Hugging Face's logo

henryscheible
/
bert-large-uncased_winobias_classifieronly

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
2
henryscheible commited on
Commit
4e22850
·
1 Parent(s): 9f51ccf

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +72 -56
README.md CHANGED
@@ -16,8 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.6930
20
- - Accuracy: 0.5095
 
 
 
 
21
 
22
  ## Model description
23
 
@@ -36,68 +40,80 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 5e-05
40
  - train_batch_size: 64
41
  - eval_batch_size: 64
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 20
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
- | 0.696 | 0.4 | 10 | 0.6953 | 0.4962 |
52
- | 0.6961 | 0.8 | 20 | 0.6933 | 0.5133 |
53
- | 0.7037 | 1.2 | 30 | 0.6936 | 0.5082 |
54
- | 0.6972 | 1.6 | 40 | 0.6934 | 0.5044 |
55
- | 0.6923 | 2.0 | 50 | 0.6939 | 0.5095 |
56
- | 0.7141 | 2.4 | 60 | 0.6955 | 0.4975 |
57
- | 0.7108 | 2.8 | 70 | 0.6933 | 0.5170 |
58
- | 0.6899 | 3.2 | 80 | 0.6936 | 0.5038 |
59
- | 0.702 | 3.6 | 90 | 0.6935 | 0.5025 |
60
- | 0.7002 | 4.0 | 100 | 0.6932 | 0.5044 |
61
- | 0.6997 | 4.4 | 110 | 0.6934 | 0.5057 |
62
- | 0.7002 | 4.8 | 120 | 0.6932 | 0.5170 |
63
- | 0.7112 | 5.2 | 130 | 0.6942 | 0.5006 |
64
- | 0.7054 | 5.6 | 140 | 0.6938 | 0.4956 |
65
- | 0.7084 | 6.0 | 150 | 0.6932 | 0.5152 |
66
- | 0.6983 | 6.4 | 160 | 0.6935 | 0.5019 |
67
- | 0.7123 | 6.8 | 170 | 0.6932 | 0.5126 |
68
- | 0.6932 | 7.2 | 180 | 0.6932 | 0.5082 |
69
- | 0.6979 | 7.6 | 190 | 0.6942 | 0.5019 |
70
- | 0.7062 | 8.0 | 200 | 0.6937 | 0.4987 |
71
- | 0.7083 | 8.4 | 210 | 0.6931 | 0.5164 |
72
- | 0.7063 | 8.8 | 220 | 0.6935 | 0.5032 |
73
- | 0.6969 | 9.2 | 230 | 0.6931 | 0.5170 |
74
- | 0.7051 | 9.6 | 240 | 0.6931 | 0.5152 |
75
- | 0.6969 | 10.0 | 250 | 0.6933 | 0.4987 |
76
- | 0.7003 | 10.4 | 260 | 0.6935 | 0.4962 |
77
- | 0.7045 | 10.8 | 270 | 0.6932 | 0.5076 |
78
- | 0.7003 | 11.2 | 280 | 0.6931 | 0.5126 |
79
- | 0.7049 | 11.6 | 290 | 0.6931 | 0.5133 |
80
- | 0.7117 | 12.0 | 300 | 0.6932 | 0.5152 |
81
- | 0.7016 | 12.4 | 310 | 0.6933 | 0.5063 |
82
- | 0.6961 | 12.8 | 320 | 0.6930 | 0.5082 |
83
- | 0.6992 | 13.2 | 330 | 0.6932 | 0.5063 |
84
- | 0.703 | 13.6 | 340 | 0.6934 | 0.5063 |
85
- | 0.7112 | 14.0 | 350 | 0.6930 | 0.5114 |
86
- | 0.7036 | 14.4 | 360 | 0.6938 | 0.5063 |
87
- | 0.695 | 14.8 | 370 | 0.6939 | 0.5057 |
88
- | 0.7051 | 15.2 | 380 | 0.6932 | 0.5076 |
89
- | 0.7019 | 15.6 | 390 | 0.6930 | 0.5120 |
90
- | 0.701 | 16.0 | 400 | 0.6930 | 0.5126 |
91
- | 0.6988 | 16.4 | 410 | 0.6931 | 0.5101 |
92
- | 0.7049 | 16.8 | 420 | 0.6931 | 0.5107 |
93
- | 0.7073 | 17.2 | 430 | 0.6931 | 0.5101 |
94
- | 0.6995 | 17.6 | 440 | 0.6930 | 0.5088 |
95
- | 0.7142 | 18.0 | 450 | 0.6930 | 0.5076 |
96
- | 0.7041 | 18.4 | 460 | 0.6930 | 0.5101 |
97
- | 0.7041 | 18.8 | 470 | 0.6931 | 0.5107 |
98
- | 0.7064 | 19.2 | 480 | 0.6930 | 0.5095 |
99
- | 0.7019 | 19.6 | 490 | 0.6930 | 0.5107 |
100
- | 0.7045 | 20.0 | 500 | 0.6930 | 0.5095 |
 
