Hugging Face's logo

simonycl
/
best_model-sst-2-16-13

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
simonycl commited on
Commit
f2484fc
•
1 Parent(s): 36636a3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -52
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: 0.7026
21
- - Accuracy: 0.4062
22
 
23
  ## Model description
24
 
@@ -50,56 +50,56 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | No log | 1.0 | 1 | 0.7085 | 0.4688 |
54
- | No log | 2.0 | 2 | 0.7085 | 0.4688 |
55
- | No log | 3.0 | 3 | 0.7085 | 0.4688 |
56
- | No log | 4.0 | 4 | 0.7084 | 0.4688 |
57
- | No log | 5.0 | 5 | 0.7084 | 0.4688 |
58
- | No log | 6.0 | 6 | 0.7084 | 0.4688 |
59
- | No log | 7.0 | 7 | 0.7083 | 0.4688 |
60
- | No log | 8.0 | 8 | 0.7083 | 0.4688 |
61
- | No log | 9.0 | 9 | 0.7082 | 0.4688 |
62
- | 0.6957 | 10.0 | 10 | 0.7082 | 0.4688 |
63
- | 0.6957 | 11.0 | 11 | 0.7081 | 0.4688 |
64
- | 0.6957 | 12.0 | 12 | 0.7080 | 0.4688 |
65
- | 0.6957 | 13.0 | 13 | 0.7079 | 0.4688 |
66
- | 0.6957 | 14.0 | 14 | 0.7078 | 0.4688 |
67
- | 0.6957 | 15.0 | 15 | 0.7077 | 0.4688 |
68
- | 0.6957 | 16.0 | 16 | 0.7076 | 0.4688 |
69
- | 0.6957 | 17.0 | 17 | 0.7075 | 0.4688 |
70
- | 0.6957 | 18.0 | 18 | 0.7074 | 0.4688 |
71
- | 0.6957 | 19.0 | 19 | 0.7073 | 0.4688 |
72
- | 0.6906 | 20.0 | 20 | 0.7072 | 0.4688 |
73
- | 0.6906 | 21.0 | 21 | 0.7070 | 0.4688 |
74
- | 0.6906 | 22.0 | 22 | 0.7069 | 0.4688 |
75
- | 0.6906 | 23.0 | 23 | 0.7067 | 0.4688 |
76
- | 0.6906 | 24.0 | 24 | 0.7066 | 0.4688 |
77
- | 0.6906 | 25.0 | 25 | 0.7064 | 0.4688 |
78
- | 0.6906 | 26.0 | 26 | 0.7063 | 0.4688 |
79
- | 0.6906 | 27.0 | 27 | 0.7061 | 0.4688 |
80
- | 0.6906 | 28.0 | 28 | 0.7060 | 0.4688 |
81
- | 0.6906 | 29.0 | 29 | 0.7058 | 0.4375 |
82
- | 0.6833 | 30.0 | 30 | 0.7057 | 0.4375 |
83
- | 0.6833 | 31.0 | 31 | 0.7055 | 0.4375 |
84
- | 0.6833 | 32.0 | 32 | 0.7054 | 0.4375 |
85
- | 0.6833 | 33.0 | 33 | 0.7052 | 0.4375 |
86
- | 0.6833 | 34.0 | 34 | 0.7051 | 0.4688 |
87
- | 0.6833 | 35.0 | 35 | 0.7050 | 0.4688 |
88
- | 0.6833 | 36.0 | 36 | 0.7048 | 0.4688 |
89
- | 0.6833 | 37.0 | 37 | 0.7047 | 0.4688 |
90
- | 0.6833 | 38.0 | 38 | 0.7045 | 0.4688 |
91
- | 0.6833 | 39.0 | 39 | 0.7044 | 0.4688 |
92
- | 0.6618 | 40.0 | 40 | 0.7042 | 0.4688 |
93
- | 0.6618 | 41.0 | 41 | 0.7041 | 0.4688 |
94
- | 0.6618 | 42.0 | 42 | 0.7039 | 0.4688 |
95
- | 0.6618 | 43.0 | 43 | 0.7038 | 0.4375 |
96
- | 0.6618 | 44.0 | 44 | 0.7037 | 0.4062 |
97
- | 0.6618 | 45.0 | 45 | 0.7035 | 0.4375 |
98
- | 0.6618 | 46.0 | 46 | 0.7033 | 0.4375 |
99
- | 0.6618 | 47.0 | 47 | 0.7032 | 0.4375 |
100
- | 0.6618 | 48.0 | 48 | 0.7030 | 0.4062 |
101
- | 0.6618 | 49.0 | 49 | 0.7028 | 0.4062 |
102
- | 0.6438 | 50.0 | 50 | 0.7026 | 0.4062 |
103
 
