Hugging Face's logo

pig4431
/
SST2_XLNET_5E

Text Classification
Transformers
PyTorch
xlnet
Generated from Trainer
Model card Files
xet
Community
1
pig4431 commited on
Commit
9ef9efc
·
1 Parent(s): bc77dec

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +101 -0
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: SST2_XLNet_5E
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
+ # SST2_XLNet_5E
16
+
17
+ This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.5502
20
+ - Accuracy: 0.9133
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: 3e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 5
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | 0.6038 | 0.12 | 50 | 0.2830 | 0.8933 |
52
+ | 0.3903 | 0.23 | 100 | 0.3346 | 0.9 |
53
+ | 0.3476 | 0.35 | 150 | 0.4187 | 0.8533 |
54
+ | 0.3528 | 0.46 | 200 | 0.3177 | 0.9 |
55
+ | 0.3372 | 0.58 | 250 | 0.4171 | 0.8333 |
56
+ | 0.3106 | 0.69 | 300 | 0.2825 | 0.9 |
57
+ | 0.295 | 0.81 | 350 | 0.3152 | 0.9 |
58
+ | 0.2828 | 0.92 | 400 | 0.4360 | 0.88 |
59
+ | 0.2359 | 1.04 | 450 | 0.3971 | 0.9 |
60
+ | 0.2224 | 1.15 | 500 | 0.3380 | 0.88 |
61
+ | 0.2136 | 1.27 | 550 | 0.3889 | 0.8933 |
62
+ | 0.264 | 1.39 | 600 | 0.4182 | 0.8667 |
63
+ | 0.1864 | 1.5 | 650 | 0.4887 | 0.88 |
64
+ | 0.1817 | 1.62 | 700 | 0.3626 | 0.9133 |
65
+ | 0.2021 | 1.73 | 750 | 0.4481 | 0.8933 |
66
+ | 0.2154 | 1.85 | 800 | 0.3702 | 0.8933 |
67
+ | 0.2392 | 1.96 | 850 | 0.5025 | 0.8933 |
68
+ | 0.1496 | 2.08 | 900 | 0.4606 | 0.9133 |
69
+ | 0.1537 | 2.19 | 950 | 0.5008 | 0.8933 |
70
+ | 0.1015 | 2.31 | 1000 | 0.5612 | 0.9067 |
71
+ | 0.0915 | 2.42 | 1050 | 0.5249 | 0.8933 |
72
+ | 0.1239 | 2.54 | 1100 | 0.4234 | 0.9133 |
73
+ | 0.1135 | 2.66 | 1150 | 0.4910 | 0.9067 |
74
+ | 0.1738 | 2.77 | 1200 | 0.3844 | 0.92 |
75
+ | 0.1428 | 2.89 | 1250 | 0.4282 | 0.92 |
76
+ | 0.1282 | 3.0 | 1300 | 0.4320 | 0.9 |
77
+ | 0.059 | 3.12 | 1350 | 0.4957 | 0.9133 |
78
+ | 0.0517 | 3.23 | 1400 | 0.4927 | 0.92 |
79
+ | 0.0853 | 3.35 | 1450 | 0.4187 | 0.92 |
80
+ | 0.0808 | 3.46 | 1500 | 0.4304 | 0.92 |
81
+ | 0.09 | 3.58 | 1550 | 0.3447 | 0.9267 |
82
+ | 0.044 | 3.7 | 1600 | 0.4994 | 0.9067 |
83
+ | 0.0443 | 3.81 | 1650 | 0.4516 | 0.9133 |
84
+ | 0.0974 | 3.93 | 1700 | 0.4172 | 0.92 |
85
+ | 0.0768 | 4.04 | 1750 | 0.4777 | 0.9133 |
86
+ | 0.0418 | 4.16 | 1800 | 0.4924 | 0.9267 |
87
+ | 0.0237 | 4.27 | 1850 | 0.5254 | 0.92 |
88
+ | 0.0426 | 4.39 | 1900 | 0.5532 | 0.9133 |
89
+ | 0.0336 | 4.5 | 1950 | 0.5838 | 0.9067 |
90
+ | 0.0188 | 4.62 | 2000 | 0.5775 | 0.9067 |
91
+ | 0.0318 | 4.73 | 2050 | 0.5781 | 0.9067 |
92
+ | 0.0348 | 4.85 | 2100 | 0.5526 | 0.9133 |
93
+ | 0.0524 | 4.97 | 2150 | 0.5502 | 0.9133 |
94
+
95
+
96
+ ### Framework versions
97
+
98
+ - Transformers 4.23.1
99
+ - Pytorch 1.13.0
100
+ - Datasets 2.6.1
101
+ - Tokenizers 0.13.1