Hugging Face's logo

liwii
/
factual-consistency-regression-ja

Transformers
PyTorch
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
liwii commited on
Commit
bab540c
•
1 Parent(s): 288f37a

factual-consistency-regression-ja

Browse files
Files changed (1) hide show
  1. README.md +157 -0
README.md ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: line-corporation/line-distilbert-base-japanese
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: line-corporation/line-distilbert-base-japanese
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # line-corporation/line-distilbert-base-japanese
15
+
16
+ This model is a fine-tuned version of [line-corporation/line-distilbert-base-japanese](https://huggingface.co/line-corporation/line-distilbert-base-japanese) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0615
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 1e-05
38
+ - train_batch_size: 64
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - distributed_type: tpu
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 100
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:---------------:|
50
+ | No log | 1.0 | 306 | 0.0856 |
51
+ | 0.1041 | 2.0 | 612 | 0.0819 |
52
+ | 0.1041 | 3.0 | 918 | 0.0795 |
53
+ | 0.0919 | 4.0 | 1224 | 0.0781 |
54
+ | 0.0876 | 5.0 | 1530 | 0.0770 |
55
+ | 0.0876 | 6.0 | 1836 | 0.0758 |
56
+ | 0.0845 | 7.0 | 2142 | 0.0751 |
57
+ | 0.0845 | 8.0 | 2448 | 0.0750 |
58
+ | 0.083 | 9.0 | 2754 | 0.0737 |
59
+ | 0.0809 | 10.0 | 3060 | 0.0732 |
60
+ | 0.0809 | 11.0 | 3366 | 0.0727 |
61
+ | 0.0802 | 12.0 | 3672 | 0.0722 |
62
+ | 0.0802 | 13.0 | 3978 | 0.0717 |
63
+ | 0.0797 | 14.0 | 4284 | 0.0721 |
64
+ | 0.078 | 15.0 | 4590 | 0.0711 |
65
+ | 0.078 | 16.0 | 4896 | 0.0707 |
66
+ | 0.0765 | 17.0 | 5202 | 0.0703 |
67
+ | 0.0774 | 18.0 | 5508 | 0.0699 |
68
+ | 0.0774 | 19.0 | 5814 | 0.0698 |
69
+ | 0.0762 | 20.0 | 6120 | 0.0696 |
70
+ | 0.0762 | 21.0 | 6426 | 0.0692 |
71
+ | 0.0756 | 22.0 | 6732 | 0.0691 |
72
+ | 0.0756 | 23.0 | 7038 | 0.0688 |
73
+ | 0.0756 | 24.0 | 7344 | 0.0687 |
74
+ | 0.075 | 25.0 | 7650 | 0.0680 |
75
+ | 0.075 | 26.0 | 7956 | 0.0680 |
76
+ | 0.0742 | 27.0 | 8262 | 0.0678 |
77
+ | 0.0738 | 28.0 | 8568 | 0.0677 |
78
+ | 0.0738 | 29.0 | 8874 | 0.0672 |
79
+ | 0.0742 | 30.0 | 9180 | 0.0673 |
80
+ | 0.0742 | 31.0 | 9486 | 0.0669 |
81
+ | 0.0733 | 32.0 | 9792 | 0.0669 |
82
+ | 0.0732 | 33.0 | 10098 | 0.0667 |
83
+ | 0.0732 | 34.0 | 10404 | 0.0664 |
84
+ | 0.0722 | 35.0 | 10710 | 0.0665 |
85
+ | 0.0728 | 36.0 | 11016 | 0.0662 |
86
+ | 0.0728 | 37.0 | 11322 | 0.0660 |
87
+ | 0.0719 | 38.0 | 11628 | 0.0659 |
88
+ | 0.0719 | 39.0 | 11934 | 0.0655 |
