update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: gpl-3.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: bert-base-chinese-ws-finetuned-ner_all
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# bert-base-chinese-ws-finetuned-ner_all
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [ckiplab/bert-base-chinese-ws](https://huggingface.co/ckiplab/bert-base-chinese-ws) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.0330
|
23 |
+
- Precision: 0.9723
|
24 |
+
- Recall: 0.9734
|
25 |
+
- F1: 0.9728
|
26 |
+
- Accuracy: 0.9879
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 1e-05
|
46 |
+
- train_batch_size: 18
|
47 |
+
- eval_batch_size: 18
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 3
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
57 |
+
| 0.0648 | 0.29 | 500 | 0.0524 | 0.9586 | 0.9572 | 0.9579 | 0.9813 |
|
58 |
+
| 0.0509 | 0.59 | 1000 | 0.0460 | 0.9615 | 0.9628 | 0.9622 | 0.9832 |
|
59 |
+
| 0.0478 | 0.88 | 1500 | 0.0429 | 0.9624 | 0.9660 | 0.9642 | 0.9840 |
|
60 |
+
| 0.0417 | 1.17 | 2000 | 0.0409 | 0.9650 | 0.9680 | 0.9665 | 0.9851 |
|
61 |
+
| 0.0402 | 1.47 | 2500 | 0.0387 | 0.9662 | 0.9693 | 0.9677 | 0.9856 |
|
62 |
+
| 0.0378 | 1.76 | 3000 | 0.0359 | 0.9699 | 0.9717 | 0.9708 | 0.9869 |
|
63 |
+
| 0.0385 | 2.05 | 3500 | 0.0353 | 0.9703 | 0.9718 | 0.9710 | 0.9871 |
|
64 |
+
| 0.0337 | 2.34 | 4000 | 0.0341 | 0.9709 | 0.9731 | 0.9720 | 0.9875 |
|
65 |
+
| 0.0348 | 2.64 | 4500 | 0.0333 | 0.9721 | 0.9733 | 0.9727 | 0.9878 |
|
66 |
+
| 0.0346 | 2.93 | 5000 | 0.0331 | 0.9722 | 0.9735 | 0.9729 | 0.9879 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.13.0
|
72 |
+
- Pytorch 1.8.0+cu111
|
73 |
+
- Datasets 2.4.0
|
74 |
+
- Tokenizers 0.10.3
|