Hugging Face's logo

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

Text Classification
Transformers
PyTorch
xlm-roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Community
1
dipteshkanojia commited on
Commit
64cdc6b
·
1 Parent(s): 898a754

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -10
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 1.0927
23
- - Accuracy: 0.1891
24
- - Precision: 0.0630
25
- - Recall: 0.3333
26
- - F1: 0.1060
27
 
28
  ## Model description
29
 
@@ -42,7 +42,7 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 4.932923543227153e-05
46
  - train_batch_size: 8
47
  - eval_batch_size: 16
48
  - seed: 43
@@ -54,10 +54,14 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
- | 1.1183 | 0.5 | 248 | 1.1037 | 0.2736 | 0.0912 | 0.3333 | 0.1432 |
58
- | 1.1195 | 1.0 | 496 | 1.1022 | 0.5372 | 0.1791 | 0.3333 | 0.2330 |
59
- | 1.106 | 1.5 | 744 | 1.0973 | 0.1891 | 0.0630 | 0.3333 | 0.1060 |
60
- | 1.1075 | 2.0 | 992 | 1.0927 | 0.1891 | 0.0630 | 0.3333 | 0.1060 |
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.7328
23
+ - Accuracy: 0.7022
24
+ - Precision: 0.6437
25
+ - Recall: 0.6634
26
+ - F1: 0.6483
27
 
28
  ## Model description
29
 
 
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
+ - learning_rate: 1e-05
46
  - train_batch_size: 8
47
  - eval_batch_size: 16
48
  - seed: 43
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
+ | 1.098 | 0.5 | 248 | 1.0944 | 0.5352 | 0.2355 | 0.3344 | 0.2397 |
58
+ | 1.0827 | 1.0 | 496 | 1.0957 | 0.5352 | 0.5789 | 0.3379 | 0.2502 |
59
+ | 1.0503 | 1.5 | 744 | 0.9969 | 0.5312 | 0.3621 | 0.4996 | 0.3914 |
60
+ | 0.9728 | 2.0 | 992 | 0.8525 | 0.6056 | 0.5096 | 0.5565 | 0.4678 |
61
+ | 0.9271 | 2.49 | 1240 | 0.7809 | 0.6378 | 0.6014 | 0.6320 | 0.5963 |
62
+ | 0.7977 | 2.99 | 1488 | 0.8290 | 0.5875 | 0.5630 | 0.5918 | 0.5390 |
63
+ | 0.752 | 3.49 | 1736 | 0.7684 | 0.7123 | 0.6526 | 0.6610 | 0.6558 |
64
+ | 0.6846 | 3.99 | 1984 | 0.7328 | 0.7022 | 0.6437 | 0.6634 | 0.6483 |
65
 
66
 
67
  ### Framework versions