Hugging Face's logo

ankush-003
/
nosql-identifier-bert

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
2
ankush-003 commited on
Commit
d68b115
·
1 Parent(s): 3a569f8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -103
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.7566
21
- - Accuracy: 0.925
22
 
23
  ## Model description
24
 
@@ -43,112 +43,32 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 100
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | No log | 1.0 | 40 | 0.3987 | 0.875 |
53
- | No log | 2.0 | 80 | 0.2198 | 1.0 |
54
- | No log | 3.0 | 120 | 0.1294 | 1.0 |
55
- | No log | 4.0 | 160 | 0.5029 | 0.775 |
56
- | No log | 5.0 | 200 | 0.1562 | 0.95 |
57
- | No log | 6.0 | 240 | 0.1672 | 0.9 |
58
- | No log | 7.0 | 280 | 0.1928 | 0.9 |
59
- | No log | 8.0 | 320 | 0.1154 | 0.95 |
60
- | No log | 9.0 | 360 | 0.1780 | 0.95 |
61
- | No log | 10.0 | 400 | 0.4642 | 0.9 |
62
- | No log | 11.0 | 440 | 0.2898 | 0.95 |
63
- | No log | 12.0 | 480 | 0.2842 | 0.925 |
64
- | 0.3022 | 13.0 | 520 | 0.3082 | 0.95 |
65
- | 0.3022 | 14.0 | 560 | 0.3127 | 0.95 |
66
- | 0.3022 | 15.0 | 600 | 0.3421 | 0.95 |
67
- | 0.3022 | 16.0 | 640 | 0.1690 | 0.975 |
68
- | 0.3022 | 17.0 | 680 | 0.2002 | 0.95 |
69
- | 0.3022 | 18.0 | 720 | 0.4938 | 0.925 |
70
- | 0.3022 | 19.0 | 760 | 0.2749 | 0.95 |
71
- | 0.3022 | 20.0 | 800 | 0.2013 | 0.975 |
72
- | 0.3022 | 21.0 | 840 | 0.4775 | 0.925 |
73
- | 0.3022 | 22.0 | 880 | 0.2020 | 0.975 |
74
- | 0.3022 | 23.0 | 920 | 0.2081 | 0.975 |
75
- | 0.3022 | 24.0 | 960 | 0.2603 | 0.95 |
76
- | 0.0784 | 25.0 | 1000 | 0.5710 | 0.925 |
77
- | 0.0784 | 26.0 | 1040 | 0.4450 | 0.925 |
78
- | 0.0784 | 27.0 | 1080 | 0.2669 | 0.95 |
79
- | 0.0784 | 28.0 | 1120 | 0.6181 | 0.9 |
80
- | 0.0784 | 29.0 | 1160 | 0.3211 | 0.95 |
81
- | 0.0784 | 30.0 | 1200 | 0.3222 | 0.95 |
82
- | 0.0784 | 31.0 | 1240 | 0.3238 | 0.95 |
83
- | 0.0784 | 32.0 | 1280 | 0.4617 | 0.925 |
84
- | 0.0784 | 33.0 | 1320 | 0.4142 | 0.95 |
85
- | 0.0784 | 34.0 | 1360 | 0.4887 | 0.925 |
86
- | 0.0784 | 35.0 | 1400 | 0.6418 | 0.925 |
87
- | 0.0784 | 36.0 | 1440 | 0.4104 | 0.95 |
88
- | 0.0784 | 37.0 | 1480 | 0.5617 | 0.925 |
89
- | 0.0605 | 38.0 | 1520 | 0.3141 | 0.95 |
90
- | 0.0605 | 39.0 | 1560 | 0.3596 | 0.95 |
91
- | 0.0605 | 40.0 | 1600 | 0.6732 | 0.925 |
92
- | 0.0605 | 41.0 | 1640 | 0.6785 | 0.925 |
93
- | 0.0605 | 42.0 | 1680 | 0.6904 | 0.925 |
94
- | 0.0605 | 43.0 | 1720 | 0.4378 | 0.95 |
95
- | 0.0605 | 44.0 | 1760 | 0.6341 | 0.925 |
96
- | 0.0605 | 45.0 | 1800 | 0.3517 | 0.95 |
97
- | 0.0605 | 46.0 | 1840 | 0.7044 | 0.925 |
98
- | 0.0605 | 47.0 | 1880 | 0.7259 | 0.925 |
99
- | 0.0605 | 48.0 | 1920 | 0.7297 | 0.925 |
100
- | 0.0605 | 49.0 | 1960 | 0.7293 | 0.925 |
101
- | 0.0363 | 50.0 | 2000 | 0.7248 | 0.925 |
102
- | 0.0363 | 51.0 | 2040 | 0.4813 | 0.95 |
103
- | 0.0363 | 52.0 | 2080 | 0.4647 | 0.95 |
104
- | 0.0363 | 53.0 | 2120 | 0.4684 | 0.95 |
105
- | 0.0363 | 54.0 | 2160 | 0.6032 | 0.925 |
106
- | 0.0363 | 55.0 | 2200 | 0.4853 | 0.95 |
107
- | 0.0363 | 56.0 | 2240 | 0.4840 | 0.95 |
108
- | 0.0363 | 57.0 | 2280 | 0.4827 | 0.95 |
109
- | 0.0363 | 58.0 | 2320 | 0.4400 | 0.95 |
110
- | 0.0363 | 59.0 | 2360 | 0.4886 | 0.95 |
111
- | 0.0363 | 60.0 | 2400 | 0.4966 | 0.95 |
112
- | 0.0363 | 61.0 | 2440 | 0.4897 | 0.95 |
113
- | 0.0363 | 62.0 | 2480 | 0.4682 | 0.95 |
114
- | 0.0299 | 63.0 | 2520 | 0.4750 | 0.95 |
115
- | 0.0299 | 64.0 | 2560 | 0.4844 | 0.95 |
116
- | 0.0299 | 65.0 | 2600 | 0.7955 | 0.9 |
117
- | 0.0299 | 66.0 | 2640 | 0.5219 | 0.925 |
118
- | 0.0299 | 67.0 | 2680 | 0.4882 | 0.925 |
119
- | 0.0299 | 68.0 | 2720 | 0.4505 | 0.95 |
120
- | 0.0299 | 69.0 | 2760 | 0.2627 | 0.975 |
121
- | 0.0299 | 70.0 | 2800 | 0.2633 | 0.975 |
122
- | 0.0299 | 71.0 | 2840 | 0.2667 | 0.975 |
123
- | 0.0299 | 72.0 | 2880 | 0.2955 | 0.95 |
124
- | 0.0299 | 73.0 | 2920 | 0.4848 | 0.95 |
125
- | 0.0299 | 74.0 | 2960 | 0.7284 | 0.925 |
126
- | 0.0334 | 75.0 | 3000 | 0.4787 | 0.95 |
127
- | 0.0334 | 76.0 | 3040 | 0.4838 | 0.95 |
128
- | 0.0334 | 77.0 | 3080 | 0.4995 | 0.95 |
129
- | 0.0334 | 78.0 | 3120 | 0.2645 | 0.975 |
130
- | 0.0334 | 79.0 | 3160 | 0.4928 | 0.95 |
131
- | 0.0334 | 80.0 | 3200 | 0.6753 | 0.925 |
132
- | 0.0334 | 81.0 | 3240 | 0.6419 | 0.925 |
133
- | 0.0334 | 82.0 | 3280 | 0.4380 | 0.95 |
134
- | 0.0334 | 83.0 | 3320 | 0.4723 | 0.95 |
135
- | 0.0334 | 84.0 | 3360 | 0.4748 | 0.95 |
136
- | 0.0334 | 85.0 | 3400 | 0.4657 | 0.95 |
137
- | 0.0334 | 86.0 | 3440 | 0.4651 | 0.95 |
138
- | 0.0334 | 87.0 | 3480 | 0.4647 | 0.95 |
139
- | 0.0319 | 88.0 | 3520 | 0.4570 | 0.95 |
140
- | 0.0319 | 89.0 | 3560 | 0.4539 | 0.95 |
141
- | 0.0319 | 90.0 | 3600 | 0.7459 | 0.925 |
142
- | 0.0319 | 91.0 | 3640 | 0.7451 | 0.925 |
143
- | 0.0319 | 92.0 | 3680 | 0.7484 | 0.925 |
144
- | 0.0319 | 93.0 | 3720 | 0.7533 | 0.925 |
145
- | 0.0319 | 94.0 | 3760 | 0.7536 | 0.925 |
146
- | 0.0319 | 95.0 | 3800 | 0.7547 | 0.925 |
147
- | 0.0319 | 96.0 | 3840 | 0.7566 | 0.925 |
148
- | 0.0319 | 97.0 | 3880 | 0.7556 | 0.925 |
149
- | 0.0319 | 98.0 | 3920 | 0.7563 | 0.925 |
150
- | 0.0319 | 99.0 | 3960 | 0.7565 | 0.925 |
151
- | 0.0281 | 100.0 | 4000 | 0.7566 | 0.925 |
152
 