 
 
 
 
 
 
 
 
 
 
 
101
 
102
 
103
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.6926
20
+ - Accuracy: 0.5069
21
+ - Tp: 0.3119
22
+ - Tn: 0.1951
23
+ - Fp: 0.3049
24
+ - Fn: 0.1881
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 0.0001
44
  - train_batch_size: 64
45
  - eval_batch_size: 64
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 50
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Tp | Tn | Fp | Fn |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|
55
+ | 0.7009 | 0.8 | 20 | 0.6969 | 0.5126 | 0.3561 | 0.1566 | 0.3434 | 0.1439 |
56
+ | 0.7014 | 1.6 | 40 | 0.6964 | 0.5126 | 0.3794 | 0.1332 | 0.3668 | 0.1206 |
57
+ | 0.7042 | 2.4 | 60 | 0.6970 | 0.5088 | 0.4167 | 0.0922 | 0.4078 | 0.0833 |
58
+ | 0.6999 | 3.2 | 80 | 0.6941 | 0.5082 | 0.2399 | 0.2683 | 0.2317 | 0.2601 |
59
+ | 0.6987 | 4.0 | 100 | 0.6944 | 0.5069 | 0.3333 | 0.1736 | 0.3264 | 0.1667 |
60
+ | 0.7022 | 4.8 | 120 | 0.6949 | 0.5164 | 0.3946 | 0.1218 | 0.3782 | 0.1054 |
61
+ | 0.7054 | 5.6 | 140 | 0.6937 | 0.5051 | 0.1982 | 0.3068 | 0.1932 | 0.3018 |
62
+ | 0.7129 | 6.4 | 160 | 0.6933 | 0.5069 | 0.3068 | 0.2001 | 0.2999 | 0.1932 |
63
+ | 0.6964 | 7.2 | 180 | 0.6932 | 0.5114 | 0.2203 | 0.2910 | 0.2090 | 0.2797 |
64
+ | 0.7014 | 8.0 | 200 | 0.6933 | 0.5076 | 0.3264 | 0.1812 | 0.3188 | 0.1736 |
65
+ | 0.707 | 8.8 | 220 | 0.6936 | 0.5164 | 0.1446 | 0.3718 | 0.1282 | 0.3554 |
66
+ | 0.6977 | 9.6 | 240 | 0.6932 | 0.5038 | 0.3182 | 0.1856 | 0.3144 | 0.1818 |
67
+ | 0.71 | 10.4 | 260 | 0.6944 | 0.5170 | 0.4192 | 0.0979 | 0.4021 | 0.0808 |
68
+ | 0.6998 | 11.2 | 280 | 0.6932 | 0.5044 | 0.2121 | 0.2923 | 0.2077 | 0.2879 |
69
+ | 0.7134 | 12.0 | 300 | 0.6931 | 0.5114 | 0.2879 | 0.2235 | 0.2765 | 0.2121 |
70
+ | 0.6967 | 12.8 | 320 | 0.6931 | 0.5038 | 0.2247 | 0.2790 | 0.2210 | 0.2753 |
71
+ | 0.708 | 13.6 | 340 | 0.6930 | 0.5101 | 0.3037 | 0.2064 | 0.2936 | 0.1963 |
72
