Hugging Face's logo

muhtasham
/
bert-small-finetuned-ner-to-multilabel-finer-139

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
muhtasham commited on
Commit
63ae454
•
1 Parent(s): 175fec1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +149 -0
README.md ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: bert-small-finetuned-ner-to-multilabel-finer-139
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # bert-small-finetuned-ner-to-multilabel-finer-139
14
+
15
+ This model is a fine-tuned version of [google/bert_uncased_L-4_H-512_A-8](https://huggingface.co/google/bert_uncased_L-4_H-512_A-8) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.0019
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 3e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: constant
42
+ - num_epochs: 40
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:-----:|:---------------:|
48
+ | 0.1398 | 0.0 | 500 | 0.0244 |
49
+ | 0.0164 | 0.01 | 1000 | 0.0114 |
50
+ | 0.01 | 0.01 | 1500 | 0.0084 |
51
+ | 0.0081 | 0.02 | 2000 | 0.0073 |
52
+ | 0.0072 | 0.02 | 2500 | 0.0068 |
53
+ | 0.0069 | 0.03 | 3000 | 0.0065 |
54
+ | 0.0067 | 0.03 | 3500 | 0.0063 |
55
+ | 0.0066 | 0.04 | 4000 | 0.0062 |
56
+ | 0.0061 | 0.04 | 4500 | 0.0062 |
57
+ | 0.0069 | 0.04 | 5000 | 0.0061 |
58
+ | 0.0063 | 0.05 | 5500 | 0.0061 |
59
+ | 0.0062 | 0.05 | 6000 | 0.0061 |
60
+ | 0.006 | 0.06 | 6500 | 0.0061 |
61
+ | 0.0059 | 0.06 | 7000 | 0.0056 |
62
+ | 0.0058 | 0.07 | 7500 | 0.0054 |
63
+ | 0.0054 | 0.07 | 8000 | 0.0054 |
64
+ | 0.0057 | 0.08 | 8500 | 0.0053 |
65
+ | 0.0057 | 0.08 | 9000 | 0.0052 |
66
+ | 0.0056 | 0.08 | 9500 | 0.0051 |
67
+ | 0.0051 | 0.09 | 10000 | 0.0050 |
68
+ | 0.0054 | 0.09 | 10500 | 0.0049 |
69
+ | 0.005 | 0.1 | 11000 | 0.0048 |
70
+ | 0.0049 | 0.1 | 11500 | 0.0046 |
71
+ | 0.0049 | 0.11 | 12000 | 0.0046 |
72
+ | 0.0046 | 0.11 | 12500 | 0.0044 |
73
+ | 0.0043 | 0.12 | 13000 | 0.0043 |
74
+ | 0.0045 | 0.12 | 13500 | 0.0042 |
75
+ | 0.0042 | 0.12 | 14000 | 0.0042 |
76
+ | 0.0042 | 0.13 | 14500 | 0.0039 |
77
+ | 0.0042 | 0.13 | 15000 | 0.0038 |
78
+ | 0.0039 | 0.14 | 15500 | 0.0037 |
79
+ | 0.004 | 0.14 | 16000 | 0.0036 |
80
+ | 0.0037 | 0.15 | 16500 | 0.0035 |
81
+ | 0.0036 | 0.15 | 17000 | 0.0035 |
82
+ | 0.0036 | 0.16 | 17500 | 0.0035 |
83
+ | 0.0035 | 0.16 | 18000 | 0.0033 |
84
+ | 0.0037 | 0.16 | 18500 | 0.0033 |
85
+ | 0.0035 | 0.17 | 19000 | 0.0032 |
86
+ | 0.0032 | 0.17 | 19500 | 0.0031 |
87
+ | 0.0032 | 0.18 | 20000 | 0.0031 |
88
+ | 0.0033 | 0.18 | 20500 | 0.0030 |
89
+ | 0.003 | 0.19 | 21000 | 0.0030 |
90
+ | 0.0034 | 0.19 | 21500 | 0.0029 |
91
+ | 0.0031 | 0.2 | 22000 | 0.0029 |
92
+ | 0.003 | 0.2 | 22500 | 0.0028 |
93
+ | 0.0032 | 0.2 | 23000 | 0.0028 |
94
+ | 0.003 | 0.21 | 23500 | 0.0027 |
95
+ | 0.0029 | 0.21 | 24000 | 0.0027 |
96
+ | 0.0027 | 0.22 | 24500 | 0.0026 |
97
+ | 0.0029 | 0.22 | 25000 | 0.0026 |
98
+ | 0.0027 | 0.23 | 25500 | 0.0026 |
99
+ | 0.0028 | 0.23 | 26000 | 0.0026 |
100
+ | 0.0027 | 0.24 | 26500 | 0.0025 |
101
+ | 0.0026 | 0.24 | 27000 | 0.0025 |
102
+ | 0.0026 | 0.24 | 27500 | 0.0025 |
103
+ | 0.0026 | 0.25 | 28000 | 0.0024 |
104
+ | 0.0025 | 0.25 | 28500 | 0.0024 |
105
+ | 0.0026 | 0.26 | 29000 | 0.0024 |
106
+ | 0.0025 | 0.26 | 29500 | 0.0024 |
107
+ | 0.0024 | 0.27 | 30000 | 0.0024 |
108
+ | 0.0026 | 0.27 | 30500 | 0.0023 |
109
+ | 0.0024 | 0.28 | 31000 | 0.0023 |
110
+ | 0.0025 | 0.28 | 31500 | 0.0023 |
111
+ | 0.0024 | 0.28 | 32000 | 0.0023 |
112
+ | 0.0023 | 0.29 | 32500 | 0.0022 |
113
+ | 0.0024 | 0.29 | 33000 | 0.0022 |
114
+ | 0.0024 | 0.3 | 33500 | 0.0022 |
115
+ | 0.0022 | 0.3 | 34000 | 0.0022 |
116
+ | 0.0023 | 0.31 | 34500 | 0.0021 |
117
+ | 0.0023 | 0.31 | 35000 | 0.0021 |
118
+ | 0.0024 | 0.32 | 35500 | 0.0021 |
119
+ | 0.0023 | 0.32 | 36000 | 0.0021 |
120
+ | 0.0023 | 0.32 | 36500 | 0.0021 |
121
+ | 0.0021 | 0.33 | 37000 | 0.0021 |
122
+ | 0.0021 | 0.33 | 37500 | 0.0021 |
123
+ | 0.0022 | 0.34 | 38000 | 0.0021 |
124
+ | 0.0022 | 0.34 | 38500 | 0.0020 |
125
+ | 0.0022 | 0.35 | 39000 | 0.0020 |
126
+ | 0.0022 | 0.35 | 39500 | 0.0020 |
127
+ | 0.0022 | 0.36 | 40000 | 0.0022 |
128
+ | 0.0022 | 0.36 | 40500 | 0.0020 |
129
+ | 0.0022 | 0.36 | 41000 | 0.0020 |
130
+ | 0.0021 | 0.37 | 41500 | 0.0020 |
131
+ | 0.0022 | 0.37 | 42000 | 0.0020 |
132
+ | 0.0021 | 0.38 | 42500 | 0.0020 |
133
+ | 0.0021 | 0.38 | 43000 | 0.0019 |
134
+ | 0.0022 | 0.39 | 43500 | 0.0019 |
135
+ | 0.002 | 0.39 | 44000 | 0.0019 |
136
+ | 0.0021 | 0.4 | 44500 | 0.0020 |
137
+ | 0.0022 | 0.4 | 45000 | 0.0019 |
138
+ | 0.0022 | 0.4 | 45500 | 0.0019 |
139
+ | 0.002 | 0.41 | 46000 | 0.0019 |
140
+ | 0.0018 | 0.41 | 46500 | 0.0019 |
141
+ | 0.0022 | 0.42 | 47000 | 0.0019 |
142
+
143
+
144
+ ### Framework versions
145
+
146
+ - Transformers 4.21.2
147
+ - Pytorch 1.12.1+cu113
148
+ - Datasets 2.4.0
149
+ - Tokenizers 0.12.1