Hugging Face's logo

simonycl
/
bert-large-uncased-sst-2-32-13-30

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
simonycl commited on
Commit
acd8d3d
•
1 Parent(s): 47423a8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +90 -0
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-large-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: bert-large-uncased-sst-2-32-13-30
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # bert-large-uncased-sst-2-32-13-30
17
+
18
+ This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6452
21
+ - Accuracy: 0.6719
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1.5e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 5
47
+ - num_epochs: 30
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 2 | 0.7180 | 0.4688 |
54
+ | No log | 2.0 | 4 | 0.7071 | 0.4688 |
55
+ | No log | 3.0 | 6 | 0.6996 | 0.5469 |
56
+ | No log | 4.0 | 8 | 0.6827 | 0.5625 |
57
+ | 0.6456 | 5.0 | 10 | 0.6712 | 0.5469 |
58
+ | 0.6456 | 6.0 | 12 | 0.6542 | 0.6094 |
59
+ | 0.6456 | 7.0 | 14 | 0.6525 | 0.6719 |
60
+ | 0.6456 | 8.0 | 16 | 0.6535 | 0.6875 |
61
+ | 0.6456 | 9.0 | 18 | 0.6454 | 0.6406 |
62
+ | 0.4153 | 10.0 | 20 | 0.6414 | 0.625 |
63
+ | 0.4153 | 11.0 | 22 | 0.6470 | 0.6094 |
64
+ | 0.4153 | 12.0 | 24 | 0.6509 | 0.6094 |
65
+ | 0.4153 | 13.0 | 26 | 0.6489 | 0.6094 |
66
+ | 0.4153 | 14.0 | 28 | 0.6498 | 0.6094 |
67
+ | 0.238 | 15.0 | 30 | 0.6514 | 0.6094 |
68
+ | 0.238 | 16.0 | 32 | 0.6440 | 0.6562 |
69
+ | 0.238 | 17.0 | 34 | 0.6432 | 0.6719 |
70
+ | 0.238 | 18.0 | 36 | 0.6497 | 0.6719 |
71
+ | 0.238 | 19.0 | 38 | 0.6569 | 0.6406 |
72
+ | 0.1523 | 20.0 | 40 | 0.6636 | 0.6094 |
73
+ | 0.1523 | 21.0 | 42 | 0.6692 | 0.5781 |
74
+ | 0.1523 | 22.0 | 44 | 0.6740 | 0.5625 |
75
+ | 0.1523 | 23.0 | 46 | 0.6708 | 0.5625 |
76
+ | 0.1523 | 24.0 | 48 | 0.6632 | 0.6094 |
77
+ | 0.1187 | 25.0 | 50 | 0.6596 | 0.6406 |
78
+ | 0.1187 | 26.0 | 52 | 0.6560 | 0.6562 |
79
+ | 0.1187 | 27.0 | 54 | 0.6517 | 0.6719 |
80
+ | 0.1187 | 28.0 | 56 | 0.6482 | 0.6875 |
81
+ | 0.1187 | 29.0 | 58 | 0.6462 | 0.6875 |
82
+ | 0.09 | 30.0 | 60 | 0.6452 | 0.6719 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.32.0.dev0
88
+ - Pytorch 2.0.1+cu118
89
+ - Datasets 2.4.0
90
+ - Tokenizers 0.13.3