153
 
154
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1785
21
+ - Accuracy: 0.975
22
 
23
  ## Model description
24
 
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 20
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 40 | 0.5065 | 0.9 |
53
+ | No log | 2.0 | 80 | 0.1797 | 0.975 |
54
+ | No log | 3.0 | 120 | 0.3728 | 0.8 |
55
+ | No log | 4.0 | 160 | 0.1881 | 0.925 |
56
+ | No log | 5.0 | 200 | 0.1524 | 0.95 |
57
+ | No log | 6.0 | 240 | 0.1662 | 0.9 |
58
+ | No log | 7.0 | 280 | 0.2983 | 0.9 |
59
+ | No log | 8.0 | 320 | 0.1435 | 0.975 |
60
+ | No log | 9.0 | 360 | 0.1648 | 0.975 |
61
+ | No log | 10.0 | 400 | 0.1821 | 0.975 |
62
+ | No log | 11.0 | 440 | 0.3313 | 0.95 |
63
+ | No log | 12.0 | 480 | 0.2157 | 0.95 |
64
+ | 0.2728 | 13.0 | 520 | 0.3267 | 0.95 |
65
+ | 0.2728 | 14.0 | 560 | 0.1715 | 0.975 |
66
+ | 0.2728 | 15.0 | 600 | 0.1850 | 0.975 |
67
+ | 0.2728 | 16.0 | 640 | 0.2443 | 0.95 |
68
+ | 0.2728 | 17.0 | 680 | 0.1755 | 0.975 |
69
+ | 0.2728 | 18.0 | 720 | 0.1747 | 0.975 |
70
+ | 0.2728 | 19.0 | 760 | 0.1763 | 0.975 |
71
+ | 0.2728 | 20.0 | 800 | 0.1785 | 0.975 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions