ben-epstein commited on
Commit
9a07a1c
1 Parent(s): 63156f2

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +92 -0
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - wikiann
8
+ metrics:
9
+ - precision
10
+ - recall
11
+ - f1
12
+ - accuracy
13
+ model-index:
14
+ - name: distilbert-base-cased-wikiann
15
+ results:
16
+ - task:
17
+ name: Token Classification
18
+ type: token-classification
19
+ dataset:
20
+ name: wikiann
21
+ type: wikiann
22
+ config: en
23
+ split: validation
24
+ args: en
25
+ metrics:
26
+ - name: Precision
27
+ type: precision
28
+ value: 0.7962710012293402
29
+ - name: Recall
30
+ type: recall
31
+ value: 0.8241905839106461
32
+ - name: F1
33
+ type: f1
34
+ value: 0.8099902737251633
35
+ - name: Accuracy
36
+ type: accuracy
37
+ value: 0.926231747293136
38
+ ---
39
+
40
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
41
+ should probably proofread and complete it, then remove this comment. -->
42
+
43
+ # distilbert-base-cased-wikiann
44
+
45
+ This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the wikiann dataset.
46
+ It achieves the following results on the evaluation set:
47
+ - Loss: 0.2549
48
+ - Precision: 0.7963
49
+ - Recall: 0.8242
50
+ - F1: 0.8100
51
+ - Accuracy: 0.9262
52
+
53
+ ## Model description
54
+
55
+ More information needed
56
+
57
+ ## Intended uses & limitations
58
+
59
+ More information needed
60
+
61
+ ## Training and evaluation data
62
+
63
+ More information needed
64
+
65
+ ## Training procedure
66
+
67
+ ### Training hyperparameters
68
+
69
+ The following hyperparameters were used during training:
70
+ - learning_rate: 2e-05
71
+ - train_batch_size: 16
72
+ - eval_batch_size: 16
73
+ - seed: 101
74
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
+ - lr_scheduler_type: linear
76
+ - num_epochs: 3
77
+
78
+ ### Training results
79
+
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.3137 | 1.0 | 1250 | 0.2685 | 0.7716 | 0.8027 | 0.7868 | 0.9181 |
83
+ | 0.2199 | 2.0 | 2500 | 0.2526 | 0.7765 | 0.8132 | 0.7944 | 0.9220 |
84
+ | 0.1613 | 3.0 | 3750 | 0.2549 | 0.7963 | 0.8242 | 0.8100 | 0.9262 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - Transformers 4.34.1
90
+ - Pytorch 2.0.1+cu117
91
+ - Datasets 2.14.6
92
+ - Tokenizers 0.14.1