Hugging Face's logo

almaghrabima
/
ner_column_TQ

Token Classification
Transformers
PyTorch
English
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
almaghrabima commited on
Commit
6d77378
•
1 Parent(s): df07950

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md CHANGED
@@ -1,3 +1,84 @@
1
  ---
2
  license: mit
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - precision
7
+ - recall
8
+ - f1
9
+ - accuracy
10
+ model-index:
11
+ - name: ner_column_TQ
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
+ # ner_column_TQ
19
+
20
+ This model is a fine-tuned version of [Gladiator/microsoft-deberta-v3-large_ner_conll2003](https://huggingface.co/Gladiator/microsoft-deberta-v3-large_ner_conll2003) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.2111
23
+ - Precision: 0.8593
24
+ - Recall: 0.8587
25
+ - F1: 0.8590
26
+ - Accuracy: 0.9163
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 2e-05
46
+ - train_batch_size: 64
47
+ - eval_batch_size: 64
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 20
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
+ | No log | 1.0 | 702 | 0.1938 | 0.7778 | 0.7851 | 0.7815 | 0.8957 |
58
+ | 0.3587 | 2.0 | 1404 | 0.1562 | 0.8216 | 0.8219 | 0.8217 | 0.9098 |
59
+ | 0.1645 | 3.0 | 2106 | 0.1472 | 0.8161 | 0.8268 | 0.8214 | 0.9114 |
60
+ | 0.1645 | 4.0 | 2808 | 0.1528 | 0.8357 | 0.8195 | 0.8275 | 0.9097 |
61
+ | 0.1372 | 5.0 | 3510 | 0.1411 | 0.8301 | 0.8349 | 0.8325 | 0.9141 |
62
+ | 0.1259 | 6.0 | 4212 | 0.1396 | 0.8341 | 0.8431 | 0.8386 | 0.9149 |
63
+ | 0.1259 | 7.0 | 4914 | 0.1470 | 0.8178 | 0.8323 | 0.8250 | 0.9126 |
64
+ | 0.1205 | 8.0 | 5616 | 0.1413 | 0.8421 | 0.8480 | 0.8451 | 0.9156 |
65
+ | 0.1152 | 9.0 | 6318 | 0.1417 | 0.8342 | 0.8481 | 0.8411 | 0.9158 |
66
+ | 0.1126 | 10.0 | 7020 | 0.1475 | 0.8427 | 0.8493 | 0.8460 | 0.9154 |
67
+ | 0.1126 | 11.0 | 7722 | 0.1490 | 0.8477 | 0.8510 | 0.8493 | 0.9155 |
68
+ | 0.108 | 12.0 | 8424 | 0.1535 | 0.8511 | 0.8540 | 0.8526 | 0.9160 |
69
+ | 0.1035 | 13.0 | 9126 | 0.1569 | 0.8515 | 0.8552 | 0.8533 | 0.9160 |
70
+ | 0.1035 | 14.0 | 9828 | 0.1677 | 0.8530 | 0.8537 | 0.8534 | 0.9158 |
71
+ | 0.097 | 15.0 | 10530 | 0.1721 | 0.8549 | 0.8557 | 0.8553 | 0.9159 |
72
+ | 0.0912 | 16.0 | 11232 | 0.1822 | 0.8573 | 0.8574 | 0.8573 | 0.9165 |
73
+ | 0.0912 | 17.0 | 11934 | 0.1969 | 0.8577 | 0.8578 | 0.8577 | 0.9158 |
74
+ | 0.0854 | 18.0 | 12636 | 0.1969 | 0.8597 | 0.8587 | 0.8592 | 0.9165 |
75
+ | 0.08 | 19.0 | 13338 | 0.2035 | 0.8587 | 0.8587 | 0.8587 | 0.9165 |
76
+ | 0.0768 | 20.0 | 14040 | 0.2111 | 0.8593 | 0.8587 | 0.8590 | 0.9163 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.30.2
82
+ - Pytorch 1.13.1+cu116
83
+ - Datasets 2.13.2
84
+ - Tokenizers 0.13.3