Hugging Face's logo

pengold
/
distilbert-base-vietnamese-case

Fill-Mask
Transformers
PyTorch
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
pengold commited on
Commit
4b0a4b6
•
1 Parent(s): 7051a07

End of training

Browse files
Files changed (2) hide show
  1. README.md +34 -112
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -1,18 +1,11 @@
1
  ---
2
- license: cc-by-4.0
3
  base_model: distilbert-base-cased
4
- language:
5
- - vi
6
  tags:
7
  - generated_from_trainer
8
  model-index:
9
  - name: distilbert-base-vietnamese-case
10
  results: []
11
- widget:
12
- - text: Đà Nẵng là một thành [MASK]
13
- example_title: Example 1
14
- - text: 'Chí Phèo là một nhân [MASK] hư cấu '
15
- example_title: Example 2
16
  ---
17
 
18
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -22,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 3.9239
26
 
27
  ## Model description
28
 
@@ -47,117 +40,46 @@ The following hyperparameters were used during training:
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
- - num_epochs: 100
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
- | 6.1273 | 1.0 | 79 | 6.0333 |
57
- | 5.9095 | 2.0 | 158 | 5.9172 |
58
- | 5.8407 | 3.0 | 237 | 5.7789 |
59
- | 5.7761 | 4.0 | 316 | 5.6779 |
60
- | 5.6909 | 5.0 | 395 | 5.6731 |
61
- | 5.6318 | 6.0 | 474 | 5.5712 |
62
- | 5.5787 | 7.0 | 553 | 5.4994 |
63
- | 5.4948 | 8.0 | 632 | 5.4146 |
64
- | 5.4399 | 9.0 | 711 | 5.3760 |
65
- | 5.3676 | 10.0 | 790 | 5.3624 |
66
- | 5.3691 | 11.0 | 869 | 5.2900 |
67
- | 5.2904 | 12.0 | 948 | 5.3213 |
68
- | 5.228 | 13.0 | 1027 | 5.2162 |
69
- | 5.2384 | 14.0 | 1106 | 5.2232 |
70
- | 5.1101 | 15.0 | 1185 | 5.1858 |
71
- | 5.1316 | 16.0 | 1264 | 4.9780 |
72
- | 5.0517 | 17.0 | 1343 | 5.0227 |
73
- | 5.0014 | 18.0 | 1422 | 4.9703 |
74
- | 5.0012 | 19.0 | 1501 | 4.9751 |
75
- | 4.9574 | 20.0 | 1580 | 4.9152 |
76
- | 4.8492 | 21.0 | 1659 | 4.8699 |
77
- | 4.8717 | 22.0 | 1738 | 4.8291 |
78
- | 4.8014 | 23.0 | 1817 | 4.8247 |
79
- | 4.7941 | 24.0 | 1896 | 4.7314 |
80
- | 4.7218 | 25.0 | 1975 | 4.8128 |
81
- | 4.6991 | 26.0 | 2054 | 4.7312 |
82
- | 4.695 | 27.0 | 2133 | 4.6820 |
83
- | 4.6339 | 28.0 | 2212 | 4.6659 |
84
- | 4.5968 | 29.0 | 2291 | 4.6682 |
85
- | 4.581 | 30.0 | 2370 | 4.5671 |
86
- | 4.5606 | 31.0 | 2449 | 4.5874 |
87
- | 4.4842 | 32.0 | 2528 | 4.4972 |
88
- | 4.5101 | 33.0 | 2607 | 4.5457 |
89
- | 4.4482 | 34.0 | 2686 | 4.4926 |
90
- | 4.4563 | 35.0 | 2765 | 4.4372 |
91
- | 4.4161 | 36.0 | 2844 | 4.3623 |
92
- | 4.3537 | 37.0 | 2923 | 4.4122 |
