Commit
•
cb22fbc
1
Parent(s):
10c368e
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- precision
|
6 |
+
- recall
|
7 |
+
- f1
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: bert_chinese_mc_base-BioNER-EN-ZH
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# bert_chinese_mc_base-BioNER-EN-ZH
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [StivenLancheros/bert_chinese_mc_base-BioNER-EN](https://huggingface.co/StivenLancheros/bert_chinese_mc_base-BioNER-EN) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.3611
|
22 |
+
- Precision: 0.6967
|
23 |
+
- Recall: 0.7980
|
24 |
+
- F1: 0.7439
|
25 |
+
- Accuracy: 0.9215
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 3e-05
|
45 |
+
- train_batch_size: 16
|
46 |
+
- eval_batch_size: 16
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 20
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
56 |
+
| 0.4895 | 1.0 | 680 | 0.6248 | 0.4389 | 0.6486 | 0.5235 | 0.8301 |
|
57 |
+
| 0.3569 | 2.0 | 1360 | 0.6207 | 0.4931 | 0.7204 | 0.5854 | 0.8481 |
|
58 |
+
| 0.2778 | 3.0 | 2040 | 0.4876 | 0.5723 | 0.7371 | 0.6443 | 0.8864 |
|
59 |
+
| 0.2558 | 4.0 | 2720 | 0.4496 | 0.5882 | 0.7446 | 0.6572 | 0.8892 |
|
60 |
+
| 0.2363 | 5.0 | 3400 | 0.4674 | 0.5845 | 0.7619 | 0.6615 | 0.8892 |
|
61 |
+
| 0.2129 | 6.0 | 4080 | 0.4311 | 0.6148 | 0.7674 | 0.6827 | 0.9005 |
|
62 |
+
| 0.2019 | 7.0 | 4760 | 0.3930 | 0.6428 | 0.7710 | 0.7011 | 0.9103 |
|
63 |
+
| 0.1912 | 8.0 | 5440 | 0.4031 | 0.6438 | 0.7815 | 0.7060 | 0.9095 |
|
64 |
+
| 0.1741 | 9.0 | 6120 | 0.3914 | 0.6506 | 0.7765 | 0.7080 | 0.9101 |
|
65 |
+
| 0.1727 | 10.0 | 6800 | 0.3808 | 0.6530 | 0.7814 | 0.7114 | 0.9117 |
|
66 |
+
| 0.1625 | 11.0 | 7480 | 0.4047 | 0.6545 | 0.7828 | 0.7129 | 0.9106 |
|
67 |
+
| 0.1546 | 12.0 | 8160 | 0.3803 | 0.6543 | 0.7849 | 0.7137 | 0.9115 |
|
68 |
+
| 0.1515 | 13.0 | 8840 | 0.3635 | 0.6828 | 0.7979 | 0.7359 | 0.9217 |
|
69 |
+
| 0.1415 | 14.0 | 9520 | 0.3872 | 0.6718 | 0.7962 | 0.7287 | 0.9160 |
|
70 |
+
| 0.1425 | 15.0 | 10200 | 0.3699 | 0.6879 | 0.7939 | 0.7371 | 0.9193 |
|
71 |
+
| 0.1327 | 16.0 | 10880 | 0.3762 | 0.6869 | 0.7977 | 0.7382 | 0.9184 |
|
72 |
+
| 0.1307 | 17.0 | 11560 | 0.3732 | 0.6822 | 0.8013 | 0.7369 | 0.9181 |
|
73 |
+
| 0.1309 | 18.0 | 12240 | 0.3629 | 0.6956 | 0.7970 | 0.7428 | 0.9208 |
|
74 |
+
| 0.1268 | 19.0 | 12920 | 0.3643 | 0.6930 | 0.7990 | 0.7423 | 0.9210 |
|
75 |
+
| 0.1257 | 20.0 | 13600 | 0.3611 | 0.6967 | 0.7980 | 0.7439 | 0.9215 |
|
76 |
+
|
77 |
+
|
78 |
+
### Framework versions
|
79 |
+
|
80 |
+
- Transformers 4.27.2
|
81 |
+
- Pytorch 1.13.0+cu117
|
82 |
+
- Datasets 2.7.1
|
83 |
+
- Tokenizers 0.13.2
|