Hugging Face's logo

IIIT-L
/
roberta-large-finetuned-non-code-mixed-DS

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
1
dipteshkanojia commited on
Commit
ec6b897
·
1 Parent(s): af484dd

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ - precision
8
+ - recall
9
+ - f1
10
+ model-index:
11
+ - name: roberta-large-finetuned-non-code-mixed-DS
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # roberta-large-finetuned-non-code-mixed-DS
19
+
20
+ This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 3.1265
23
+ - Accuracy: 0.6936
24
+ - Precision: 0.6794
25
+ - Recall: 0.6782
26
+ - F1: 0.6784
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 1e-05
46
+ - train_batch_size: 16
47
+ - eval_batch_size: 32
48
+ - seed: 43
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 20
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | 1.0688 | 1.0 | 463 | 0.8847 | 0.6127 | 0.6038 | 0.6032 | 0.6014 |
59
+ | 0.8226 | 2.0 | 926 | 0.7622 | 0.6796 | 0.6769 | 0.6822 | 0.6716 |
60
+ | 0.6844 | 2.99 | 1389 | 0.8391 | 0.6828 | 0.6718 | 0.6563 | 0.6602 |
61
+ | 0.536 | 3.99 | 1852 | 0.8218 | 0.6990 | 0.6950 | 0.6807 | 0.6844 |
62
+ | 0.3938 | 4.99 | 2315 | 0.9616 | 0.6958 | 0.6967 | 0.7056 | 0.6880 |
63
+ | 0.2674 | 5.99 | 2778 | 1.1389 | 0.7033 | 0.6868 | 0.6895 | 0.6879 |
64
+ | 0.2073 | 6.98 | 3241 | 1.5578 | 0.6915 | 0.6786 | 0.6807 | 0.6792 |
65
+ | 0.1641 | 7.98 | 3704 | 1.9538 | 0.6850 | 0.6734 | 0.6715 | 0.6717 |
66
+ | 0.1394 | 8.98 | 4167 | 2.3230 | 0.6893 | 0.6733 | 0.6742 | 0.6736 |
67
+ | 0.1248 | 9.98 | 4630 | 2.4050 | 0.6936 | 0.6824 | 0.6819 | 0.6815 |
68
+ | 0.1002 | 10.98 | 5093 | 2.4227 | 0.6947 | 0.6832 | 0.6932 | 0.6795 |
69
+ | 0.0776 | 11.97 | 5556 | 2.5782 | 0.7012 | 0.6876 | 0.6923 | 0.6887 |
70
+ | 0.0685 | 12.97 | 6019 | 2.7967 | 0.6915 | 0.6836 | 0.6930 | 0.6820 |
71
+ | 0.045 | 13.97 | 6482 | 2.8884 | 0.7044 | 0.6873 | 0.6855 | 0.6863 |
72
+ | 0.0462 | 14.97 | 6945 | 2.9528 | 0.6947 | 0.6754 | 0.6749 | 0.6751 |
73
+ | 0.0444 | 15.97 | 7408 | 3.0356 | 0.6904 | 0.6778 | 0.6805 | 0.6778 |
74
+ | 0.0343 | 16.96 | 7871 | 3.0123 | 0.6936 | 0.6784 | 0.6762 | 0.6771 |
75
+ | 0.0245 | 17.96 | 8334 | 3.0160 | 0.6893 | 0.6720 | 0.6735 | 0.6727 |
76
+ | 0.0198 | 18.96 | 8797 | 3.1597 | 0.6904 | 0.6741 | 0.6727 | 0.6732 |
77
+ | 0.0189 | 19.96 | 9260 | 3.1265 | 0.6936 | 0.6794 | 0.6782 | 0.6784 |
78
+
79
+
80
+ ### Framework versions
81
+
82
+ - Transformers 4.20.1
83
+ - Pytorch 1.10.1+cu111
84
+ - Datasets 2.3.2
85
+ - Tokenizers 0.12.1