93
- | 4.3775 | 38.0 | 3002 | 4.3519 |
94
- | 4.3519 | 39.0 | 3081 | 4.3866 |
95
- | 4.3392 | 40.0 | 3160 | 4.3779 |
96
- | 4.3011 | 41.0 | 3239 | 4.3855 |
97
- | 4.2702 | 42.0 | 3318 | 4.2953 |
98
- | 4.2614 | 43.0 | 3397 | 4.3726 |
99
- | 4.2464 | 44.0 | 3476 | 4.3147 |
100
- | 4.1984 | 45.0 | 3555 | 4.2556 |
101
- | 4.2463 | 46.0 | 3634 | 4.2224 |
102
- | 4.1559 | 47.0 | 3713 | 4.1839 |
103
- | 4.1859 | 48.0 | 3792 | 4.2830 |
104
- | 4.1063 | 49.0 | 3871 | 4.1803 |
105
- | 4.1222 | 50.0 | 3950 | 4.1545 |
106
- | 4.1423 | 51.0 | 4029 | 4.2308 |
107
- | 4.0657 | 52.0 | 4108 | 4.1227 |
108
- | 4.1018 | 53.0 | 4187 | 4.1687 |
109
- | 4.0689 | 54.0 | 4266 | 4.1626 |
110
- | 4.0676 | 55.0 | 4345 | 4.1790 |
111
- | 4.0127 | 56.0 | 4424 | 4.0618 |
112
- | 4.066 | 57.0 | 4503 | 4.0780 |
113
- | 3.9994 | 58.0 | 4582 | 4.1382 |
114
- | 4.0002 | 59.0 | 4661 | 4.0318 |
115
- | 4.0064 | 60.0 | 4740 | 4.0891 |
116
- | 3.9681 | 61.0 | 4819 | 4.0633 |
117
- | 3.9608 | 62.0 | 4898 | 4.0223 |
118
- | 3.9544 | 63.0 | 4977 | 4.0722 |
119
- | 3.97 | 64.0 | 5056 | 4.0127 |
120
- | 3.913 | 65.0 | 5135 | 3.9915 |
121
- | 3.9177 | 66.0 | 5214 | 4.0256 |
122
- | 3.9388 | 67.0 | 5293 | 3.9830 |
123
- | 3.9429 | 68.0 | 5372 | 4.0162 |
124
- | 3.9036 | 69.0 | 5451 | 4.0515 |
125
- | 3.8851 | 70.0 | 5530 | 3.9716 |
126
- | 3.8894 | 71.0 | 5609 | 3.9939 |
127
- | 3.896 | 72.0 | 5688 | 3.9699 |
128
- | 3.8893 | 73.0 | 5767 | 3.9772 |
129
- | 3.8648 | 74.0 | 5846 | 4.0543 |
130
- | 3.8511 | 75.0 | 5925 | 3.9879 |
131
- | 3.8286 | 76.0 | 6004 | 3.9393 |
132
- | 3.851 | 77.0 | 6083 | 4.0088 |
133
- | 3.8407 | 78.0 | 6162 | 3.9580 |
134
- | 3.8391 | 79.0 | 6241 | 3.9453 |
135
- | 3.8537 | 80.0 | 6320 | 3.9377 |
136
- | 3.823 | 81.0 | 6399 | 3.9423 |
137
- | 3.8395 | 82.0 | 6478 | 3.9240 |
138
- | 3.7859 | 83.0 | 6557 | 3.8921 |
139
- | 3.8177 | 84.0 | 6636 | 3.9167 |
140
- | 3.7862 | 85.0 | 6715 | 3.9479 |
141
- | 3.7978 | 86.0 | 6794 | 3.9230 |
142
- | 3.7939 | 87.0 | 6873 | 3.9401 |
143
- | 3.8006 | 88.0 | 6952 | 3.9525 |
144
- | 3.7697 | 89.0 | 7031 | 3.9304 |
145
- | 3.7914 | 90.0 | 7110 | 3.8875 |
146
- | 3.7799 | 91.0 | 7189 | 3.8851 |
147
- | 3.812 | 92.0 | 7268 | 3.9349 |
148
- | 3.7942 | 93.0 | 7347 | 3.8931 |
149
- | 3.7671 | 94.0 | 7426 | 3.8653 |
150
- | 3.7654 | 95.0 | 7505 | 3.8282 |
151
- | 3.7648 | 96.0 | 7584 | 3.8408 |
152
- | 3.8011 | 97.0 | 7663 | 3.8898 |
153
- | 3.7781 | 98.0 | 7742 | 3.9560 |
154
- | 3.8056 | 99.0 | 7821 | 3.8882 |
155
- | 3.7749 | 100.0 | 7900 | 3.9239 |
156
 
157
 
158
  ### Framework versions
159
 
160
  - Transformers 4.33.2
161
- - Pytorch 2.0.1+cu118
162
  - Datasets 2.14.5
163
- - Tokenizers 0.13.3
 
1
  ---
2
+ license: apache-2.0
3
  base_model: distilbert-base-cased
 
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
  - name: distilbert-base-vietnamese-case
8
  results: []
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
15
 
16
  This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 3.1978
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 1000
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 6.6995 | 1.0 | 313 | 5.7838 |
50
+ | 5.7246 | 2.0 | 626 | 5.5341 |
51
+ | 5.4565 | 3.0 | 939 | 5.3280 |
52
+ | 5.271 | 4.0 | 1252 | 5.1409 |
53
+ | 5.0514 | 5.0 | 1565 | 4.9143 |
54
+ | 4.874 | 6.0 | 1878 | 4.7130 |
55
+ | 4.7083 | 7.0 | 2191 | 4.5682 |
56
+ | 4.5677 | 8.0 | 2504 | 4.3724 |
57
+ | 4.4244 | 9.0 | 2817 | 4.3262 |
58
+ | 4.3013 | 10.0 | 3130 | 4.1231 |
59
+ | 4.2077 | 11.0 | 3443 | 4.1388 |
60
+ | 4.1103 | 12.0 | 3756 | 3.8696 |
61
+ | 4.0141 | 13.0 | 4069 | 3.8849 |
62
+ | 3.9435 | 14.0 | 4382 | 3.7311 |
63
+ | 3.8604 | 15.0 | 4695 | 3.7155 |
64
+ | 3.804 | 16.0 | 5008 | 3.6445 |
65
+ | 3.7076 | 17.0 | 5321 | 3.5784 |
66
+ | 3.6807 | 18.0 | 5634 | 3.5516 |
67
+ | 3.6239 | 19.0 | 5947 | 3.4008 |
68
+ | 3.5729 | 20.0 | 6260 | 3.4827 |
69
+ | 3.5308 | 21.0 | 6573 | 3.3921 |
70
+ | 3.4707 | 22.0 | 6886 | 3.3729 |
71
+ | 3.4341 | 23.0 | 7199 | 3.3543 |
72
+ | 3.3989 | 24.0 | 7512 | 3.2836 |
73
+ | 3.3505 | 25.0 | 7825 | 3.3003 |
74
+ | 3.3256 | 26.0 | 8138 | 3.1750 |
75
+ | 3.2892 | 27.0 | 8451 | 3.1930 |
76
+ | 3.2614 | 28.0 | 8764 | 3.2089 |
77
+ | 3.2387 | 29.0 | 9077 | 3.1978 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
81
 
82
  - Transformers 4.33.2
83
+ - Pytorch 2.0.1+cu117
84
  - Datasets 2.14.5
85
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1672aa7c6a41f2a998b417467a2e09346fcd157e9eed3f801a2a379a2f5746b4
3
  size 263284081
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa1d7268b702edbb7273b762f253c7e060f3a52cc7741063cca6fedc9c52e8a
3
  size 263284081