update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- f1
|
6 |
+
model-index:
|
7 |
+
- name: bert-base-chinese-finetuned-split
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# bert-base-chinese-finetuned-split
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0149
|
19 |
+
- F1: 1.0
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 14
|
40 |
+
- eval_batch_size: 14
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 20
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
50 |
+
| 3.9187 | 1.0 | 1 | 2.0505 | 0.0 |
|
51 |
+
| 2.1256 | 2.0 | 2 | 1.0335 | 0.0 |
|
52 |
+
| 1.1829 | 3.0 | 3 | 0.5776 | 0.0 |
|
53 |
+
| 0.6385 | 4.0 | 4 | 0.4856 | 0.0 |
|
54 |
+
| 0.5098 | 5.0 | 5 | 0.3884 | 0.0 |
|
55 |
+
| 0.4158 | 6.0 | 6 | 0.2813 | 0.0 |
|
56 |
+
| 0.3302 | 7.0 | 7 | 0.2339 | 0.0 |
|
57 |
+
| 0.2741 | 8.0 | 8 | 0.2079 | 0.7826 |
|
58 |
+
| 0.2314 | 9.0 | 9 | 0.1601 | 0.7826 |
|
59 |
+
| 0.2039 | 10.0 | 10 | 0.1188 | 0.7826 |
|
60 |
+
| 0.1463 | 11.0 | 11 | 0.0897 | 0.88 |
|
61 |
+
| 0.1364 | 12.0 | 12 | 0.0639 | 0.9231 |
|
62 |
+
| 0.1028 | 13.0 | 13 | 0.0473 | 1.0 |
|
63 |
+
| 0.0787 | 14.0 | 14 | 0.0404 | 1.0 |
|
64 |
+
| 0.0555 | 15.0 | 15 | 0.0333 | 1.0 |
|
65 |
+
| 0.047 | 16.0 | 16 | 0.0251 | 1.0 |
|
66 |
+
| 0.039 | 17.0 | 17 | 0.0199 | 1.0 |
|
67 |
+
| 0.0386 | 18.0 | 18 | 0.0174 | 1.0 |
|
68 |
+
| 0.026 | 19.0 | 19 | 0.0159 | 1.0 |
|
69 |
+
| 0.0268 | 20.0 | 20 | 0.0149 | 1.0 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.18.0
|
75 |
+
- Pytorch 1.12.0+cu102
|
76 |
+
- Datasets 1.18.4
|
77 |
+
- Tokenizers 0.12.1
|