update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
- accuracy
|
9 |
+
- f1
|
10 |
+
model-index:
|
11 |
+
- name: bert-keyword-discriminator
|
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-keyword-discriminator
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.1310
|
23 |
+
- Precision: 0.8522
|
24 |
+
- Recall: 0.8868
|
25 |
+
- Accuracy: 0.9732
|
26 |
+
- F1: 0.8692
|
27 |
+
- Ent/precision: 0.8874
|
28 |
+
- Ent/accuracy: 0.9246
|
29 |
+
- Ent/f1: 0.9056
|
30 |
+
- Con/precision: 0.8011
|
31 |
+
- Con/accuracy: 0.8320
|
32 |
+
- Con/f1: 0.8163
|
33 |
+
|
34 |
+
## Model description
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Intended uses & limitations
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training and evaluation data
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training procedure
|
47 |
+
|
48 |
+
### Training hyperparameters
|
49 |
+
|
50 |
+
The following hyperparameters were used during training:
|
51 |
+
- learning_rate: 2e-05
|
52 |
+
- train_batch_size: 16
|
53 |
+
- eval_batch_size: 16
|
54 |
+
- seed: 42
|
55 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
56 |
+
- lr_scheduler_type: linear
|
57 |
+
- num_epochs: 8
|
58 |
+
- mixed_precision_training: Native AMP
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1 | Ent/precision | Ent/accuracy | Ent/f1 | Con/precision | Con/accuracy | Con/f1 |
|
63 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:--------:|:------:|:-------------:|:------------:|:------:|:-------------:|:------------:|:------:|
|
64 |
+
| 0.1744 | 1.0 | 1875 | 0.1261 | 0.7176 | 0.7710 | 0.9494 | 0.7433 | 0.7586 | 0.8503 | 0.8018 | 0.6514 | 0.6561 | 0.6537 |
|
65 |
+
| 0.1261 | 2.0 | 3750 | 0.1041 | 0.7742 | 0.8057 | 0.9600 | 0.7896 | 0.8083 | 0.8816 | 0.8433 | 0.7185 | 0.6957 | 0.7070 |
|
66 |
+
| 0.0878 | 3.0 | 5625 | 0.0979 | 0.8176 | 0.8140 | 0.9655 | 0.8158 | 0.8518 | 0.8789 | 0.8651 | 0.7634 | 0.7199 | 0.7410 |
|
67 |
+
| 0.0625 | 4.0 | 7500 | 0.0976 | 0.8228 | 0.8643 | 0.9696 | 0.8430 | 0.8515 | 0.9182 | 0.8836 | 0.7784 | 0.7862 | 0.7823 |
|
68 |
+
| 0.0456 | 5.0 | 9375 | 0.1047 | 0.8304 | 0.8758 | 0.9704 | 0.8525 | 0.8758 | 0.9189 | 0.8968 | 0.7655 | 0.8133 | 0.7887 |
|
69 |
+
| 0.0342 | 6.0 | 11250 | 0.1207 | 0.8363 | 0.8887 | 0.9719 | 0.8617 | 0.8719 | 0.9274 | 0.8988 | 0.7846 | 0.8327 | 0.8080 |
|
70 |
+
| 0.0256 | 7.0 | 13125 | 0.1241 | 0.848 | 0.8892 | 0.9731 | 0.8681 | 0.8791 | 0.9299 | 0.9038 | 0.8019 | 0.8302 | 0.8158 |
|
71 |
+
| 0.0205 | 8.0 | 15000 | 0.1310 | 0.8522 | 0.8868 | 0.9732 | 0.8692 | 0.8874 | 0.9246 | 0.9056 | 0.8011 | 0.8320 | 0.8163 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.19.2
|
77 |
+
- Pytorch 1.11.0+cu113
|
78 |
+
- Datasets 2.2.2
|
79 |
+
- Tokenizers 0.12.1
|