Farshid commited on
Commit
3874321
1 Parent(s): 8384464

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - financial_phrasebank
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model-index:
11
+ - name: distilbert-base-uncased_allagree3
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: financial_phrasebank
18
+ type: financial_phrasebank
19
+ args: sentences_allagree
20
+ metrics:
21
+ - name: Accuracy
22
+ type: accuracy
23
+ value: 0.9778761061946902
24
+ - name: F1
25
+ type: f1
26
+ value: 0.9780006392634297
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # distilbert-base-uncased_allagree3
33
+
34
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the financial_phrasebank dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.0937
37
+ - Accuracy: 0.9779
38
+ - F1: 0.9780
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 2e-05
58
+ - train_batch_size: 32
59
+ - eval_batch_size: 32
60
+ - seed: 42
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - num_epochs: 10
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
69
+ | 0.6418 | 1.0 | 57 | 0.3340 | 0.8805 | 0.8768 |
70
+ | 0.1821 | 2.0 | 114 | 0.1088 | 0.9690 | 0.9691 |
71
+ | 0.0795 | 3.0 | 171 | 0.0822 | 0.9823 | 0.9823 |
72
+ | 0.0385 | 4.0 | 228 | 0.0939 | 0.9646 | 0.9646 |
73
+ | 0.0218 | 5.0 | 285 | 0.1151 | 0.9735 | 0.9737 |
74
+ | 0.0149 | 6.0 | 342 | 0.1126 | 0.9690 | 0.9694 |
75
+ | 0.006 | 7.0 | 399 | 0.0989 | 0.9779 | 0.9780 |
76
+ | 0.0093 | 8.0 | 456 | 0.1009 | 0.9779 | 0.9780 |
77
+ | 0.0063 | 9.0 | 513 | 0.0899 | 0.9779 | 0.9780 |
78
+ | 0.0039 | 10.0 | 570 | 0.0937 | 0.9779 | 0.9780 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.17.0
84
+ - Pytorch 1.11.0+cpu
85
+ - Datasets 2.3.2
86
+ - Tokenizers 0.12.1