Hugging Face's logo

Etelis
/
TUF_XLNET_5E

Text Classification
Transformers
PyTorch
xlnet
Generated from Trainer
Model card Files
xet
Community
1
Etelis commited on
Commit
122a680
·
1 Parent(s): a5a5516

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +108 -0
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: TUF_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
+ # TUF_XLNET_5E
16
+
17
+ This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2725
20
+ - Accuracy: 0.9533
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
+ | 0.4817 | 0.1 | 50 | 0.2602 | 0.8733 |
52
+ | 0.2405 | 0.2 | 100 | 0.5818 | 0.88 |
53
+ | 0.2172 | 0.3 | 150 | 0.1851 | 0.9533 |
54
+ | 0.2697 | 0.4 | 200 | 0.1692 | 0.9267 |
55
+ | 0.2313 | 0.5 | 250 | 0.1086 | 0.9467 |
56
+ | 0.2245 | 0.59 | 300 | 0.2031 | 0.9267 |
57
+ | 0.1805 | 0.69 | 350 | 0.1414 | 0.9467 |
58
+ | 0.1896 | 0.79 | 400 | 0.0824 | 0.9733 |
59
+ | 0.1969 | 0.89 | 450 | 0.1499 | 0.9533 |
60
+ | 0.1745 | 0.99 | 500 | 0.1827 | 0.9267 |
61
+ | 0.1143 | 1.09 | 550 | 0.1923 | 0.9533 |
62
+ | 0.1478 | 1.19 | 600 | 0.1718 | 0.94 |
63
+ | 0.1368 | 1.29 | 650 | 0.1170 | 0.9733 |
64
+ | 0.1288 | 1.39 | 700 | 0.1418 | 0.9667 |
65
+ | 0.1689 | 1.49 | 750 | 0.1173 | 0.9733 |
66
+ | 0.1078 | 1.58 | 800 | 0.2784 | 0.9333 |
67
+ | 0.1343 | 1.68 | 850 | 0.1555 | 0.9533 |
68
+ | 0.1104 | 1.78 | 900 | 0.1361 | 0.9533 |
69
+ | 0.1267 | 1.88 | 950 | 0.1936 | 0.9267 |
70
+ | 0.0928 | 1.98 | 1000 | 0.3070 | 0.94 |
71
+ | 0.0949 | 2.08 | 1050 | 0.1905 | 0.94 |
72
+ | 0.0329 | 2.18 | 1100 | 0.2296 | 0.9533 |
73
+ | 0.0406 | 2.28 | 1150 | 0.3202 | 0.94 |
74
+ | 0.0983 | 2.38 | 1200 | 0.4515 | 0.9267 |
75
+ | 0.0533 | 2.48 | 1250 | 0.2152 | 0.9533 |
76
+ | 0.0878 | 2.57 | 1300 | 0.1573 | 0.9533 |
77
+ | 0.0595 | 2.67 | 1350 | 0.1699 | 0.96 |
78
+ | 0.0937 | 2.77 | 1400 | 0.2825 | 0.9333 |
79
+ | 0.0817 | 2.87 | 1450 | 0.2325 | 0.9467 |
80
+ | 0.0845 | 2.97 | 1500 | 0.1918 | 0.9533 |
81
+ | 0.0711 | 3.07 | 1550 | 0.3186 | 0.94 |
82
+ | 0.033 | 3.17 | 1600 | 0.2571 | 0.94 |
83
+ | 0.0134 | 3.27 | 1650 | 0.2733 | 0.94 |
84
+ | 0.0546 | 3.37 | 1700 | 0.1934 | 0.9533 |
85
+ | 0.0277 | 3.47 | 1750 | 0.2731 | 0.94 |
86
+ | 0.0081 | 3.56 | 1800 | 0.2531 | 0.9467 |
87
+ | 0.0387 | 3.66 | 1850 | 0.2121 | 0.96 |
88
+ | 0.0014 | 3.76 | 1900 | 0.2601 | 0.96 |
89
+ | 0.0379 | 3.86 | 1950 | 0.2501 | 0.9467 |
90
+ | 0.0271 | 3.96 | 2000 | 0.2899 | 0.94 |
91
+ | 0.0182 | 4.06 | 2050 | 0.2197 | 0.9533 |
92
+ | 0.0263 | 4.16 | 2100 | 0.2374 | 0.9533 |
93
+ | 0.0079 | 4.26 | 2150 | 0.3192 | 0.94 |
94
+ | 0.0239 | 4.36 | 2200 | 0.3755 | 0.9333 |
95
+ | 0.02 | 4.46 | 2250 | 0.2702 | 0.9467 |
96
+ | 0.0072 | 4.55 | 2300 | 0.2055 | 0.9533 |
97
+ | 0.0124 | 4.65 | 2350 | 0.2299 | 0.9533 |
98
+ | 0.0072 | 4.75 | 2400 | 0.2813 | 0.9533 |
99
+ | 0.0125 | 4.85 | 2450 | 0.2696 | 0.9533 |
100
+ | 0.0205 | 4.95 | 2500 | 0.2725 | 0.9533 |
101
+
102
+
103
+ ### Framework versions
104
+
105
+ - Transformers 4.24.0
106
+ - Pytorch 1.13.0
107
+ - Datasets 2.7.1
108
+ - Tokenizers 0.13.2