roupenminassian commited on
Commit
bb41d76
1 Parent(s): 990ff93

End of training

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - f1
7
+ model-index:
8
+ - name: twitter-misinformation-classifier-3
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # twitter-misinformation-classifier-3
16
+
17
+ This model is a fine-tuned version of [Twitter/twhin-bert-large](https://huggingface.co/Twitter/twhin-bert-large) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0632
20
+ - F1: 0.9829
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 3
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
50
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
51
+ | 0.3092 | 0.04 | 250 | 0.0873 | 0.9683 |
52
+ | 0.095 | 0.09 | 500 | 0.0973 | 0.9752 |
53
+ | 0.0937 | 0.13 | 750 | 0.0969 | 0.9669 |
54
+ | 0.0859 | 0.17 | 1000 | 0.0762 | 0.9772 |
55
+ | 0.0828 | 0.22 | 1250 | 0.1208 | 0.9669 |
56
+ | 0.0685 | 0.26 | 1500 | 0.0745 | 0.9803 |
57
+ | 0.0801 | 0.3 | 1750 | 0.0678 | 0.9798 |
58
+ | 0.0717 | 0.35 | 2000 | 0.1027 | 0.9783 |
59
+ | 0.1132 | 0.39 | 2250 | 0.0968 | 0.9771 |
60
+ | 0.1088 | 0.43 | 2500 | 0.0838 | 0.9794 |
61
+ | 0.0976 | 0.48 | 2750 | 0.0915 | 0.9787 |
62
+ | 0.0863 | 0.52 | 3000 | 0.0828 | 0.9797 |
63
+ | 0.0967 | 0.56 | 3250 | 0.1350 | 0.9722 |
64
+ | 0.1225 | 0.61 | 3500 | 0.1098 | 0.9753 |
65
+ | 0.1017 | 0.65 | 3750 | 0.0807 | 0.9754 |
66
+ | 0.091 | 0.69 | 4000 | 0.1083 | 0.9757 |
67
+ | 0.0882 | 0.74 | 4250 | 0.0768 | 0.9811 |
68
+ | 0.0688 | 0.78 | 4500 | 0.0819 | 0.9788 |
69
+ | 0.0728 | 0.82 | 4750 | 0.0758 | 0.9802 |
70
+ | 0.0967 | 0.87 | 5000 | 0.1157 | 0.9743 |
71
+ | 0.0862 | 0.91 | 5250 | 0.0677 | 0.9816 |
72
+ | 0.0815 | 0.95 | 5500 | 0.0709 | 0.9768 |
73
+ | 0.0776 | 1.0 | 5750 | 0.0737 | 0.9799 |
74
+ | 0.0635 | 1.04 | 6000 | 0.0941 | 0.9761 |
75
+ | 0.0805 | 1.08 | 6250 | 0.0993 | 0.9778 |
76
+ | 0.0887 | 1.13 | 6500 | 0.0916 | 0.9770 |
77
+ | 0.0824 | 1.17 | 6750 | 0.0859 | 0.9790 |
78
+ | 0.0885 | 1.21 | 7000 | 0.0893 | 0.9795 |
79
+ | 0.0868 | 1.26 | 7250 | 0.0686 | 0.9801 |
80
+ | 0.09 | 1.3 | 7500 | 0.0940 | 0.9767 |
81
+ | 0.0907 | 1.34 | 7750 | 0.0878 | 0.9796 |
82
+ | 0.0835 | 1.39 | 8000 | 0.0736 | 0.9790 |
83
+ | 0.0747 | 1.43 | 8250 | 0.0878 | 0.9817 |
84
+ | 0.0745 | 1.47 | 8500 | 0.0675 | 0.9809 |
85
+ | 0.0754 | 1.52 | 8750 | 0.0708 | 0.9813 |
86
+ | 0.0781 | 1.56 | 9000 | 0.0816 | 0.9822 |
