MENG21 commited on
Commit
aaffea4
·
verified ·
1 Parent(s): a080ec4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md CHANGED
@@ -93,6 +93,69 @@ Use the code below to get started with the model.
93
 
94
  ## Training Details
95
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96
  ### Training Data
97
 
98
  <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
93
 
94
  ## Training Details
95
 
96
+ <!-- <###################################################################> -->
97
+
98
+ # results_bert-large-uncased
99
+
100
+ This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
101
+ It achieves the following results on the evaluation set:
102
+ - Loss: 0.2128
103
+ - Accuracy: 0.9141
104
+ - Precision: 0.9182
105
+ - Recall: 0.9421
106
+ - F1: 0.9300
107
+
108
+ ## Model description
109
+
110
+ More information needed
111
+
112
+ ## Intended uses & limitations
113
+
114
+ More information needed
115
+
116
+ ## Training and evaluation data
117
+
118
+ More information needed
119
+
120
+ ## Training procedure
121
+
122
+ ### Training hyperparameters
123
+
124
+ The following hyperparameters were used during training:
125
+ - learning_rate: 5e-05
126
+ - train_batch_size: 32
127
+ - eval_batch_size: 32
128
+ - seed: 42
129
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
130
+ - lr_scheduler_type: linear
131
+ - lr_scheduler_warmup_ratio: 0.1
132
+ - num_epochs: 1
133
+
134
+ ### Training results
135
+
136
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
137
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
138
+ | 0.6415 | 0.09 | 50 | 0.5315 | 0.7175 | 0.6981 | 0.9394 | 0.8010 |
139
+ | 0.4007 | 0.18 | 100 | 0.7702 | 0.7243 | 0.9892 | 0.5505 | 0.7074 |
140
+ | 0.5158 | 0.28 | 150 | 0.4075 | 0.8591 | 0.8904 | 0.8748 | 0.8825 |
141
+ | 0.3934 | 0.37 | 200 | 0.2809 | 0.8763 | 0.9354 | 0.8546 | 0.8932 |
142
+ | 0.2691 | 0.46 | 250 | 0.3406 | 0.8832 | 0.8837 | 0.9294 | 0.9060 |
143
+ | 0.2814 | 0.55 | 300 | 0.2582 | 0.8768 | 0.8512 | 0.9651 | 0.9046 |
144
+ | 0.2735 | 0.64 | 350 | 0.2715 | 0.8953 | 0.8708 | 0.9711 | 0.9182 |
145
+ | 0.2411 | 0.74 | 400 | 0.2389 | 0.9103 | 0.9242 | 0.9279 | 0.9260 |
146
+ | 0.2371 | 0.83 | 450 | 0.2081 | 0.9104 | 0.9212 | 0.9316 | 0.9264 |
147
+ | 0.1974 | 0.92 | 500 | 0.2128 | 0.9141 | 0.9182 | 0.9421 | 0.9300 |
148
+
149
+
150
+ ### Framework versions
151
+
152
+ - Transformers 4.37.2
153
+ - Pytorch 2.1.0+cu121
154
+ - Datasets 2.17.0
155
+ - Tokenizers 0.15.2
156
+
157
+ <!-- <###################################################################> -->
158
+
159
  ### Training Data
160
 
161
  <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->