+ | 0.696 | 14.4 | 360 | 0.6940 | 0.5114 | 0.4261 | 0.0852 | 0.4148 | 0.0739 |
73
+ | 0.7016 | 15.2 | 380 | 0.6937 | 0.5006 | 0.1231 | 0.3775 | 0.1225 | 0.3769 |
74
+ | 0.6922 | 16.0 | 400 | 0.6930 | 0.5088 | 0.2999 | 0.2090 | 0.2910 | 0.2001 |
75
+ | 0.698 | 16.8 | 420 | 0.6930 | 0.5120 | 0.2222 | 0.2898 | 0.2102 | 0.2778 |
76
+ | 0.695 | 17.6 | 440 | 0.6934 | 0.5114 | 0.1414 | 0.3699 | 0.1301 | 0.3586 |
77
+ | 0.7023 | 18.4 | 460 | 0.6950 | 0.5126 | 0.4710 | 0.0417 | 0.4583 | 0.0290 |
78
+ | 0.7079 | 19.2 | 480 | 0.6937 | 0.5133 | 0.4167 | 0.0966 | 0.4034 | 0.0833 |
79
+ | 0.7005 | 20.0 | 500 | 0.6931 | 0.5095 | 0.3491 | 0.1604 | 0.3396 | 0.1509 |
80
+ | 0.7024 | 20.8 | 520 | 0.6956 | 0.5082 | 0.4760 | 0.0322 | 0.4678 | 0.0240 |
81
+ | 0.699 | 21.6 | 540 | 0.6929 | 0.5101 | 0.2797 | 0.2304 | 0.2696 | 0.2203 |
82
+ | 0.6946 | 22.4 | 560 | 0.6929 | 0.5107 | 0.2822 | 0.2285 | 0.2715 | 0.2178 |
83
+ | 0.7076 | 23.2 | 580 | 0.6940 | 0.5177 | 0.4249 | 0.0928 | 0.4072 | 0.0751 |
84
+ | 0.6996 | 24.0 | 600 | 0.6930 | 0.5082 | 0.2879 | 0.2203 | 0.2797 | 0.2121 |
85
+ | 0.7059 | 24.8 | 620 | 0.6938 | 0.5158 | 0.3990 | 0.1168 | 0.3832 | 0.1010 |
86
+ | 0.6987 | 25.6 | 640 | 0.6933 | 0.5088 | 0.1591 | 0.3497 | 0.1503 | 0.3409 |
87
+ | 0.7008 | 26.4 | 660 | 0.6949 | 0.5120 | 0.4628 | 0.0492 | 0.4508 | 0.0372 |
88
+ | 0.6949 | 27.2 | 680 | 0.6931 | 0.5032 | 0.1824 | 0.3207 | 0.1793 | 0.3176 |
89
+ | 0.71 | 28.0 | 700 | 0.6929 | 0.5114 | 0.2872 | 0.2241 | 0.2759 | 0.2128 |
90
+ | 0.6962 | 28.8 | 720 | 0.6929 | 0.5051 | 0.2980 | 0.2071 | 0.2929 | 0.2020 |
91
+ | 0.6984 | 29.6 | 740 | 0.6955 | 0.5088 | 0.4735 | 0.0354 | 0.4646 | 0.0265 |
92
+ | 0.7136 | 30.4 | 760 | 0.6929 | 0.5158 | 0.2431 | 0.2727 | 0.2273 | 0.2569 |
93
+ | 0.7106 | 31.2 | 780 | 0.6932 | 0.5126 | 0.3718 | 0.1408 | 0.3592 | 0.1282 |
94
+ | 0.6972 | 32.0 | 800 | 0.6936 | 0.5126 | 0.4091 | 0.1035 | 0.3965 | 0.0909 |
95
+ | 0.7147 | 32.8 | 820 | 0.6930 | 0.5057 | 0.3321 | 0.1736 | 0.3264 | 0.1679 |
96
+ | 0.7035 | 33.6 | 840 | 0.6928 | 0.5158 | 0.2235 | 0.2923 | 0.2077 | 0.2765 |
97
+ | 0.7045 | 34.4 | 860 | 0.6955 | 0.5101 | 0.4729 | 0.0372 | 0.4628 | 0.0271 |
98
+ | 0.7088 | 35.2 | 880 | 0.6937 | 0.5114 | 0.4211 | 0.0903 | 0.4097 | 0.0789 |
99
+ | 0.7065 | 36.0 | 900 | 0.6927 | 0.5164 | 0.2702 | 0.2462 | 0.2538 | 0.2298 |
100
+ | 0.7068 | 36.8 | 920 | 0.6929 | 0.5069 | 0.1900 | 0.3169 | 0.1831 | 0.3100 |
101
+ | 0.706 | 37.6 | 940 | 0.6937 | 0.5189 | 0.4343 | 0.0846 | 0.4154 | 0.0657 |
102
+ | 0.6958 | 38.4 | 960 | 0.6927 | 0.5095 | 0.2967 | 0.2128 | 0.2872 | 0.2033 |
103
+ | 0.7012 | 39.2 | 980 | 0.6928 | 0.5051 | 0.3277 | 0.1774 | 0.3226 | 0.1723 |
104
+ | 0.7008 | 40.0 | 1000 | 0.6928 | 0.5088 | 0.3182 | 0.1907 | 0.3093 | 0.1818 |
105
+ | 0.7108 | 40.8 | 1020 | 0.6927 | 0.5063 | 0.3112 | 0.1951 | 0.3049 | 0.1888 |
106
+ | 0.6972 | 41.6 | 1040 | 0.6928 | 0.5101 | 0.3308 | 0.1793 | 0.3207 | 0.1692 |
107
+ | 0.7058 | 42.4 | 1060 | 0.6926 | 0.5126 | 0.2727 | 0.2399 | 0.2601 | 0.2273 |
108
+ | 0.6977 | 43.2 | 1080 | 0.6927 | 0.5152 | 0.2317 | 0.2835 | 0.2165 | 0.2683 |
109
+ | 0.6971 | 44.0 | 1100 | 0.6926 | 0.5158 | 0.2386 | 0.2771 | 0.2229 | 0.2614 |
110
+ | 0.7049 | 44.8 | 1120 | 0.6928 | 0.5107 | 0.3573 | 0.1534 | 0.3466 | 0.1427 |
111
+ | 0.6979 | 45.6 | 1140 | 0.6928 | 0.5114 | 0.3516 | 0.1597 | 0.3403 | 0.1484 |
112
+ | 0.7054 | 46.4 | 1160 | 0.6930 | 0.5164 | 0.3883 | 0.1282 | 0.3718 | 0.1117 |
113
+ | 0.6997 | 47.2 | 1180 | 0.6930 | 0.5126 | 0.3902 | 0.1225 | 0.3775 | 0.1098 |
114
+ | 0.7005 | 48.0 | 1200 | 0.6927 | 0.5082 | 0.3428 | 0.1654 | 0.3346 | 0.1572 |
115
+ | 0.6998 | 48.8 | 1220 | 0.6927 | 0.5069 | 0.3295 | 0.1774 | 0.3226 | 0.1705 |
116
+ | 0.7018 | 49.6 | 1240 | 0.6926 | 0.5069 | 0.3119 | 0.1951 | 0.3049 | 0.1881 |
117
 
118
 
119
  ### Framework versions