Hugging Face's logo

juancavallotti
/
bert_sentence_classifier

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
juancavallotti commited on
Commit
d145ada
·
1 Parent(s): 7ef25d3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - f1
7
+ - precision
8
+ - recall
9
+ model-index:
10
+ - name: bert_sentence_classifier
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # bert_sentence_classifier
18
+
19
+ This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.4207
22
+ - F1: 0.6163
23
+ - Precision: 0.6163
24
+ - Recall: 0.6163
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 2e-05
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 3
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall |
54
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:---------:|:------:|
55
+ | 1.8231 | 0.12 | 500 | 1.5368 | 0.5776 | 0.5776 | 0.5776 |
56
+ | 1.5269 | 0.25 | 1000 | 1.4710 | 0.5935 | 0.5935 | 0.5935 |
57
+ | 1.5059 | 0.37 | 1500 | 1.4287 | 0.6091 | 0.6091 | 0.6091 |
58
+ | 1.4711 | 0.5 | 2000 | 1.4186 | 0.6106 | 0.6106 | 0.6106 |
59
+ | 1.4269 | 0.62 | 2500 | 1.4154 | 0.6106 | 0.6106 | 0.6106 |
60
+ | 1.4392 | 0.74 | 3000 | 1.4029 | 0.6197 | 0.6197 | 0.6197 |
61
+ | 1.4587 | 0.87 | 3500 | 1.3800 | 0.6216 | 0.6216 | 0.6216 |
62
+ | 1.4519 | 0.99 | 4000 | 1.3790 | 0.6231 | 0.6231 | 0.6231 |
63
+ | 1.2645 | 1.12 | 4500 | 1.3879 | 0.6201 | 0.6201 | 0.6201 |
64
+ | 1.2581 | 1.24 | 5000 | 1.4064 | 0.6186 | 0.6186 | 0.6186 |
65
+ | 1.2425 | 1.36 | 5500 | 1.4008 | 0.6220 | 0.6220 | 0.6220 |
66
+ | 1.2581 | 1.49 | 6000 | 1.3839 | 0.6209 | 0.6209 | 0.6209 |
67
+ | 1.2522 | 1.61 | 6500 | 1.3916 | 0.6224 | 0.6224 | 0.6224 |
68
+ | 1.2675 | 1.73 | 7000 | 1.3816 | 0.6194 | 0.6194 | 0.6194 |
69
+ | 1.2697 | 1.86 | 7500 | 1.3960 | 0.6125 | 0.6125 | 0.6125 |
70
+ | 1.258 | 1.98 | 8000 | 1.3871 | 0.6220 | 0.6220 | 0.6220 |
71
+ | 1.087 | 2.11 | 8500 | 1.4184 | 0.6159 | 0.6159 | 0.6159 |
72
+ | 1.0504 | 2.23 | 9000 | 1.4144 | 0.6201 | 0.6201 | 0.6201 |
73
+ | 1.0649 | 2.35 | 9500 | 1.4304 | 0.6175 | 0.6175 | 0.6175 |
74
+ | 1.0468 | 2.48 | 10000 | 1.4433 | 0.6205 | 0.6205 | 0.6205 |
75
+ | 1.0711 | 2.6 | 10500 | 1.4420 | 0.6099 | 0.6099 | 0.6099 |
76
+ | 1.0684 | 2.73 | 11000 | 1.4280 | 0.6114 | 0.6114 | 0.6114 |
77
+ | 1.0514 | 2.85 | 11500 | 1.4436 | 0.6121 | 0.6121 | 0.6121 |
78
+ | 1.0729 | 2.97 | 12000 | 1.4207 | 0.6163 | 0.6163 | 0.6163 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.19.2
84
+ - Pytorch 1.11.0+cu113
85
+ - Datasets 2.2.2
86
+ - Tokenizers 0.12.1