87
+ | 0.069 | 1.6 | 9250 | 0.0761 | 0.9820 |
88
+ | 0.0708 | 1.65 | 9500 | 0.0887 | 0.9814 |
89
+ | 0.1062 | 1.69 | 9750 | 0.0887 | 0.9803 |
90
+ | 0.0643 | 1.73 | 10000 | 0.0771 | 0.9821 |
91
+ | 0.0675 | 1.77 | 10250 | 0.0870 | 0.9809 |
92
+ | 0.0705 | 1.82 | 10500 | 0.0791 | 0.9817 |
93
+ | 0.0737 | 1.86 | 10750 | 0.0780 | 0.9815 |
94
+ | 0.0665 | 1.9 | 11000 | 0.0779 | 0.9828 |
95
+ | 0.0919 | 1.95 | 11250 | 0.0905 | 0.9768 |
96
+ | 0.0687 | 1.99 | 11500 | 0.0647 | 0.9806 |
97
+ | 0.0675 | 2.03 | 11750 | 0.0634 | 0.9814 |
98
+ | 0.0549 | 2.08 | 12000 | 0.0670 | 0.9812 |
99
+ | 0.0593 | 2.12 | 12250 | 0.0676 | 0.9815 |
100
+ | 0.0603 | 2.16 | 12500 | 0.0624 | 0.9828 |
101
+ | 0.0553 | 2.21 | 12750 | 0.0762 | 0.9806 |
102
+ | 0.0502 | 2.25 | 13000 | 0.0798 | 0.9835 |
103
+ | 0.0431 | 2.29 | 13250 | 0.1644 | 0.9227 |
104
+ | 0.0514 | 2.34 | 13500 | 0.0831 | 0.9803 |
105
+ | 0.0536 | 2.38 | 13750 | 0.0585 | 0.9833 |
106
+ | 0.0472 | 2.42 | 14000 | 0.0570 | 0.9839 |
107
+ | 0.0581 | 2.47 | 14250 | 0.0561 | 0.9828 |
108
+ | 0.0465 | 2.51 | 14500 | 0.0585 | 0.9842 |
109
+ | 0.0542 | 2.55 | 14750 | 0.1652 | 0.9827 |
110
+ | 0.0595 | 2.6 | 15000 | 0.1015 | 0.9821 |
111
+ | 0.051 | 2.64 | 15250 | 0.2099 | 0.8379 |
112
+ | 0.0447 | 2.68 | 15500 | 0.0633 | 0.9826 |
113
+ | 0.0389 | 2.73 | 15750 | 0.0647 | 0.9830 |
114
+ | 0.0533 | 2.77 | 16000 | 0.0623 | 0.9829 |
115
+ | 0.0524 | 2.81 | 16250 | 0.0586 | 0.9831 |
116
+ | 0.0576 | 2.86 | 16500 | 0.0597 | 0.9830 |
117
+ | 0.0483 | 2.9 | 16750 | 0.0689 | 0.9836 |
118
+ | 0.0469 | 2.94 | 17000 | 0.0569 | 0.9837 |
119
+ | 0.0447 | 2.99 | 17250 | 0.0632 | 0.9829 |
120
+
121
+
122
+ ### Framework versions
123
+
124
+ - Transformers 4.28.1
125
+ - Pytorch 2.0.0+cu118
126
+ - Datasets 2.11.0
127
+ - Tokenizers 0.13.3
logs/events.out.tfevents.1681972099.e0307d85487d.30874.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfc8518e705a96db34bb629f95e222fa55ce106ed0e334e7c1ed4e3fd393947e
3
- size 36923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55170eefef342df7b2362e3269ecf075f212fa54cef99d1071f93f28906e3ef6
3
+ size 37283
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:affcfb1f45c4b14a70a6589c3d153b430ed4309e5a6613a88dab64d5a923a5d6
3
+ size 17082925
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 1000000000000000019884624838656,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }