Hugging Face's logo

MattiaParavisi
/
distilbert-base-uncased-finetuned-dob

Fill-Mask
Transformers
PyTorch
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
MattiaParavisi commited on
Commit
da6f3b9
•
1 Parent(s): 209be63

End of training

Browse files
Files changed (1) hide show
  1. README.md +103 -103
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0004
19
 
20
  ## Model description
21
 
@@ -46,111 +46,111 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 0.5695 | 1.0 | 10 | 0.3778 |
50
- | 0.3413 | 2.0 | 20 | 0.1809 |
51
- | 0.1647 | 3.0 | 30 | 0.0799 |
52
- | 0.0795 | 4.0 | 40 | 0.0308 |
53
- | 0.0348 | 5.0 | 50 | 0.0063 |
54
- | 0.0087 | 6.0 | 60 | 0.0029 |
55
- | 0.0034 | 7.0 | 70 | 0.0020 |
56
- | 0.0021 | 8.0 | 80 | 0.0016 |
57
- | 0.0013 | 9.0 | 90 | 0.0014 |
58
- | 0.0011 | 10.0 | 100 | 0.0013 |
59
- | 0.001 | 11.0 | 110 | 0.0012 |
60
- | 0.0009 | 12.0 | 120 | 0.0011 |
61
- | 0.0009 | 13.0 | 130 | 0.0011 |
62
- | 0.0008 | 14.0 | 140 | 0.0010 |
63
- | 0.0007 | 15.0 | 150 | 0.0010 |
64
- | 0.0007 | 16.0 | 160 | 0.0009 |
65
- | 0.0006 | 17.0 | 170 | 0.0009 |
66
- | 0.0006 | 18.0 | 180 | 0.0009 |
67
- | 0.0005 | 19.0 | 190 | 0.0009 |
68
- | 0.0005 | 20.0 | 200 | 0.0008 |
69
- | 0.0005 | 21.0 | 210 | 0.0008 |
70
- | 0.0005 | 22.0 | 220 | 0.0008 |
71
- | 0.0004 | 23.0 | 230 | 0.0008 |
72
- | 0.0004 | 24.0 | 240 | 0.0008 |
73
- | 0.0004 | 25.0 | 250 | 0.0007 |
74
- | 0.0004 | 26.0 | 260 | 0.0007 |
75
- | 0.0004 | 27.0 | 270 | 0.0007 |
76
- | 0.0004 | 28.0 | 280 | 0.0007 |
77
- | 0.0004 | 29.0 | 290 | 0.0007 |
78
- | 0.0004 | 30.0 | 300 | 0.0007 |
79
- | 0.0003 | 31.0 | 310 | 0.0007 |
80
- | 0.0003 | 32.0 | 320 | 0.0007 |
81
- | 0.0003 | 33.0 | 330 | 0.0007 |
82
- | 0.0003 | 34.0 | 340 | 0.0007 |
83
- | 0.0003 | 35.0 | 350 | 0.0006 |
84
- | 0.0003 | 36.0 | 360 | 0.0006 |
85
- | 0.0003 | 37.0 | 370 | 0.0006 |
86
- | 0.0003 | 38.0 | 380 | 0.0006 |
87
- | 0.0003 | 39.0 | 390 | 0.0006 |
88
- | 0.0003 | 40.0 | 400 | 0.0006 |
89
- | 0.0003 | 41.0 | 410 | 0.0006 |
90
- | 0.0003 | 42.0 | 420 | 0.0006 |
91
- | 0.0003 | 43.0 | 430 | 0.0006 |
92
- | 0.0002 | 44.0 | 440 | 0.0006 |
93
- | 0.0002 | 45.0 | 450 | 0.0006 |
94
- | 0.0002 | 46.0 | 460 | 0.0006 |
95
- | 0.0002 | 47.0 | 470 | 0.0005 |
96
- | 0.0002 | 48.0 | 480 | 0.0005 |
97
- | 0.0002 | 49.0 | 490 | 0.0005 |
98
- | 0.0002 | 50.0 | 500 | 0.0005 |
99
- | 0.0002 | 51.0 | 510 | 0.0005 |
100
- | 0.0002 | 52.0 | 520 | 0.0005 |
101
- | 0.0002 | 53.0 | 530 | 0.0005 |
102
- | 0.0002 | 54.0 | 540 | 0.0005 |
103
- | 0.0002 | 55.0 | 550 | 0.0005 |
104
- | 0.0002 | 56.0 | 560 | 0.0005 |
105
- | 0.0002 | 57.0 | 570 | 0.0005 |
106
- | 0.0002 | 58.0 | 580 | 0.0005 |
107
- | 0.0002 | 59.0 | 590 | 0.0005 |
108
- | 0.0002 | 60.0 | 600 | 0.0005 |
109
- | 0.0002 | 61.0 | 610 | 0.0005 |
110
- | 0.0002 | 62.0 | 620 | 0.0005 |
111
- | 0.0002 | 63.0 | 630 | 0.0005 |
112
- | 0.0002 | 64.0 | 640 | 0.0005 |
113
- | 0.0002 | 65.0 | 650 | 0.0005 |
114
- | 0.0002 | 66.0 | 660 | 0.0005 |
115
- | 0.0002 | 67.0 | 670 | 0.0005 |
116
- | 0.0002 | 68.0 | 680 | 0.0005 |
117
- | 0.0002 | 69.0 | 690 | 0.0005 |
118
- | 0.0002 | 70.0 | 700 | 0.0005 |
119
- | 0.0002 | 71.0 | 710 | 0.0005 |
120
- | 0.0002 | 72.0 | 720 | 0.0004 |
121
- | 0.0002 | 73.0 | 730 | 0.0004 |
122
- | 0.0002 | 74.0 | 740 | 0.0004 |
123
- | 0.0002 | 75.0 | 750 | 0.0004 |
124
- | 0.0002 | 76.0 | 760 | 0.0004 |
125
- | 0.0002 | 77.0 | 770 | 0.0004 |
126
- | 0.0002 | 78.0 | 780 | 0.0004 |
127
- | 0.0002 | 79.0 | 790 | 0.0004 |
128
- | 0.0002 | 80.0 | 800 | 0.0004 |
129
- | 0.0002 | 81.0 | 810 | 0.0004 |
130
- | 0.0002 | 82.0 | 820 | 0.0004 |
131
- | 0.0001 | 83.0 | 830 | 0.0004 |
132
- | 0.0002 | 84.0 | 840 | 0.0004 |
133
- | 0.0001 | 85.0 | 850 | 0.0004 |
134
- | 0.0001 | 86.0 | 860 | 0.0004 |
135
- | 0.0002 | 87.0 | 870 | 0.0004 |
136
- | 0.0001 | 88.0 | 880 | 0.0004 |
137
- | 0.0001 | 89.0 | 890 | 0.0004 |
138
- | 0.0001 | 90.0 | 900 | 0.0004 |
139
- | 0.0002 | 91.0 | 910 | 0.0004 |
140
- | 0.0001 | 92.0 | 920 | 0.0004 |
141
- | 0.0001 | 93.0 | 930 | 0.0004 |
142
- | 0.0001 | 94.0 | 940 | 0.0004 |
143
- | 0.0001 | 95.0 | 950 | 0.0004 |
144
- | 0.0001 | 96.0 | 960 | 0.0004 |
145
- | 0.0001 | 97.0 | 970 | 0.0004 |
146
- | 0.0001 | 98.0 | 980 | 0.0004 |
147
- | 0.0001 | 99.0 | 990 | 0.0004 |
148
- | 0.0001 | 100.0 | 1000 | 0.0004 |
149
 
150
 
151
  ### Framework versions
152
 
153
- - Transformers 4.33.3
154
  - Pytorch 2.0.1+cu118
155
  - Datasets 2.14.5
156
- - Tokenizers 0.13.3
 
15
 
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0001
19
 
20
  ## Model description
21
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 0.5564 | 1.0 | 10 | 0.3900 |
50
+ | 0.3348 | 2.0 | 20 | 0.1773 |
51
+ | 0.1584 | 3.0 | 30 | 0.0763 |
52
+ | 0.0758 | 4.0 | 40 | 0.0294 |
53
+ | 0.0322 | 5.0 | 50 | 0.0055 |
54
+ | 0.0075 | 6.0 | 60 | 0.0023 |
55
+ | 0.0035 | 7.0 | 70 | 0.0015 |
56
+ | 0.0021 | 8.0 | 80 | 0.0011 |
57
+ | 0.0013 | 9.0 | 90 | 0.0009 |
58
+ | 0.0011 | 10.0 | 100 | 0.0008 |
59
+ | 0.0009 | 11.0 | 110 | 0.0008 |
60
+ | 0.0009 | 12.0 | 120 | 0.0007 |
61
+ | 0.0008 | 13.0 | 130 | 0.0006 |
62
+ | 0.0008 | 14.0 | 140 | 0.0006 |
63
+ | 0.0007 | 15.0 | 150 | 0.0006 |
64
+ | 0.0007 | 16.0 | 160 | 0.0005 |
65
+ | 0.0006 | 17.0 | 170 | 0.0005 |
66
+ | 0.0006 | 18.0 | 180 | 0.0005 |
67
+ | 0.0005 | 19.0 | 190 | 0.0004 |
68
+ | 0.0005 | 20.0 | 200 | 0.0004 |
69
+ | 0.0005 | 21.0 | 210 | 0.0004 |
70
+ | 0.0005 | 22.0 | 220 | 0.0004 |
71
+ | 0.0005 | 23.0 | 230 | 0.0004 |
72
+ | 0.0004 | 24.0 | 240 | 0.0004 |
73
+ | 0.0004 | 25.0 | 250 | 0.0003 |
74
+ | 0.0004 | 26.0 | 260 | 0.0003 |
75
+ | 0.0004 | 27.0 | 270 | 0.0003 |
76
+ | 0.0004 | 28.0 | 280 | 0.0003 |
77
+ | 0.0003 | 29.0 | 290 | 0.0003 |
78
+ | 0.0003 | 30.0 | 300 | 0.0003 |
79
+ | 0.0003 | 31.0 | 310 | 0.0003 |
80
+ | 0.0004 | 32.0 | 320 | 0.0003 |
81
+ | 0.0003 | 33.0 | 330 | 0.0003 |
82
+ | 0.0003 | 34.0 | 340 | 0.0003 |
83
+ | 0.0003 | 35.0 | 350 | 0.0003 |
84
+ | 0.0003 | 36.0 | 360 | 0.0003 |
85
+ | 0.0003 | 37.0 | 370 | 0.0002 |
86
+ | 0.0003 | 38.0 | 380 | 0.0002 |
87
+ | 0.0003 | 39.0 | 390 | 0.0002 |
88
+ | 0.0003 | 40.0 | 400 | 0.0002 |
89
+ | 0.0003 | 41.0 | 410 | 0.0002 |
90
+ | 0.0003 | 42.0 | 420 | 0.0002 |
91
+ | 0.0002 | 43.0 | 430 | 0.0002 |
92
+ | 0.0002 | 44.0 | 440 | 0.0002 |
93
+ | 0.0002 | 45.0 | 450 | 0.0002 |
94
+ | 0.0002 | 46.0 | 460 | 0.0002 |
95
+ | 0.0002 | 47.0 | 470 | 0.0002 |
96
+ | 0.0002 | 48.0 | 480 | 0.0002 |
97
+ | 0.0002 | 49.0 | 490 | 0.0002 |
98
+ | 0.0002 | 50.0 | 500 | 0.0002 |
99
+ | 0.0002 | 51.0 | 510 | 0.0002 |
