Hugging Face's logo

henryscheible
/
xlnet-base-cased_crows_pairs_finetuned

Text Classification
Transformers
PyTorch
xlnet
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
henryscheible commited on
Commit
312cf29
·
1 Parent(s): c7a0084

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - crows_pairs
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: xlnet-base-cased_crows_pairs_finetuned
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: crows_pairs
17
+ type: crows_pairs
18
+ config: crows_pairs
19
+ split: test
20
+ args: crows_pairs
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.49337748344370863
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # xlnet-base-cased_crows_pairs_finetuned
31
+
32
+ This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the crows_pairs dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.7205
35
+ - Accuracy: 0.4934
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 1e-05
55
+ - train_batch_size: 128
56
+ - eval_batch_size: 64
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 15
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | No log | 0.5 | 5 | 0.7872 | 0.5099 |
67
+ | No log | 1.0 | 10 | 0.7224 | 0.4868 |
68
+ | No log | 1.5 | 15 | 0.7039 | 0.5464 |
69
+ | No log | 2.0 | 20 | 0.6976 | 0.5 |
70
+ | No log | 2.5 | 25 | 0.7210 | 0.4702 |
71
+ | No log | 3.0 | 30 | 0.6963 | 0.5099 |
72
+ | No log | 3.5 | 35 | 0.6971 | 0.5166 |
73
+ | No log | 4.0 | 40 | 0.7045 | 0.4735 |
74
+ | No log | 4.5 | 45 | 0.7228 | 0.4768 |
75
+ | No log | 5.0 | 50 | 0.7042 | 0.4702 |
76
+ | No log | 5.5 | 55 | 0.7013 | 0.4834 |
77
+ | No log | 6.0 | 60 | 0.7056 | 0.4768 |
78
+ | No log | 6.5 | 65 | 0.7086 | 0.4702 |
79
+ | No log | 7.0 | 70 | 0.7027 | 0.4834 |
80
+ | No log | 7.5 | 75 | 0.7137 | 0.4834 |
81
+ | No log | 8.0 | 80 | 0.7100 | 0.4735 |
82
+ | No log | 8.5 | 85 | 0.7083 | 0.4934 |
83
+ | No log | 9.0 | 90 | 0.7067 | 0.4934 |
84
+ | No log | 9.5 | 95 | 0.7052 | 0.4768 |
85
+ | No log | 10.0 | 100 | 0.7078 | 0.4669 |
86
+ | No log | 10.5 | 105 | 0.7147 | 0.4768 |
87
+ | No log | 11.0 | 110 | 0.7200 | 0.4834 |
88
+ | No log | 11.5 | 115 | 0.7164 | 0.4570 |
89
+ | No log | 12.0 | 120 | 0.7146 | 0.4669 |
90
+ | No log | 12.5 | 125 | 0.7096 | 0.4934 |
91
+ | No log | 13.0 | 130 | 0.7138 | 0.4702 |
92
+ | No log | 13.5 | 135 | 0.7201 | 0.4768 |
93
+ | No log | 14.0 | 140 | 0.7236 | 0.4967 |
94
+ | No log | 14.5 | 145 | 0.7216 | 0.4967 |
95
+ | No log | 15.0 | 150 | 0.7205 | 0.4934 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.26.1
101
+ - Pytorch 1.13.1
102
+ - Datasets 2.10.1
103
+ - Tokenizers 0.13.2