callmesan commited on
Commit
fe7e01e
1 Parent(s): d2b5c44

End of training

Browse files
Files changed (1) hide show
  1. README.md +73 -0
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: cardiffnlp/twitter-roberta-large-hate-latest
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - precision
10
+ - recall
11
+ - f1
12
+ model-index:
13
+ - name: twitter-roberta-large-hate-latest-roman-urdu-fine-grained
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # twitter-roberta-large-hate-latest-roman-urdu-fine-grained
21
+
22
+ This model is a fine-tuned version of [cardiffnlp/twitter-roberta-large-hate-latest](https://huggingface.co/cardiffnlp/twitter-roberta-large-hate-latest) on the None dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.4394
25
+ - Accuracy: 0.8521
26
+ - Precision: 0.7814
27
+ - Recall: 0.7733
28
+ - F1: 0.7764
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 1e-05
48
+ - train_batch_size: 32
49
+ - eval_batch_size: 128
50
+ - seed: 42
51
+ - gradient_accumulation_steps: 4
52
+ - total_train_batch_size: 128
53
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
+ - lr_scheduler_type: linear
55
+ - num_epochs: 5
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
60
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
61
+ | 0.8983 | 0.9912 | 56 | 0.7694 | 0.7359 | 0.6713 | 0.6012 | 0.6247 |
62
+ | 0.7237 | 2.0 | 113 | 0.5778 | 0.7987 | 0.7241 | 0.6824 | 0.6913 |
63
+ | 0.5471 | 2.9912 | 169 | 0.4937 | 0.8297 | 0.7491 | 0.7530 | 0.7503 |
64
+ | 0.5403 | 4.0 | 226 | 0.4589 | 0.8424 | 0.7705 | 0.7575 | 0.7626 |
65
+ | 0.5452 | 4.9558 | 280 | 0.4394 | 0.8521 | 0.7814 | 0.7733 | 0.7764 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.45.1
71
+ - Pytorch 2.4.0
72
+ - Datasets 3.0.1
73
+ - Tokenizers 0.20.0