Commit
•
203c545
1
Parent(s):
163dac1
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- conll2003
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
+
model-index:
|
13 |
+
- name: bert-finetuned-ner
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Token Classification
|
17 |
+
type: token-classification
|
18 |
+
dataset:
|
19 |
+
name: conll2003
|
20 |
+
type: conll2003
|
21 |
+
config: conll2003
|
22 |
+
split: validation
|
23 |
+
args: conll2003
|
24 |
+
metrics:
|
25 |
+
- name: Precision
|
26 |
+
type: precision
|
27 |
+
value: 0.9341059602649007
|
28 |
+
- name: Recall
|
29 |
+
type: recall
|
30 |
+
value: 0.9495119488387749
|
31 |
+
- name: F1
|
32 |
+
type: f1
|
33 |
+
value: 0.941745952261726
|
34 |
+
- name: Accuracy
|
35 |
+
type: accuracy
|
36 |
+
value: 0.9862689115205746
|
37 |
+
---
|
38 |
+
|
39 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
40 |
+
should probably proofread and complete it, then remove this comment. -->
|
41 |
+
|
42 |
+
# bert-finetuned-ner
|
43 |
+
|
44 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
|
45 |
+
It achieves the following results on the evaluation set:
|
46 |
+
- Loss: 0.0609
|
47 |
+
- Precision: 0.9341
|
48 |
+
- Recall: 0.9495
|
49 |
+
- F1: 0.9417
|
50 |
+
- Accuracy: 0.9863
|
51 |
+
|
52 |
+
## Model description
|
53 |
+
|
54 |
+
More information needed
|
55 |
+
|
56 |
+
## Intended uses & limitations
|
57 |
+
|
58 |
+
More information needed
|
59 |
+
|
60 |
+
## Training and evaluation data
|
61 |
+
|
62 |
+
More information needed
|
63 |
+
|
64 |
+
## Training procedure
|
65 |
+
|
66 |
+
### Training hyperparameters
|
67 |
+
|
68 |
+
The following hyperparameters were used during training:
|
69 |
+
- learning_rate: 2e-05
|
70 |
+
- train_batch_size: 8
|
71 |
+
- eval_batch_size: 8
|
72 |
+
- seed: 42
|
73 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
74 |
+
- lr_scheduler_type: linear
|
75 |
+
- num_epochs: 3
|
76 |
+
|
77 |
+
### Training results
|
78 |
+
|
79 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
80 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
81 |
+
| 0.0905 | 1.0 | 1756 | 0.0761 | 0.9081 | 0.9241 | 0.9160 | 0.9802 |
|
82 |
+
| 0.0353 | 2.0 | 3512 | 0.0606 | 0.9219 | 0.9478 | 0.9347 | 0.9860 |
|
83 |
+
| 0.0175 | 3.0 | 5268 | 0.0609 | 0.9341 | 0.9495 | 0.9417 | 0.9863 |
|
84 |
+
|
85 |
+
|
86 |
+
### Framework versions
|
87 |
+
|
88 |
+
- Transformers 4.30.2
|
89 |
+
- Pytorch 2.0.1+cu118
|
90 |
+
- Datasets 2.13.1
|
91 |
+
- Tokenizers 0.13.3
|