trickstar0
commited on
Commit
•
e996761
1
Parent(s):
2a1db8b
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: NlpHUST/ner-vietnamese-electra-base
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: ner-education-hcmut
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# ner-education-hcmut
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [NlpHUST/ner-vietnamese-electra-base](https://huggingface.co/NlpHUST/ner-vietnamese-electra-base) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.0681
|
18 |
+
- Location: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 7}
|
19 |
+
- Miscellaneous: {'precision': 0.6911764705882353, 'recall': 0.7230769230769231, 'f1': 0.7067669172932332, 'number': 65}
|
20 |
+
- Organization: {'precision': 0.4166666666666667, 'recall': 0.5, 'f1': 0.45454545454545453, 'number': 10}
|
21 |
+
- Person: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3}
|
22 |
+
- Overall Precision: 0.6190
|
23 |
+
- Overall Recall: 0.6118
|
24 |
+
- Overall F1: 0.6154
|
25 |
+
- Overall Accuracy: 0.9851
|
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: 5e-05
|
45 |
+
- train_batch_size: 8
|
46 |
+
- eval_batch_size: 8
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 3.0
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Location | Miscellaneous | Organization | Person | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------:|:---------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
56 |
+
| No log | 1.0 | 207 | 0.0705 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 7} | {'precision': 0.49333333333333335, 'recall': 0.5692307692307692, 'f1': 0.5285714285714285, 'number': 65} | {'precision': 0.36363636363636365, 'recall': 0.4, 'f1': 0.380952380952381, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.4556 | 0.4824 | 0.4686 | 0.9806 |
|
57 |
+
| No log | 2.0 | 414 | 0.0672 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 7} | {'precision': 0.6133333333333333, 'recall': 0.7076923076923077, 'f1': 0.657142857142857, 'number': 65} | {'precision': 0.4666666666666667, 'recall': 0.7, 'f1': 0.56, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.5638 | 0.6235 | 0.5922 | 0.9838 |
|
58 |
+
| 0.0564 | 3.0 | 621 | 0.0681 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 7} | {'precision': 0.6911764705882353, 'recall': 0.7230769230769231, 'f1': 0.7067669172932332, 'number': 65} | {'precision': 0.4166666666666667, 'recall': 0.5, 'f1': 0.45454545454545453, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.6190 | 0.6118 | 0.6154 | 0.9851 |
|
59 |
+
|
60 |
+
|
61 |
+
### Framework versions
|
62 |
+
|
63 |
+
- Transformers 4.42.4
|
64 |
+
- Pytorch 2.3.1+cu121
|
65 |
+
- Datasets 2.21.0
|
66 |
+
- Tokenizers 0.19.1
|