104
 
105
  ### 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: 0.6710
21
+ - Accuracy: 0.7188
22
 
23
  ## Model description
24
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 1 | 0.6895 | 0.5312 |
54
+ | No log | 2.0 | 2 | 0.6895 | 0.5312 |
55
+ | No log | 3.0 | 3 | 0.6894 | 0.5312 |
56
+ | No log | 4.0 | 4 | 0.6894 | 0.5312 |
57
+ | No log | 5.0 | 5 | 0.6894 | 0.5312 |
58
+ | No log | 6.0 | 6 | 0.6893 | 0.5312 |
59
+ | No log | 7.0 | 7 | 0.6893 | 0.5312 |
60
+ | No log | 8.0 | 8 | 0.6892 | 0.5312 |
61
+ | No log | 9.0 | 9 | 0.6891 | 0.5312 |
62
+ | 0.7006 | 10.0 | 10 | 0.6890 | 0.5312 |
63
+ | 0.7006 | 11.0 | 11 | 0.6889 | 0.5312 |
64
+ | 0.7006 | 12.0 | 12 | 0.6888 | 0.5312 |
65
+ | 0.7006 | 13.0 | 13 | 0.6887 | 0.5312 |
66
+ | 0.7006 | 14.0 | 14 | 0.6886 | 0.5312 |
67
+ | 0.7006 | 15.0 | 15 | 0.6884 | 0.5312 |
68
+ | 0.7006 | 16.0 | 16 | 0.6883 | 0.5312 |
69
+ | 0.7006 | 17.0 | 17 | 0.6881 | 0.5312 |
70
+ | 0.7006 | 18.0 | 18 | 0.6879 | 0.5312 |
71
+ | 0.7006 | 19.0 | 19 | 0.6877 | 0.5312 |
72
+ | 0.6992 | 20.0 | 20 | 0.6875 | 0.5312 |
73
+ | 0.6992 | 21.0 | 21 | 0.6872 | 0.5312 |
74
+ | 0.6992 | 22.0 | 22 | 0.6870 | 0.5312 |
75
+ | 0.6992 | 23.0 | 23 | 0.6867 | 0.5 |
76
+ | 0.6992 | 24.0 | 24 | 0.6864 | 0.5 |
77
+ | 0.6992 | 25.0 | 25 | 0.6861 | 0.5 |
78
+ | 0.6992 | 26.0 | 26 | 0.6857 | 0.5 |
79
+ | 0.6992 | 27.0 | 27 | 0.6854 | 0.5 |
80
+ | 0.6992 | 28.0 | 28 | 0.6850 | 0.5 |
81
+ | 0.6992 | 29.0 | 29 | 0.6846 | 0.5 |
82
+ | 0.68 | 30.0 | 30 | 0.6842 | 0.5 |
83
+ | 0.68 | 31.0 | 31 | 0.6838 | 0.5 |
84
+ | 0.68 | 32.0 | 32 | 0.6833 | 0.5 |
85
+ | 0.68 | 33.0 | 33 | 0.6829 | 0.5 |
86
+ | 0.68 | 34.0 | 34 | 0.6824 | 0.5 |
87
+ | 0.68 | 35.0 | 35 | 0.6819 | 0.5 |
88
+ | 0.68 | 36.0 | 36 | 0.6814 | 0.5312 |
89
+ | 0.68 | 37.0 | 37 | 0.6808 | 0.5625 |
90
+ | 0.68 | 38.0 | 38 | 0.6802 | 0.5625 |
91
+ | 0.68 | 39.0 | 39 | 0.6796 | 0.5938 |
92
+ | 0.6655 | 40.0 | 40 | 0.6789 | 0.5938 |
93
+ | 0.6655 | 41.0 | 41 | 0.6783 | 0.5938 |
94
+ | 0.6655 | 42.0 | 42 | 0.6776 | 0.5938 |
95
+ | 0.6655 | 43.0 | 43 | 0.6769 | 0.6562 |
96
+ | 0.6655 | 44.0 | 44 | 0.6762 | 0.7188 |
97
+ | 0.6655 | 45.0 | 45 | 0.6754 | 0.7188 |
98
+ | 0.6655 | 46.0 | 46 | 0.6746 | 0.7188 |
99
+ | 0.6655 | 47.0 | 47 | 0.6737 | 0.75 |
100
+ | 0.6655 | 48.0 | 48 | 0.6728 | 0.75 |
101
+ | 0.6655 | 49.0 | 49 | 0.6719 | 0.75 |
102
+ | 0.6452 | 50.0 | 50 | 0.6710 | 0.7188 |
103
 
104
 
105
  ### Framework versions