Hugging Face's logo

SetFit
/
deberta-v3-large__sst2__train-8-4

Text Classification
Transformers
PyTorch
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
lewtun HF staff commited on
Commit
a805b1e
•
1 Parent(s): 93d59e3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +102 -0
README.md ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: deberta-v3-large__sst2__train-8-4
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
+ # deberta-v3-large__sst2__train-8-4
16
+
17
+ This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.3023
20
+ - Accuracy: 0.7057
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
+ | 0.6816 | 1.0 | 3 | 0.8072 | 0.25 |
53
+ | 0.6672 | 2.0 | 6 | 0.8740 | 0.25 |
54
+ | 0.6667 | 3.0 | 9 | 0.8578 | 0.25 |
55
+ | 0.5346 | 4.0 | 12 | 1.0353 | 0.25 |
56
+ | 0.4517 | 5.0 | 15 | 1.1030 | 0.25 |
57
+ | 0.3095 | 6.0 | 18 | 0.9986 | 0.25 |
58
+ | 0.2464 | 7.0 | 21 | 0.9286 | 0.5 |
59
+ | 0.1342 | 8.0 | 24 | 0.4063 | 1.0 |
60
+ | 0.0851 | 9.0 | 27 | 0.2210 | 1.0 |
61
+ | 0.0491 | 10.0 | 30 | 0.2302 | 1.0 |
62
+ | 0.0211 | 11.0 | 33 | 0.4020 | 0.75 |
63
+ | 0.017 | 12.0 | 36 | 0.2382 | 1.0 |
64
+ | 0.0084 | 13.0 | 39 | 0.0852 | 1.0 |
65
+ | 0.0051 | 14.0 | 42 | 0.0354 | 1.0 |
66
+ | 0.0047 | 15.0 | 45 | 0.0208 | 1.0 |
67
+ | 0.0029 | 16.0 | 48 | 0.0155 | 1.0 |
68
+ | 0.0022 | 17.0 | 51 | 0.0139 | 1.0 |
69
+ | 0.0019 | 18.0 | 54 | 0.0144 | 1.0 |
70
+ | 0.0016 | 19.0 | 57 | 0.0168 | 1.0 |
71
+ | 0.0013 | 20.0 | 60 | 0.0231 | 1.0 |
72
+ | 0.0011 | 21.0 | 63 | 0.0369 | 1.0 |
73
+ | 0.0009 | 22.0 | 66 | 0.0528 | 1.0 |
74
+ | 0.001 | 23.0 | 69 | 0.0639 | 1.0 |
75
+ | 0.0009 | 24.0 | 72 | 0.0670 | 1.0 |
76
+ | 0.0009 | 25.0 | 75 | 0.0526 | 1.0 |
77
+ | 0.0008 | 26.0 | 78 | 0.0425 | 1.0 |
78
+ | 0.0011 | 27.0 | 81 | 0.0135 | 1.0 |
79
+ | 0.0007 | 28.0 | 84 | 0.0076 | 1.0 |
80
+ | 0.0007 | 29.0 | 87 | 0.0057 | 1.0 |
81
+ | 0.0007 | 30.0 | 90 | 0.0049 | 1.0 |
82
+ | 0.0008 | 31.0 | 93 | 0.0045 | 1.0 |
83
+ | 0.0007 | 32.0 | 96 | 0.0044 | 1.0 |
84
+ | 0.0008 | 33.0 | 99 | 0.0043 | 1.0 |
85
+ | 0.0005 | 34.0 | 102 | 0.0044 | 1.0 |
86
+ | 0.0006 | 35.0 | 105 | 0.0045 | 1.0 |
87
+ | 0.0006 | 36.0 | 108 | 0.0046 | 1.0 |
88
+ | 0.0007 | 37.0 | 111 | 0.0048 | 1.0 |
89
+ | 0.0006 | 38.0 | 114 | 0.0049 | 1.0 |
90
+ | 0.0005 | 39.0 | 117 | 0.0050 | 1.0 |
91
+ | 0.0005 | 40.0 | 120 | 0.0050 | 1.0 |
92
+ | 0.0004 | 41.0 | 123 | 0.0051 | 1.0 |
93
+ | 0.0005 | 42.0 | 126 | 0.0051 | 1.0 |
94
+ | 0.0004 | 43.0 | 129 | 0.0051 | 1.0 |
95
+
96
+
97
+ ### Framework versions
98
+
99
+ - Transformers 4.15.0
100
+ - Pytorch 1.10.2+cu102
101
+ - Datasets 1.18.2
102
+ - Tokenizers 0.10.3