Hugging Face's logo

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

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
Model card Files Community
1
dipteshkanojia commited on
Commit
10cb3f4
·
1 Parent(s): fbf5a94

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -16
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 [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 2.0032
23
- - Accuracy: 0.7344
24
- - Precision: 0.6701
25
- - Recall: 0.6682
26
- - F1: 0.6688
27
 
28
  ## Model description
29
 
@@ -48,22 +48,32 @@ The following hyperparameters were used during training:
48
  - seed: 43
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
- - num_epochs: 10
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
- | 0.9813 | 1.0 | 248 | 0.8133 | 0.6197 | 0.5679 | 0.5797 | 0.5139 |
58
- | 0.7795 | 1.99 | 496 | 0.7135 | 0.7183 | 0.6739 | 0.6963 | 0.6782 |
59
- | 0.6188 | 2.99 | 744 | 0.7418 | 0.7324 | 0.6726 | 0.6860 | 0.6761 |
60
- | 0.4741 | 3.98 | 992 | 0.8716 | 0.7123 | 0.6495 | 0.6615 | 0.6501 |
61
- | 0.3326 | 4.98 | 1240 | 1.1437 | 0.7163 | 0.6502 | 0.6470 | 0.6475 |
62
- | 0.2636 | 5.98 | 1488 | 1.3626 | 0.7264 | 0.6832 | 0.6583 | 0.6587 |
63
- | 0.1783 | 6.97 | 1736 | 1.5554 | 0.7445 | 0.6958 | 0.6833 | 0.6823 |
64
- | 0.1258 | 7.97 | 1984 | 1.6650 | 0.7404 | 0.6773 | 0.6731 | 0.6747 |
65
- | 0.099 | 8.96 | 2232 | 1.8831 | 0.7304 | 0.6637 | 0.6622 | 0.6627 |
66
- | 0.0932 | 9.96 | 2480 | 2.0032 | 0.7344 | 0.6701 | 0.6682 | 0.6688 |
 
 
 
 
 
 
 
 
 
 
67
 
68
 
69
  ### Framework versions
 
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: 3.1340
23
+ - Accuracy: 0.7203
24
+ - Precision: 0.6584
25
+ - Recall: 0.6548
26
+ - F1: 0.6558
27
 
28
  ## Model description
29
 
 
48
  - seed: 43
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
+ - num_epochs: 20
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
+ | 0.9729 | 1.0 | 248 | 0.7491 | 0.6922 | 0.6434 | 0.6625 | 0.6358 |
58
+ | 0.7474 | 1.99 | 496 | 0.6947 | 0.7183 | 0.6712 | 0.6915 | 0.6760 |
59
+ | 0.5938 | 2.99 | 744 | 0.7370 | 0.7123 | 0.6624 | 0.6839 | 0.6642 |
60
+ | 0.4264 | 3.98 | 992 | 0.8820 | 0.7123 | 0.6540 | 0.6636 | 0.6492 |
61
+ | 0.2806 | 4.98 | 1240 | 1.2022 | 0.7404 | 0.6807 | 0.6694 | 0.6742 |
62
+ | 0.2239 | 5.98 | 1488 | 1.3933 | 0.7223 | 0.6593 | 0.6587 | 0.6568 |
63
+ | 0.1585 | 6.97 | 1736 | 1.8543 | 0.7304 | 0.6730 | 0.6763 | 0.6737 |
64
+ | 0.1302 | 7.97 | 1984 | 2.0783 | 0.7143 | 0.6495 | 0.6520 | 0.6504 |
65
+ | 0.1008 | 8.96 | 2232 | 2.3523 | 0.7183 | 0.6588 | 0.6561 | 0.6552 |
66
+ | 0.0793 | 9.96 | 2480 | 2.5260 | 0.7163 | 0.6516 | 0.6566 | 0.6538 |
67
+ | 0.0498 | 10.96 | 2728 | 2.6074 | 0.7425 | 0.6902 | 0.6817 | 0.6830 |
68
+ | 0.0484 | 11.95 | 2976 | 2.6758 | 0.7284 | 0.6687 | 0.6734 | 0.6709 |
69
+ | 0.0409 | 12.95 | 3224 | 2.8658 | 0.7425 | 0.6817 | 0.6756 | 0.6781 |
70
+ | 0.0239 | 13.94 | 3472 | 2.9484 | 0.7465 | 0.6980 | 0.6818 | 0.6870 |
71
+ | 0.025 | 14.94 | 3720 | 3.0827 | 0.7304 | 0.6778 | 0.6577 | 0.6641 |
72
+ | 0.0286 | 15.94 | 3968 | 3.0011 | 0.7183 | 0.6509 | 0.6475 | 0.6491 |
73
+ | 0.0264 | 16.93 | 4216 | 3.1581 | 0.7264 | 0.6645 | 0.6563 | 0.6595 |
74
+ | 0.009 | 17.93 | 4464 | 3.1200 | 0.7223 | 0.6589 | 0.6561 | 0.6569 |
75
+ | 0.012 | 18.92 | 4712 | 3.1364 | 0.7203 | 0.6573 | 0.6503 | 0.6525 |
76
+ | 0.017 | 19.92 | 4960 | 3.1340 | 0.7203 | 0.6584 | 0.6548 | 0.6558 |
77
 
78
 
79
  ### Framework versions