TiffanyTiffany
commited on
Commit
•
07dbe5b
1
Parent(s):
a549ded
update model card README.md
Browse files
README.md
CHANGED
@@ -1,13 +1,38 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
-
base_model: bert-base-cased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
-
-
|
|
|
|
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: bert-finetuned-ner
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,7 +40,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# bert-finetuned-ner
|
17 |
|
18 |
-
This model
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -42,9 +73,18 @@ The following hyperparameters were used during training:
|
|
42 |
- lr_scheduler_type: linear
|
43 |
- num_epochs: 3
|
44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
### Framework versions
|
46 |
|
47 |
-
- Transformers 4.
|
48 |
-
- Pytorch 2.0.1
|
49 |
-
- Datasets 2.
|
50 |
-
- Tokenizers 0.13.
|
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
5 |
+
- wnut_17
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
model-index:
|
12 |
- name: bert-finetuned-ner
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Token Classification
|
16 |
+
type: token-classification
|
17 |
+
dataset:
|
18 |
+
name: wnut_17
|
19 |
+
type: wnut_17
|
20 |
+
config: wnut_17
|
21 |
+
split: validation
|
22 |
+
args: wnut_17
|
23 |
+
metrics:
|
24 |
+
- name: Precision
|
25 |
+
type: precision
|
26 |
+
value: 0.6274509803921569
|
27 |
+
- name: Recall
|
28 |
+
type: recall
|
29 |
+
value: 0.49760765550239233
|
30 |
+
- name: F1
|
31 |
+
type: f1
|
32 |
+
value: 0.5550366911274184
|
33 |
+
- name: Accuracy
|
34 |
+
type: accuracy
|
35 |
+
value: 0.9333784769246797
|
36 |
---
|
37 |
|
38 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
40 |
|
41 |
# bert-finetuned-ner
|
42 |
|
43 |
+
This model was trained from scratch on the wnut_17 dataset.
|
44 |
+
It achieves the following results on the evaluation set:
|
45 |
+
- Loss: 0.4590
|
46 |
+
- Precision: 0.6275
|
47 |
+
- Recall: 0.4976
|
48 |
+
- F1: 0.5550
|
49 |
+
- Accuracy: 0.9334
|
50 |
|
51 |
## Model description
|
52 |
|
|
|
73 |
- lr_scheduler_type: linear
|
74 |
- num_epochs: 3
|
75 |
|
76 |
+
### Training results
|
77 |
+
|
78 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
79 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
80 |
+
| No log | 1.0 | 425 | 0.4576 | 0.6556 | 0.4713 | 0.5484 | 0.9321 |
|
81 |
+
| 0.0403 | 2.0 | 850 | 0.4647 | 0.6293 | 0.4629 | 0.5334 | 0.9311 |
|
82 |
+
| 0.0227 | 3.0 | 1275 | 0.4590 | 0.6275 | 0.4976 | 0.5550 | 0.9334 |
|
83 |
+
|
84 |
+
|
85 |
### Framework versions
|
86 |
|
87 |
+
- Transformers 4.27.0.dev0
|
88 |
+
- Pytorch 2.0.1
|
89 |
+
- Datasets 2.12.0
|
90 |
+
- Tokenizers 0.13.2
|