Hugging Face's logo

jojoUla
/
bert-large-uncased-finetuned-lowR100-4-uncased-DA-20

Fill-Mask
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
jojoUla commited on
Commit
2403e79
•
1 Parent(s): b77fb7b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: bert-large-uncased-finetuned-lowR100-4-uncased-DA-20
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # bert-large-uncased-finetuned-lowR100-4-uncased-DA-20
14
+
15
+ This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 2.2624
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 30
38
+ - eval_batch_size: 30
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 40.0
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 1 | 5.4063 |
50
+ | 5.9654 | 2.0 | 2 | 6.1913 |
51
+ | 5.9654 | 3.0 | 3 | 5.8608 |
52
+ | 5.5864 | 4.0 | 4 | 4.4613 |
53
+ | 5.5864 | 5.0 | 5 | 5.0257 |
54
+ | 5.1093 | 6.0 | 6 | 4.7405 |
55
+ | 5.1093 | 7.0 | 7 | 4.7516 |
56
+ | 4.3965 | 8.0 | 8 | 3.1646 |
57
+ | 4.3965 | 9.0 | 9 | 3.7378 |
58
+ | 3.7825 | 10.0 | 10 | 2.0073 |
59
+ | 3.7825 | 11.0 | 11 | 5.5725 |
60
+ | 3.009 | 12.0 | 12 | 3.0077 |
61
+ | 3.009 | 13.0 | 13 | 2.6288 |
62
+ | 2.7427 | 14.0 | 14 | 2.8630 |
63
+ | 2.7427 | 15.0 | 15 | 2.3270 |
64
+ | 2.4122 | 16.0 | 16 | 3.3092 |
65
+ | 2.4122 | 17.0 | 17 | 2.7499 |
66
+ | 2.3707 | 18.0 | 18 | 3.2892 |
67
+ | 2.3707 | 19.0 | 19 | 2.9385 |
68
+ | 2.6243 | 20.0 | 20 | 1.5626 |
69
+ | 2.6243 | 21.0 | 21 | 1.0104 |
70
+ | 2.1606 | 22.0 | 22 | 3.3464 |
71
+ | 2.1606 | 23.0 | 23 | 3.9334 |
72
+ | 2.1419 | 24.0 | 24 | 1.7512 |
73
+ | 2.1419 | 25.0 | 25 | 2.5855 |
74
+ | 2.2265 | 26.0 | 26 | 2.2896 |
75
+ | 2.2265 | 27.0 | 27 | 2.3118 |
76
+ | 2.2539 | 28.0 | 28 | 2.9997 |
77
+ | 2.2539 | 29.0 | 29 | 3.0682 |
78
+ | 2.3866 | 30.0 | 30 | 3.3435 |
79
+ | 2.3866 | 31.0 | 31 | 3.5848 |
80
+ | 2.1788 | 32.0 | 32 | 2.4658 |
81
+ | 2.1788 | 33.0 | 33 | 2.4060 |
82
+ | 2.0932 | 34.0 | 34 | 2.8497 |
83
+ | 2.0932 | 35.0 | 35 | 3.8500 |
84
+ | 1.9799 | 36.0 | 36 | 1.9458 |
85
+ | 1.9799 | 37.0 | 37 | 2.4557 |
86
+ | 2.0164 | 38.0 | 38 | 3.3370 |
87
+ | 2.0164 | 39.0 | 39 | 3.6850 |
88
+ | 2.1732 | 40.0 | 40 | 1.7986 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.26.0
94
+ - Pytorch 1.13.1+cu116
95
+ - Datasets 2.9.0
96
+ - Tokenizers 0.13.2