Hugging Face's logo

AT
/
distilroberta-base-finetuned-wikitext2

Fill-Mask
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Model card Files Metrics Community
2
AT commited on
Commit
c777613
·
1 Parent(s): 00c9f9b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +82 -12
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.0081
18
 
19
  ## Model description
20
 
@@ -39,22 +39,92 @@ The following hyperparameters were used during training:
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
- - num_epochs: 10.0
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 0.0325 | 1.0 | 24 | 0.0498 |
49
- | 0.0297 | 2.0 | 48 | 0.0466 |
50
- | 0.0141 | 3.0 | 72 | 0.0375 |
51
- | 0.0177 | 4.0 | 96 | 0.0293 |
52
- | 0.007 | 5.0 | 120 | 0.0166 |
53
- | 0.0019 | 6.0 | 144 | 0.0120 |
54
- | 0.0038 | 7.0 | 168 | 0.0094 |
55
- | 0.0013 | 8.0 | 192 | 0.0084 |
56
- | 0.0053 | 9.0 | 216 | 0.0084 |
57
- | 0.0025 | 10.0 | 240 | 0.0081 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.0047
18
 
19
  ## Model description
20
 
 
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
+ - num_epochs: 80.0
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 0.079 | 1.0 | 24 | 0.0748 |
49
+ | 0.045 | 2.0 | 48 | 0.0507 |
50
+ | 0.0253 | 3.0 | 72 | 0.0494 |
51
+ | 0.0285 | 4.0 | 96 | 0.0469 |
52
+ | 0.0189 | 5.0 | 120 | 0.0319 |
53
+ | 0.0014 | 6.0 | 144 | 0.0220 |
54
+ | 0.0023 | 7.0 | 168 | 0.0108 |
55
+ | 0.0012 | 8.0 | 192 | 0.0079 |
56
+ | 0.0067 | 9.0 | 216 | 0.0061 |
57
+ | 0.0006 | 10.0 | 240 | 0.0099 |
58
+ | 0.0004 | 11.0 | 264 | 0.0067 |
59
+ | 0.0007 | 12.0 | 288 | 0.0060 |
60
+ | 0.0005 | 13.0 | 312 | 0.0050 |
61
+ | 0.0005 | 14.0 | 336 | 0.0050 |
62
+ | 0.0005 | 15.0 | 360 | 0.0046 |
63
+ | 0.0001 | 16.0 | 384 | 0.0052 |
64
+ | 0.0001 | 17.0 | 408 | 0.0047 |
65
+ | 0.0001 | 18.0 | 432 | 0.0046 |
66
+ | 0.0001 | 19.0 | 456 | 0.0050 |
67
+ | 0.0001 | 20.0 | 480 | 0.0046 |
68
+ | 0.0001 | 21.0 | 504 | 0.0046 |
69
+ | 0.0007 | 22.0 | 528 | 0.0046 |
70
+ | 0.0001 | 23.0 | 552 | 0.0046 |
71
+ | 0.0001 | 24.0 | 576 | 0.0049 |
72
+ | 0.0001 | 25.0 | 600 | 0.0043 |
73
+ | 0.0001 | 26.0 | 624 | 0.0046 |
74
+ | 0.0 | 27.0 | 648 | 0.0044 |
75
+ | 0.0001 | 28.0 | 672 | 0.0045 |
76
+ | 0.0001 | 29.0 | 696 | 0.0045 |
77
+ | 0.0002 | 30.0 | 720 | 0.0044 |
78
+ | 0.0 | 31.0 | 744 | 0.0044 |
79
+ | 0.0001 | 32.0 | 768 | 0.0044 |
80
+ | 0.0 | 33.0 | 792 | 0.0044 |
81
+ | 0.0001 | 34.0 | 816 | 0.0050 |
82
+ | 0.0001 | 35.0 | 840 | 0.0050 |
83
+ | 0.0002 | 36.0 | 864 | 0.0049 |
84
+ | 0.0 | 37.0 | 888 | 0.0048 |
85
+ | 0.0 | 38.0 | 912 | 0.0054 |
86
+ | 0.0 | 39.0 | 936 | 0.0048 |
87
+ | 0.0 | 40.0 | 960 | 0.0047 |
88
+ | 0.0002 | 41.0 | 984 | 0.0048 |
89
+ | 0.0 | 42.0 | 1008 | 0.0068 |
90
+ | 0.0 | 43.0 | 1032 | 0.0051 |
91
+ | 0.0002 | 44.0 | 1056 | 0.0049 |
92
+ | 0.0 | 45.0 | 1080 | 0.0049 |
93
+ | 0.0 | 46.0 | 1104 | 0.0048 |
94
+ | 0.0 | 47.0 | 1128 | 0.0046 |
95
+ | 0.0 | 48.0 | 1152 | 0.0046 |
96
+ | 0.0 | 49.0 | 1176 | 0.0048 |
97
+ | 0.0 | 50.0 | 1200 | 0.0049 |
98
+ | 0.0 | 51.0 | 1224 | 0.0047 |
99
+ | 0.0 | 52.0 | 1248 | 0.0046 |
100
+ | 0.0001 | 53.0 | 1272 | 0.0046 |
101
+ | 0.0 | 54.0 | 1296 | 0.0045 |
102
+ | 0.0 | 55.0 | 1320 | 0.0045 |
103
+ | 0.0 | 56.0 | 1344 | 0.0046 |
104
+ | 0.0 | 57.0 | 1368 | 0.0046 |
105
+ | 0.0 | 58.0 | 1392 | 0.0046 |
106
+ | 0.0 | 59.0 | 1416 | 0.0046 |
107
+ | 0.0 | 60.0 | 1440 | 0.0046 |
108
+ | 0.0 | 61.0 | 1464 | 0.0047 |
109
+ | 0.0 | 62.0 | 1488 | 0.0047 |
110
+ | 0.0 | 63.0 | 1512 | 0.0047 |
111
+ | 0.0 | 64.0 | 1536 | 0.0046 |
112
+ | 0.0 | 65.0 | 1560 | 0.0045 |
113
+ | 0.0 | 66.0 | 1584 | 0.0045 |
114
+ | 0.0 | 67.0 | 1608 | 0.0046 |
115
+ | 0.0 | 68.0 | 1632 | 0.0047 |
116
+ | 0.0 | 69.0 | 1656 | 0.0048 |
117
+ | 0.0001 | 70.0 | 1680 | 0.0048 |
118
+ | 0.0 | 71.0 | 1704 | 0.0048 |
119
+ | 0.0 | 72.0 | 1728 | 0.0047 |
120
+ | 0.0001 | 73.0 | 1752 | 0.0049 |
121
+ | 0.0 | 74.0 | 1776 | 0.0048 |
122
+ | 0.0 | 75.0 | 1800 | 0.0048 |
123
+ | 0.0 | 76.0 | 1824 | 0.0047 |
124
+ | 0.0 | 77.0 | 1848 | 0.0047 |
125
+ | 0.0 | 78.0 | 1872 | 0.0047 |
126
+ | 0.0 | 79.0 | 1896 | 0.0047 |
127
+ | 0.0 | 80.0 | 1920 | 0.0047 |
128
 
129
 
130
  ### Framework versions