vish88 commited on
Commit
39d7e31
1 Parent(s): b4b2c18

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +75 -0
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - glue
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: xlnet-base-mnli-finetuned
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: glue
17
+ type: glue
18
+ args: mnli
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.9118695873662761
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # xlnet-base-mnli-finetuned
29
+
30
+ This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the glue dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.3456
33
+ - Accuracy: 0.9119
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 2e-05
53
+ - train_batch_size: 1
54
+ - eval_batch_size: 1
55
+ - seed: 42
56
+ - gradient_accumulation_steps: 8
57
+ - total_train_batch_size: 8
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 2
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
66
+ | 0.336 | 1.0 | 49087 | 0.3299 | 0.9010 |
67
+ | 0.2582 | 2.0 | 98174 | 0.3456 | 0.9119 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.20.1
73
+ - Pytorch 1.12.0+cu113
74
+ - Datasets 2.3.2
75
+ - Tokenizers 0.12.1