 |
- F1: 0.9240
|
27 |
- Accuracy: 0.9917
|
28 |
|
|
|
29 |
## Model description
|
30 |
|
31 |
-
|
32 |
|
33 |
## Intended uses & limitations
|
34 |
|
35 |
-
|
36 |
|
37 |
## Training and evaluation data
|
38 |
|
39 |
-
|
|
|
|
|
|
|
|
|
|
|
40 |
|
41 |
## Training procedure
|
42 |
|
|
|
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
@@ -68,4 +87,4 @@ The following hyperparameters were used during training:
|
|
68 |
- Transformers 4.38.2
|
69 |
- Pytorch 2.2.1+cu121
|
70 |
- Datasets 2.18.0
|
71 |
-
- Tokenizers 0.15.2
|
|
|
11 |
model-index:
|
12 |
- name: distilbert-base-uncased-finetuned-FiNER
|
13 |
results: []
|
14 |
+
datasets:
|
15 |
+
- nlpaueb/finer-139
|
16 |
+
language:
|
17 |
+
- en
|
18 |
+
pipeline_tag: token-classification
|
19 |
---
|
20 |
|
|
|
|
|
|
|
21 |
# distilbert-base-uncased-finetuned-FiNER
|
22 |
|
23 |
+
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) trained on a subset of the [nlpaueb/finer-139](https://huggingface.co/datasets/nlpaueb/finer-139) dataset.
|
24 |
+
The subset is generated by filtering the dataset to contain only samples with at least one of the following NER tags:
|
25 |
+
* 'O',
|
26 |
+
* 'B-DebtInstrumentBasisSpreadOnVariableRate1',
|
27 |
+
* 'B-DebtInstrumentFaceAmount',
|
28 |
+
* 'B-LineOfCreditFacilityMaximumBorrowingCapacity',
|
29 |
+
* 'B-DebtInstrumentInterestRateStatedPercentage'
|
30 |
+
|
31 |
+
Then, it was fine-tuned to detect only the afforementioned 4 tags (plus other "O")
|
32 |
+
|
33 |
It achieves the following results on the evaluation set:
|
34 |
- Loss: 0.0336
|
35 |
- Precision: 0.9154
|
|
|
37 |
- F1: 0.9240
|
38 |
- Accuracy: 0.9917
|
39 |
|
40 |
+
|
41 |
## Model description
|
42 |
|
43 |
+
Model based on [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) with all default parameters.
|
44 |
|
45 |
## Intended uses & limitations
|
46 |
|
47 |
+
The model published here was trained for demo purposes only.
|
48 |
|
49 |
## Training and evaluation data
|
50 |
|
51 |
+
Original train/validation/test splits from [nlpaueb/finer-139](https://huggingface.co/datasets/nlpaueb/finer-139), after filtering for samples containing at least one of the following NER tags:
|
52 |
+
* 'O',
|
53 |
+
* 'B-DebtInstrumentBasisSpreadOnVariableRate1',
|
54 |
+
* 'B-DebtInstrumentFaceAmount',
|
55 |
+
* 'B-LineOfCreditFacilityMaximumBorrowingCapacity',
|
56 |
+
* 'B-DebtInstrumentInterestRateStatedPercentage'
|
57 |
|
58 |
## Training procedure
|
59 |
|
60 |
+
|
61 |
+
|
62 |
### Training hyperparameters
|
63 |
|
64 |
The following hyperparameters were used during training:
|
|
|
87 |
- Transformers 4.38.2
|
88 |
- Pytorch 2.2.1+cu121
|
89 |
- Datasets 2.18.0
|
90 |
+
- Tokenizers 0.15.2
|