Hugging Face's logo

datarpit
/
toy

Question Answering
Transformers
PyTorch
distilbert
Generated from Trainer
Model card Files
xet
Community
2
datarpit commited on
Commit
9ffd6ea
路
1 Parent(s): 7b2718e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +56 -16
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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.2041
18
 
19
  ## Model description
20
 
@@ -34,27 +34,67 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
- - train_batch_size: 2
38
- - eval_batch_size: 2
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
43
 
44
  ### Training results
45
 
46
- | Training Loss | Epoch | Step | Validation Loss |
47
- |:-------------:|:-----:|:----:|:---------------:|
48
- | 0.3125 | 1.0 | 923 | 0.2391 |
49
- | 0.3287 | 2.0 | 1846 | 0.2306 |
50
- | 0.1138 | 3.0 | 2769 | 0.1806 |
51
- | 0.1219 | 4.0 | 3692 | 0.1858 |
52
- | 0.0962 | 5.0 | 4615 | 0.1922 |
53
- | 0.0526 | 6.0 | 5538 | 0.1963 |
54
- | 0.0248 | 7.0 | 6461 | 0.1930 |
55
- | 0.0004 | 8.0 | 7384 | 0.2153 |
56
- | 0.0136 | 9.0 | 8307 | 0.2037 |
57
- | 0.0002 | 10.0 | 9230 | 0.2041 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.2124
18
 
19
  ## Model description
20
 
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
+ - num_epochs: 50
43
 
44
  ### Training results
45
 
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:-----:|:---------------:|
48
+ | 0.4798 | 1.0 | 231 | 0.2252 |
49
+ | 0.3378 | 2.0 | 462 | 0.1777 |
50
+ | 0.1024 | 3.0 | 693 | 0.1586 |
51
+ | 0.0736 | 4.0 | 924 | 0.1664 |
52
+ | 0.1237 | 5.0 | 1155 | 0.1692 |
53
+ | 0.1049 | 6.0 | 1386 | 0.1818 |
54
+ | 0.0239 | 7.0 | 1617 | 0.2127 |
55
+ | 0.0036 | 8.0 | 1848 | 0.1888 |
56
+ | 0.0051 | 9.0 | 2079 | 0.2061 |
57
+ | 0.0003 | 10.0 | 2310 | 0.1905 |
58
+ | 0.0005 | 11.0 | 2541 | 0.2011 |
59
+ | 0.0003 | 12.0 | 2772 | 0.1928 |
60
+ | 0.0029 | 13.0 | 3003 | 0.2563 |
61
+ | 0.0002 | 14.0 | 3234 | 0.2076 |
62
+ | 0.0002 | 15.0 | 3465 | 0.1980 |
63
+ | 0.0001 | 16.0 | 3696 | 0.2013 |
64
+ | 0.0001 | 17.0 | 3927 | 0.2089 |
65
+ | 0.0001 | 18.0 | 4158 | 0.1984 |
66
+ | 0.0001 | 19.0 | 4389 | 0.2017 |
67
+ | 0.0001 | 20.0 | 4620 | 0.2013 |
68
+ | 0.0001 | 21.0 | 4851 | 0.2142 |
69
+ | 0.0001 | 22.0 | 5082 | 0.1943 |
70
+ | 0.0001 | 23.0 | 5313 | 0.2003 |
71
+ | 0.0 | 24.0 | 5544 | 0.2015 |
72
+ | 0.0001 | 25.0 | 5775 | 0.2031 |
73
+ | 0.0002 | 26.0 | 6006 | 0.2600 |
74
+ | 0.0022 | 27.0 | 6237 | 0.2269 |
75
+ | 0.0 | 28.0 | 6468 | 0.2125 |
76
+ | 0.0 | 29.0 | 6699 | 0.2172 |
77
+ | 0.0 | 30.0 | 6930 | 0.2185 |
78
+ | 0.0 | 31.0 | 7161 | 0.2004 |
79
+ | 0.0 | 32.0 | 7392 | 0.2077 |
80
+ | 0.0 | 33.0 | 7623 | 0.2333 |
81
+ | 0.0003 | 34.0 | 7854 | 0.2102 |
82
+ | 0.0 | 35.0 | 8085 | 0.2095 |
83
+ | 0.0 | 36.0 | 8316 | 0.2030 |
84
+ | 0.0 | 37.0 | 8547 | 0.2038 |
85
+ | 0.0 | 38.0 | 8778 | 0.2062 |
86
+ | 0.0 | 39.0 | 9009 | 0.2080 |
87
+ | 0.0 | 40.0 | 9240 | 0.2083 |
88
+ | 0.0 | 41.0 | 9471 | 0.2063 |
89
+ | 0.0 | 42.0 | 9702 | 0.2146 |
90
+ | 0.0 | 43.0 | 9933 | 0.2168 |
91
+ | 0.0 | 44.0 | 10164 | 0.2112 |
92
+ | 0.0 | 45.0 | 10395 | 0.2109 |
93
+ | 0.0 | 46.0 | 10626 | 0.2116 |
94
+ | 0.0 | 47.0 | 10857 | 0.2122 |
95
+ | 0.0 | 48.0 | 11088 | 0.2122 |
96
+ | 0.0 | 49.0 | 11319 | 0.2124 |
97
+ | 0.0 | 50.0 | 11550 | 0.2124 |
98
 
99
 
100
  ### Framework versions