Jinchen commited on
Commit
7115c1f
1 Parent(s): 9fee312

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +74 -0
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - conll2003
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: bert-base-uncased-finetuned-ner
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # bert-base-uncased-finetuned-ner
21
+
22
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the conll2003 dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.0712
25
+ - Precision: 0.8945
26
+ - Recall: 0.9182
27
+ - F1: 0.9062
28
+ - Accuracy: 0.9793
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 1
49
+ - eval_batch_size: 1
50
+ - seed: 42
51
+ - distributed_type: IPU
52
+ - gradient_accumulation_steps: 16
53
+ - total_train_batch_size: 64
54
+ - total_eval_batch_size: 20
55
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
+ - lr_scheduler_type: linear
57
+ - num_epochs: 3
58
+ - training precision: Mixed Precision
59
+
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
63
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
64
+ | 0.1318 | 1.0 | 219 | 0.0967 | 0.8371 | 0.8714 | 0.8539 | 0.9705 |
65
+ | 0.0597 | 2.0 | 438 | 0.0735 | 0.8912 | 0.9052 | 0.8981 | 0.9779 |
66
+ | 0.0523 | 3.0 | 657 | 0.0712 | 0.8945 | 0.9182 | 0.9062 | 0.9793 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.20.0
72
+ - Pytorch 1.10.0+cpu
73
+ - Datasets 2.4.0
74
+ - Tokenizers 0.12.1