Hugging Face's logo

vppvgit
/
Finetuned

Fill-Mask
Transformers
PyTorch
bert
Generated from Trainer
Model card Files
xet
 Community
1
vppvgit commited on
Commit
88c927f
·
1 Parent(s): 519b364

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +102 -0
README.md ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - null
6
+ model-index:
7
+ - name: BiblItBERT-1
8
+ results:
9
+ - task:
10
+ name: Masked Language Modeling
11
+ type: fill-mask
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
+ # BiblItBERT-1
18
+
19
+ This model is a fine-tuned version of [dbmdz/bert-base-italian-xxl-cased](https://huggingface.co/dbmdz/bert-base-italian-xxl-cased) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.7784
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: 2e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 0
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 50
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:------:|:---------------:|
52
+ | 1.5764 | 1.0 | 16528 | 1.5214 |
53
+ | 1.4572 | 2.0 | 33056 | 1.4201 |
54
+ | 1.3787 | 3.0 | 49584 | 1.3728 |
55
+ | 1.3451 | 4.0 | 66112 | 1.3245 |
56
+ | 1.3066 | 5.0 | 82640 | 1.2614 |
57
+ | 1.2447 | 6.0 | 99168 | 1.2333 |
58
+ | 1.2172 | 7.0 | 115696 | 1.2149 |
59
+ | 1.2079 | 8.0 | 132224 | 1.1853 |
60
+ | 1.2167 | 9.0 | 148752 | 1.1586 |
61
+ | 1.2056 | 10.0 | 165280 | 1.1503 |
62
+ | 1.1307 | 11.0 | 181808 | 1.1224 |
63
+ | 1.1689 | 12.0 | 198336 | 1.1074 |
64
+ | 1.1007 | 13.0 | 214864 | 1.0924 |
65
+ | 1.0901 | 14.0 | 231392 | 1.0659 |
66
+ | 1.0667 | 15.0 | 247920 | 1.0650 |
67
+ | 1.0434 | 16.0 | 264448 | 1.0362 |
68
+ | 1.0333 | 17.0 | 280976 | 1.0250 |
69
+ | 1.0342 | 18.0 | 297504 | 1.0198 |
70
+ | 1.0059 | 19.0 | 314032 | 0.9950 |
71
+ | 0.9719 | 20.0 | 330560 | 0.9836 |
72
+ | 0.9863 | 21.0 | 347088 | 0.9873 |
73
+ | 0.9781 | 22.0 | 363616 | 0.9724 |
74
+ | 0.9369 | 23.0 | 380144 | 0.9599 |
75
+ | 0.9578 | 24.0 | 396672 | 0.9557 |
76
+ | 0.9253 | 25.0 | 413200 | 0.9400 |
77
+ | 0.9441 | 26.0 | 429728 | 0.9222 |
78
+ | 0.9138 | 27.0 | 446256 | 0.9140 |
79
+ | 0.882 | 28.0 | 462784 | 0.9045 |
80
+ | 0.864 | 29.0 | 479312 | 0.8880 |
81
+ | 0.8632 | 30.0 | 495840 | 0.9023 |
82
+ | 0.8342 | 32.0 | 528896 | 0.8740 |
83
+ | 0.8037 | 34.0 | 561952 | 0.8647 |
84
+ | 0.8119 | 37.0 | 611536 | 0.8358 |
85
+ | 0.8011 | 38.0 | 628064 | 0.8252 |
86
+ | 0.786 | 39.0 | 644592 | 0.8228 |
87
+ | 0.7697 | 41.0 | 677648 | 0.8138 |
88
+ | 0.7485 | 42.0 | 694176 | 0.8104 |
89
+ | 0.7689 | 43.0 | 710704 | 0.8018 |
90
+ | 0.7401 | 45.0 | 743760 | 0.7957 |
91
+ | 0.7031 | 47.0 | 776816 | 0.7726 |
92
+ | 0.7578 | 48.0 | 793344 | 0.7864 |
93
+ | 0.7298 | 49.0 | 809872 | 0.7775 |
94
+ | 0.707 | 50.0 | 826400 | 0.7784 |
95
+
96
+
97
+ ### Framework versions
98
+
99
+ - Transformers 4.10.3
100
+ - Pytorch 1.9.0+cu102
101
+ - Datasets 1.12.1
102
+ - Tokenizers 0.10.3