Hugging Face's logo

SetFit
/
distilbert-base-uncased__sst2__train-16-4

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Model card Files
xet
Community
1
lewtun HF Staff commited on
Commit
8ed5b18
·
1 Parent(s): 4c1b7c5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +89 -0
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: distilbert-base-uncased__sst2__train-16-4
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # distilbert-base-uncased__sst2__train-16-4
16
+
17
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.1501
20
+ - Accuracy: 0.6387
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 4
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 50
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 0.7043 | 1.0 | 7 | 0.7139 | 0.2857 |
53
+ | 0.68 | 2.0 | 14 | 0.7398 | 0.2857 |
54
+ | 0.641 | 3.0 | 21 | 0.7723 | 0.2857 |
55
+ | 0.5424 | 4.0 | 28 | 0.8391 | 0.2857 |
56
+ | 0.5988 | 5.0 | 35 | 0.7761 | 0.2857 |
57
+ | 0.3698 | 6.0 | 42 | 0.7707 | 0.4286 |
58
+ | 0.3204 | 7.0 | 49 | 0.8290 | 0.4286 |
59
+ | 0.2882 | 8.0 | 56 | 0.6551 | 0.5714 |
60
+ | 0.1512 | 9.0 | 63 | 0.5652 | 0.5714 |
61
+ | 0.1302 | 10.0 | 70 | 0.5278 | 0.5714 |
62
+ | 0.1043 | 11.0 | 77 | 0.4987 | 0.7143 |
63
+ | 0.0272 | 12.0 | 84 | 0.5278 | 0.5714 |
64
+ | 0.0201 | 13.0 | 91 | 0.5307 | 0.5714 |
65
+ | 0.0129 | 14.0 | 98 | 0.5382 | 0.5714 |
66
+ | 0.0117 | 15.0 | 105 | 0.5227 | 0.5714 |
67
+ | 0.0094 | 16.0 | 112 | 0.5066 | 0.7143 |
68
+ | 0.0104 | 17.0 | 119 | 0.4869 | 0.7143 |
69
+ | 0.0069 | 18.0 | 126 | 0.4786 | 0.7143 |
70
+ | 0.0062 | 19.0 | 133 | 0.4707 | 0.7143 |
71
+ | 0.0065 | 20.0 | 140 | 0.4669 | 0.7143 |
72
+ | 0.0051 | 21.0 | 147 | 0.4686 | 0.7143 |
73
+ | 0.0049 | 22.0 | 154 | 0.4784 | 0.7143 |
74
+ | 0.0046 | 23.0 | 161 | 0.4839 | 0.7143 |
75
+ | 0.0039 | 24.0 | 168 | 0.4823 | 0.7143 |
76
+ | 0.0044 | 25.0 | 175 | 0.4791 | 0.7143 |
77
+ | 0.0037 | 26.0 | 182 | 0.4778 | 0.7143 |
78
+ | 0.0038 | 27.0 | 189 | 0.4770 | 0.7143 |
79
+ | 0.0036 | 28.0 | 196 | 0.4750 | 0.7143 |
80
+ | 0.0031 | 29.0 | 203 | 0.4766 | 0.7143 |
81
+ | 0.0031 | 30.0 | 210 | 0.4754 | 0.7143 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.15.0
87
+ - Pytorch 1.10.2+cu102
88
+ - Datasets 1.18.2
89
+ - Tokenizers 0.10.3