Update README.md
Browse files- README.md +12 -25
- training_args.bin +1 -1
README.md
CHANGED
@@ -25,16 +25,16 @@ model-index:
|
|
25 |
metrics:
|
26 |
- name: Precision
|
27 |
type: precision
|
28 |
-
value: 0.
|
29 |
- name: Recall
|
30 |
type: recall
|
31 |
-
value: 0.
|
32 |
- name: F1
|
33 |
type: f1
|
34 |
-
value: 0.
|
35 |
- name: Accuracy
|
36 |
type: accuracy
|
37 |
-
value: 0.
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -42,25 +42,21 @@ should probably proofread and complete it, then remove this comment. -->
|
|
42 |
|
43 |
# bert-base-chinese-finetuned-ner
|
44 |
|
45 |
-
This model is a fine-tuned version of [Danielwei0214/bert-base-chinese-finetuned-ner](https://huggingface.co/Danielwei0214/bert-base-chinese-finetuned-ner) on the gyr66/privacy_detection dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
-
- Loss: 0.
|
48 |
-
- Precision: 0.
|
49 |
-
- Recall: 0.
|
50 |
-
- F1: 0.
|
51 |
-
- Accuracy: 0.
|
52 |
|
53 |
## Model description
|
54 |
|
55 |
-
|
56 |
-
|
57 |
-
## Intended uses & limitations
|
58 |
-
|
59 |
-
More information needed
|
60 |
|
61 |
## Training and evaluation data
|
62 |
|
63 |
-
|
64 |
|
65 |
## Training procedure
|
66 |
|
@@ -73,15 +69,6 @@ The following hyperparameters were used during training:
|
|
73 |
- seed: 42
|
74 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
- lr_scheduler_type: linear
|
76 |
-
- num_epochs: 3
|
77 |
-
|
78 |
-
### Training results
|
79 |
-
|
80 |
-
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
-
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
82 |
-
| 1.3112 | 1.0 | 36 | 0.7305 | 0.2062 | 0.2535 | 0.2274 | 0.8028 |
|
83 |
-
| 0.6083 | 2.0 | 72 | 0.5295 | 0.3598 | 0.4668 | 0.4064 | 0.8451 |
|
84 |
-
| 0.4782 | 3.0 | 108 | 0.4895 | 0.3840 | 0.5055 | 0.4365 | 0.8564 |
|
85 |
|
86 |
|
87 |
### Framework versions
|
|
|
25 |
metrics:
|
26 |
- name: Precision
|
27 |
type: precision
|
28 |
+
value: 0.65322
|
29 |
- name: Recall
|
30 |
type: recall
|
31 |
+
value: 0.74169
|
32 |
- name: F1
|
33 |
type: f1
|
34 |
+
value: 0.69465
|
35 |
- name: Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.90517
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
42 |
|
43 |
# bert-base-chinese-finetuned-ner
|
44 |
|
45 |
+
This model is a fine-tuned version of [Danielwei0214/bert-base-chinese-finetuned-ner](https://huggingface.co/Danielwei0214/bert-base-chinese-finetuned-ner) on the [gyr66/privacy_detection](https://huggingface.co/datasets/gyr66/privacy_detection) dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.7929
|
48 |
+
- Precision: 0.6532
|
49 |
+
- Recall: 0.7417
|
50 |
+
- F1: 0.6947
|
51 |
+
- Accuracy: 0.9052
|
52 |
|
53 |
## Model description
|
54 |
|
55 |
+
The model is used for competition: "https://www.datafountain.cn/competitions/472"
|
|
|
|
|
|
|
|
|
56 |
|
57 |
## Training and evaluation data
|
58 |
|
59 |
+
The training and evaluation data is from [gyr66/privacy_detection](https://huggingface.co/datasets/gyr66/privacy_detection) dataset.
|
60 |
|
61 |
## Training procedure
|
62 |
|
|
|
69 |
- seed: 42
|
70 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
71 |
- lr_scheduler_type: linear
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
|
73 |
|
74 |
### Framework versions
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3579
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a750e4818a90b3fd65d4ad00682e03bb2d43465356e4102cb81673e48bb44cfd
|
3 |
size 3579
|