Hugging Face's logo

Mbabazi
/
twitter-roberta-base-sentiment-latest

Text Classification
Transformers
PyTorch
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
Mbabazi commited on
Commit
ec97fea
•
1 Parent(s): 765c014

End of training

Browse files
Files changed (1) hide show
  1. README.md +17 -32
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.3725
20
- - Accuracy: 0.798
21
 
22
  ## Model description
23
 
@@ -49,36 +49,21 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | 0.5281 | 0.1 | 50 | 0.5483 | 0.5845 |
53
- | 0.4213 | 0.2 | 100 | 0.4663 | 0.671 |
54
- | 0.4279 | 0.3 | 150 | 0.3972 | 0.7175 |
55
- | 0.3765 | 0.4 | 200 | 0.3771 | 0.7425 |
56
- | 0.3733 | 0.5 | 250 | 0.3884 | 0.755 |
57
- | 0.4427 | 0.6 | 300 | 0.3535 | 0.7515 |
58
- | 0.367 | 0.7 | 350 | 0.3511 | 0.765 |
59
- | 0.3446 | 0.8 | 400 | 0.3422 | 0.7695 |
60
- | 0.3339 | 0.9 | 450 | 0.3560 | 0.775 |
61
- | 0.3681 | 1.0 | 500 | 0.3359 | 0.776 |
62
- | 0.2586 | 1.1 | 550 | 0.3620 | 0.776 |
63
- | 0.3399 | 1.2 | 600 | 0.3433 | 0.798 |
64
- | 0.3881 | 1.3 | 650 | 0.3457 | 0.765 |
65
- | 0.3443 | 1.4 | 700 | 0.3400 | 0.7885 |
66
- | 0.2937 | 1.5 | 750 | 0.3475 | 0.7805 |
67
- | 0.3363 | 1.6 | 800 | 0.3937 | 0.756 |
68
- | 0.3363 | 1.7 | 850 | 0.3165 | 0.8065 |
69
- | 0.3427 | 1.8 | 900 | 0.3374 | 0.7945 |
70
- | 0.3457 | 1.9 | 950 | 0.3154 | 0.8055 |
71
- | 0.3256 | 2.0 | 1000 | 0.3412 | 0.7945 |
72
- | 0.1914 | 2.1 | 1050 | 0.3785 | 0.8005 |
73
- | 0.1546 | 2.2 | 1100 | 0.3921 | 0.798 |
74
- | 0.1931 | 2.3 | 1150 | 0.3766 | 0.797 |
75
- | 0.2315 | 2.4 | 1200 | 0.3866 | 0.7985 |
76
- | 0.1973 | 2.5 | 1250 | 0.3758 | 0.7975 |
77
- | 0.3116 | 2.6 | 1300 | 0.3839 | 0.7975 |
78
- | 0.245 | 2.7 | 1350 | 0.3770 | 0.7945 |
79
- | 0.144 | 2.8 | 1400 | 0.3774 | 0.793 |
80
- | 0.219 | 2.9 | 1450 | 0.3833 | 0.792 |
81
- | 0.2341 | 3.0 | 1500 | 0.3725 | 0.798 |
82
 
83
 
84
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.3658
20
+ - Accuracy: 0.8045
21
 
22
  ## Model description
23
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 0.6116 | 0.2 | 100 | 0.4453 | 0.6965 |
53
+ | 0.4047 | 0.4 | 200 | 0.3999 | 0.735 |
54
+ | 0.3979 | 0.6 | 300 | 0.3641 | 0.7655 |
55
+ | 0.3828 | 0.8 | 400 | 0.3512 | 0.7635 |
56
+ | 0.3805 | 1.0 | 500 | 0.3489 | 0.776 |
57
+ | 0.3454 | 1.2 | 600 | 0.3488 | 0.774 |
58
+ | 0.3135 | 1.4 | 700 | 0.3529 | 0.785 |
59
+ | 0.3216 | 1.6 | 800 | 0.3344 | 0.7845 |
60
+ | 0.3005 | 1.8 | 900 | 0.3793 | 0.789 |
61
+ | 0.3041 | 2.0 | 1000 | 0.3324 | 0.7925 |
62
+ | 0.2126 | 2.2 | 1100 | 0.3839 | 0.7895 |
63
+ | 0.2218 | 2.4 | 1200 | 0.3653 | 0.7955 |
64
+ | 0.1986 | 2.6 | 1300 | 0.3745 | 0.803 |
65
+ | 0.2049 | 2.8 | 1400 | 0.3586 | 0.802 |
66
+ | 0.1911 | 3.0 | 1500 | 0.3658 | 0.8045 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
 
68
 
69
  ### Framework versions