almaghrabima commited on
Commit
91a0946
·
1 Parent(s): afdc3c8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_bert-base-NER
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_bert-base-NER
19
+
20
+ This model is a fine-tuned version of [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.1872
23
+ - Precision: 0.7623
24
+ - Recall: 0.7753
25
+ - F1: 0.7688
26
+ - Accuracy: 0.9023
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 | 0.6427 | 0.3025 | 0.2180 | 0.2534 | 0.7415 |
58
+ | 0.9329 | 2.0 | 1404 | 0.4771 | 0.4343 | 0.3587 | 0.3929 | 0.7955 |
59
+ | 0.546 | 3.0 | 2106 | 0.3983 | 0.5157 | 0.4530 | 0.4823 | 0.8242 |
60
+ | 0.546 | 4.0 | 2808 | 0.3748 | 0.5089 | 0.4758 | 0.4918 | 0.8305 |
61
+ | 0.4339 | 5.0 | 3510 | 0.2947 | 0.6362 | 0.6146 | 0.6252 | 0.8656 |
62
+ | 0.3658 | 6.0 | 4212 | 0.2818 | 0.6421 | 0.6231 | 0.6325 | 0.8664 |
63
+ | 0.3658 | 7.0 | 4914 | 0.2459 | 0.7108 | 0.6983 | 0.7045 | 0.8834 |
64
+ | 0.3221 | 8.0 | 5616 | 0.2665 | 0.6586 | 0.6404 | 0.6494 | 0.8701 |
65
+ | 0.2914 | 9.0 | 6318 | 0.2449 | 0.6880 | 0.6768 | 0.6823 | 0.8793 |
66
+ | 0.2657 | 10.0 | 7020 | 0.2411 | 0.7014 | 0.6862 | 0.6937 | 0.8824 |
67
+ | 0.2657 | 11.0 | 7722 | 0.2179 | 0.7261 | 0.7228 | 0.7244 | 0.8902 |
68
+ | 0.2453 | 12.0 | 8424 | 0.2301 | 0.6922 | 0.6919 | 0.6920 | 0.8858 |
69
+ | 0.2295 | 13.0 | 9126 | 0.2352 | 0.6768 | 0.6836 | 0.6802 | 0.8832 |
70
+ | 0.2295 | 14.0 | 9828 | 0.2020 | 0.7545 | 0.7499 | 0.7522 | 0.8970 |
71
+ | 0.2155 | 15.0 | 10530 | 0.2012 | 0.7449 | 0.7508 | 0.7478 | 0.8974 |
72
+ | 0.2064 | 16.0 | 11232 | 0.2036 | 0.7282 | 0.7402 | 0.7341 | 0.8960 |
73
+ | 0.2064 | 17.0 | 11934 | 0.1976 | 0.7390 | 0.7496 | 0.7443 | 0.8974 |
74
+ | 0.1978 | 18.0 | 12636 | 0.1859 | 0.7688 | 0.7828 | 0.7757 | 0.9040 |
75
+ | 0.1895 | 19.0 | 13338 | 0.1917 | 0.7574 | 0.7691 | 0.7632 | 0.9014 |
76
+ | 0.186 | 20.0 | 14040 | 0.1872 | 0.7623 | 0.7753 | 0.7688 | 0.9023 |
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