Noodle-bg commited on
Commit
153d7d0
·
verified ·
1 Parent(s): 7acf715

Model save

Browse files
Files changed (1) hide show
  1. README.md +78 -0
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ - precision
10
+ - recall
11
+ model-index:
12
+ - name: BERT_Text_classification_noisy
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # BERT_Text_classification_noisy
20
+
21
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.4823
24
+ - Accuracy: 0.8880
25
+ - F1: 0.8776
26
+ - Precision: 0.8835
27
+ - Recall: 0.8779
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 5e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 32
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_steps: 100
53
+ - num_epochs: 3
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
59
+ | 1.7338 | 0.24 | 50 | 1.4138 | 0.7076 | 0.6300 | 0.5892 | 0.6828 |
60
+ | 0.9336 | 0.48 | 100 | 0.5276 | 0.8361 | 0.8305 | 0.8407 | 0.8303 |
61
+ | 0.5885 | 0.71 | 150 | 0.4815 | 0.8603 | 0.8541 | 0.8583 | 0.8525 |
62
+ | 0.6172 | 0.95 | 200 | 0.5176 | 0.8777 | 0.8648 | 0.8712 | 0.8664 |
63
+ | 0.5229 | 1.19 | 250 | 0.4818 | 0.8809 | 0.8709 | 0.8769 | 0.8707 |
64
+ | 0.4757 | 1.43 | 300 | 0.4845 | 0.8827 | 0.8720 | 0.8786 | 0.8722 |
65
+ | 0.4286 | 1.67 | 350 | 0.4231 | 0.8854 | 0.8759 | 0.8776 | 0.8758 |
66
+ | 0.4837 | 1.9 | 400 | 0.4763 | 0.8907 | 0.8794 | 0.8864 | 0.8799 |
67
+ | 0.4031 | 2.14 | 450 | 0.4539 | 0.8880 | 0.8766 | 0.8833 | 0.8773 |
68
+ | 0.4305 | 2.38 | 500 | 0.4775 | 0.8858 | 0.8752 | 0.8806 | 0.8755 |
69
+ | 0.3538 | 2.62 | 550 | 0.4863 | 0.8880 | 0.8771 | 0.8853 | 0.8776 |
70
+ | 0.325 | 2.86 | 600 | 0.4823 | 0.8880 | 0.8776 | 0.8835 | 0.8779 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - Transformers 4.36.2
76
+ - Pytorch 2.1.2+cu121
77
+ - Datasets 2.16.1
78
+ - Tokenizers 0.15.2