89
+ | 0.072 | 40.0 | 12240 | 0.0655 |
90
+ | 0.0721 | 41.0 | 12546 | 0.0654 |
91
+ | 0.0721 | 42.0 | 12852 | 0.0651 |
92
+ | 0.0711 | 43.0 | 13158 | 0.0651 |
93
+ | 0.0711 | 44.0 | 13464 | 0.0649 |
94
+ | 0.0715 | 45.0 | 13770 | 0.0651 |
95
+ | 0.0709 | 46.0 | 14076 | 0.0645 |
96
+ | 0.0709 | 47.0 | 14382 | 0.0644 |
97
+ | 0.0706 | 48.0 | 14688 | 0.0644 |
98
+ | 0.0706 | 49.0 | 14994 | 0.0642 |
99
+ | 0.0703 | 50.0 | 15300 | 0.0642 |
100
+ | 0.0706 | 51.0 | 15606 | 0.0641 |
101
+ | 0.0706 | 52.0 | 15912 | 0.0641 |
102
+ | 0.07 | 53.0 | 16218 | 0.0638 |
103
+ | 0.07 | 54.0 | 16524 | 0.0635 |
104
+ | 0.07 | 55.0 | 16830 | 0.0634 |
105
+ | 0.0695 | 56.0 | 17136 | 0.0634 |
106
+ | 0.0695 | 57.0 | 17442 | 0.0634 |
107
+ | 0.0701 | 58.0 | 17748 | 0.0633 |
108
+ | 0.0696 | 59.0 | 18054 | 0.0630 |
109
+ | 0.0696 | 60.0 | 18360 | 0.0637 |
110
+ | 0.0688 | 61.0 | 18666 | 0.0630 |
111
+ | 0.0688 | 62.0 | 18972 | 0.0629 |
112
+ | 0.0691 | 63.0 | 19278 | 0.0628 |
113
+ | 0.0692 | 64.0 | 19584 | 0.0627 |
114
+ | 0.0692 | 65.0 | 19890 | 0.0630 |
115
+ | 0.0694 | 66.0 | 20196 | 0.0625 |
116
+ | 0.0687 | 67.0 | 20502 | 0.0628 |
117
+ | 0.0687 | 68.0 | 20808 | 0.0623 |
118
+ | 0.0696 | 69.0 | 21114 | 0.0625 |
119
+ | 0.0696 | 70.0 | 21420 | 0.0624 |
120
+ | 0.0675 | 71.0 | 21726 | 0.0624 |
121
+ | 0.0688 | 72.0 | 22032 | 0.0622 |
122
+ | 0.0688 | 73.0 | 22338 | 0.0622 |
123
+ | 0.0682 | 74.0 | 22644 | 0.0621 |
124
+ | 0.0682 | 75.0 | 22950 | 0.0620 |
125
+ | 0.0683 | 76.0 | 23256 | 0.0620 |
126
+ | 0.0683 | 77.0 | 23562 | 0.0620 |
127
+ | 0.0683 | 78.0 | 23868 | 0.0620 |
128
+ | 0.0679 | 79.0 | 24174 | 0.0620 |
129
+ | 0.0679 | 80.0 | 24480 | 0.0619 |
130
+ | 0.0678 | 81.0 | 24786 | 0.0619 |
131
+ | 0.0679 | 82.0 | 25092 | 0.0618 |
132
+ | 0.0679 | 83.0 | 25398 | 0.0618 |
133
+ | 0.068 | 84.0 | 25704 | 0.0618 |
134
+ | 0.0684 | 85.0 | 26010 | 0.0617 |
135
+ | 0.0684 | 86.0 | 26316 | 0.0616 |
136
+ | 0.0676 | 87.0 | 26622 | 0.0617 |
137
+ | 0.0676 | 88.0 | 26928 | 0.0617 |
138
+ | 0.0676 | 89.0 | 27234 | 0.0617 |
139
+ | 0.0679 | 90.0 | 27540 | 0.0616 |
140
+ | 0.0679 | 91.0 | 27846 | 0.0616 |
141
+ | 0.0677 | 92.0 | 28152 | 0.0616 |
142
+ | 0.0677 | 93.0 | 28458 | 0.0616 |
143
+ | 0.067 | 94.0 | 28764 | 0.0615 |
144
+ | 0.0678 | 95.0 | 29070 | 0.0615 |
145
+ | 0.0678 | 96.0 | 29376 | 0.0615 |
146
+ | 0.067 | 97.0 | 29682 | 0.0615 |
147
+ | 0.067 | 98.0 | 29988 | 0.0615 |
148
+ | 0.0682 | 99.0 | 30294 | 0.0615 |
149
+ | 0.0681 | 100.0 | 30600 | 0.0615 |
150
+
151
+
152
+ ### Framework versions
153
+
154
+ - Transformers 4.34.0
155
+ - Pytorch 2.0.0+cu118
156
+ - Datasets 2.14.5
157
+ - Tokenizers 0.14.0