100
+ | 0.0002 | 52.0 | 520 | 0.0002 |
101
+ | 0.0002 | 53.0 | 530 | 0.0002 |
102
+ | 0.0002 | 54.0 | 540 | 0.0002 |
103
+ | 0.0002 | 55.0 | 550 | 0.0002 |
104
+ | 0.0002 | 56.0 | 560 | 0.0002 |
105
+ | 0.0002 | 57.0 | 570 | 0.0002 |
106
+ | 0.0002 | 58.0 | 580 | 0.0002 |
107
+ | 0.0002 | 59.0 | 590 | 0.0002 |
108
+ | 0.0002 | 60.0 | 600 | 0.0002 |
109
+ | 0.0002 | 61.0 | 610 | 0.0002 |
110
+ | 0.0002 | 62.0 | 620 | 0.0002 |
111
+ | 0.0002 | 63.0 | 630 | 0.0002 |
112
+ | 0.0002 | 64.0 | 640 | 0.0002 |
113
+ | 0.0002 | 65.0 | 650 | 0.0002 |
114
+ | 0.0002 | 66.0 | 660 | 0.0002 |
115
+ | 0.0002 | 67.0 | 670 | 0.0002 |
116
+ | 0.0002 | 68.0 | 680 | 0.0002 |
117
+ | 0.0002 | 69.0 | 690 | 0.0002 |
118
+ | 0.0002 | 70.0 | 700 | 0.0002 |
119
+ | 0.0002 | 71.0 | 710 | 0.0002 |
120
+ | 0.0002 | 72.0 | 720 | 0.0002 |
121
+ | 0.0002 | 73.0 | 730 | 0.0002 |
122
+ | 0.0002 | 74.0 | 740 | 0.0002 |
123
+ | 0.0001 | 75.0 | 750 | 0.0002 |
124
+ | 0.0002 | 76.0 | 760 | 0.0002 |
125
+ | 0.0002 | 77.0 | 770 | 0.0002 |
126
+ | 0.0001 | 78.0 | 780 | 0.0002 |
127
+ | 0.0002 | 79.0 | 790 | 0.0002 |
128
+ | 0.0002 | 80.0 | 800 | 0.0002 |
129
+ | 0.0001 | 81.0 | 810 | 0.0002 |
130
+ | 0.0002 | 82.0 | 820 | 0.0002 |
131
+ | 0.0001 | 83.0 | 830 | 0.0001 |
132
+ | 0.0001 | 84.0 | 840 | 0.0001 |
133
+ | 0.0001 | 85.0 | 850 | 0.0001 |
134
+ | 0.0001 | 86.0 | 860 | 0.0001 |
135
+ | 0.0001 | 87.0 | 870 | 0.0001 |
136
+ | 0.0001 | 88.0 | 880 | 0.0001 |
137
+ | 0.0001 | 89.0 | 890 | 0.0001 |
138
+ | 0.0001 | 90.0 | 900 | 0.0001 |
139
+ | 0.0001 | 91.0 | 910 | 0.0001 |
140
+ | 0.0001 | 92.0 | 920 | 0.0001 |
141
+ | 0.0001 | 93.0 | 930 | 0.0001 |
142
+ | 0.0001 | 94.0 | 940 | 0.0001 |
143
+ | 0.0001 | 95.0 | 950 | 0.0001 |
144
+ | 0.0001 | 96.0 | 960 | 0.0001 |
145
+ | 0.0001 | 97.0 | 970 | 0.0001 |
146
+ | 0.0001 | 98.0 | 980 | 0.0001 |
147
+ | 0.0001 | 99.0 | 990 | 0.0001 |
148
+ | 0.0001 | 100.0 | 1000 | 0.0001 |
149
 
150
 
151
  ### Framework versions
152
 
153
+ - Transformers 4.34.0
154
  - Pytorch 2.0.1+cu118
155
  - Datasets 2.14.5
156
+ - Tokenizers 0.14.0