shed-e commited on
Commit
4d72913
1 Parent(s): 1a3ed61

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - peoples_daily_ner
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: ner_peoples_daily
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: peoples_daily_ner
20
+ type: peoples_daily_ner
21
+ config: peoples_daily_ner
22
+ split: train
23
+ args: peoples_daily_ner
24
+ metrics:
25
+ - name: Precision
26
+ type: precision
27
+ value: 0.9205354599829109
28
+ - name: Recall
29
+ type: recall
30
+ value: 0.9365401332946972
31
+ - name: F1
32
+ type: f1
33
+ value: 0.9284688307957485
34
+ - name: Accuracy
35
+ type: accuracy
36
+ value: 0.9929549534505072
37
+ ---
38
+
39
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
40
+ should probably proofread and complete it, then remove this comment. -->
41
+
42
+ # ner_peoples_daily
43
+
44
+ This model is a fine-tuned version of [hfl/rbt6](https://huggingface.co/hfl/rbt6) on the peoples_daily_ner dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 0.0249
47
+ - Precision: 0.9205
48
+ - Recall: 0.9365
49
+ - F1: 0.9285
50
+ - Accuracy: 0.9930
51
+
52
+ ## Model description
53
+
54
+ More information needed
55
+
56
+ ## Intended uses & limitations
57
+
58
+ More information needed
59
+
60
+ ## Training and evaluation data
61
+
62
+ More information needed
63
+
64
+ ## Training procedure
65
+
66
+ ### Training hyperparameters
67
+
68
+ The following hyperparameters were used during training:
69
+ - learning_rate: 2e-05
70
+ - train_batch_size: 128
71
+ - eval_batch_size: 128
72
+ - seed: 42
73
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
+ - lr_scheduler_type: linear
75
+ - num_epochs: 8
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | 0.3154 | 1.0 | 164 | 0.0410 | 0.8258 | 0.8684 | 0.8466 | 0.9868 |
82
+ | 0.0394 | 2.0 | 328 | 0.0287 | 0.8842 | 0.9070 | 0.8954 | 0.9905 |
83
+ | 0.0293 | 3.0 | 492 | 0.0264 | 0.8978 | 0.9168 | 0.9072 | 0.9916 |
84
+ | 0.02 | 4.0 | 656 | 0.0254 | 0.9149 | 0.9226 | 0.9188 | 0.9923 |
85
+ | 0.016 | 5.0 | 820 | 0.0250 | 0.9167 | 0.9281 | 0.9224 | 0.9927 |
86
+ | 0.0124 | 6.0 | 984 | 0.0252 | 0.9114 | 0.9328 | 0.9220 | 0.9928 |
87
+ | 0.0108 | 7.0 | 1148 | 0.0249 | 0.9169 | 0.9339 | 0.9254 | 0.9928 |
88
+ | 0.0097 | 8.0 | 1312 | 0.0249 | 0.9205 | 0.9365 | 0.9285 | 0.9930 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.23.1
94
+ - Pytorch 1.12.1+cu113
95
+ - Datasets 2.5.2
96
+ - Tokenizers 0.13.1