Hugging Face's logo

qgyd2021
/
lip_service_4chan

Text Generation
Transformers
PyTorch
Chinese
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
qgyd2021 commited on
Commit
431ab53
•
1 Parent(s): f322ceb

Model save

Browse files
Files changed (2) hide show
  1. README.md +184 -0
  2. generation_config.json +6 -0
README.md ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: uer/gpt2-chinese-cluecorpussmall
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - lip_service4chan
7
+ model-index:
8
+ - name: lib_service_4chan
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # lib_service_4chan
16
+
17
+ This model is a fine-tuned version of [uer/gpt2-chinese-cluecorpussmall](https://huggingface.co/uer/gpt2-chinese-cluecorpussmall) on the lip_service4chan dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8635
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0002
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 2
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 32
46
+ - total_eval_batch_size: 16
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 1000
50
+ - num_epochs: 1.0
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:-----:|:-----:|:---------------:|
56
+ | 2.716 | 0.01 | 100 | 1.9495 |
57
+ | 1.8985 | 0.02 | 200 | 1.6915 |
58
+ | 1.7151 | 0.02 | 300 | 1.5763 |
59
+ | 1.6217 | 0.03 | 400 | 1.5115 |
60
+ | 1.564 | 0.04 | 500 | 1.4694 |
61
+ | 1.5461 | 0.05 | 600 | 1.4379 |
62
+ | 1.4943 | 0.06 | 700 | 1.4127 |
63
+ | 1.4737 | 0.07 | 800 | 1.3890 |
64
+ | 1.4399 | 0.07 | 900 | 1.3813 |
65
+ | 1.4356 | 0.08 | 1000 | 1.3540 |
66
+ | 1.3999 | 0.09 | 1100 | 1.3329 |
67
+ | 1.3668 | 0.1 | 1200 | 1.3153 |
68
+ | 1.3604 | 0.11 | 1300 | 1.3029 |
69
+ | 1.3352 | 0.12 | 1400 | 1.2834 |
70
+ | 1.3278 | 0.12 | 1500 | 1.2619 |
71
+ | 1.315 | 0.13 | 1600 | 1.2539 |
72
+ | 1.2854 | 0.14 | 1700 | 1.2432 |
73
+ | 1.292 | 0.15 | 1800 | 1.2288 |
74
+ | 1.2795 | 0.16 | 1900 | 1.2188 |
75
+ | 1.2677 | 0.16 | 2000 | 1.2059 |
76
+ | 1.2599 | 0.17 | 2100 | 1.2019 |
77
+ | 1.2479 | 0.18 | 2200 | 1.1915 |
78
+ | 1.2245 | 0.19 | 2300 | 1.1827 |
79
+ | 1.2326 | 0.2 | 2400 | 1.1734 |
80
+ | 1.2124 | 0.21 | 2500 | 1.1660 |
81
+ | 1.2171 | 0.21 | 2600 | 1.1576 |
82
+ | 1.1917 | 0.22 | 2700 | 1.1518 |
83
+ | 1.1867 | 0.23 | 2800 | 1.1444 |
84
+ | 1.1821 | 0.24 | 2900 | 1.1386 |
85
+ | 1.1741 | 0.25 | 3000 | 1.1347 |
86
+ | 1.1753 | 0.25 | 3100 | 1.1293 |
87
+ | 1.1629 | 0.26 | 3200 | 1.1264 |
88
+ | 1.1694 | 0.27 | 3300 | 1.1201 |
89
+ | 1.1482 | 0.28 | 3400 | 1.1146 |
90
+ | 1.156 | 0.29 | 3500 | 1.1052 |
91
+ | 1.1512 | 0.3 | 3600 | 1.0982 |
92
+ | 1.142 | 0.3 | 3700 | 1.0971 |
93
+ | 1.1544 | 0.31 | 3800 | 1.0920 |
94
+ | 1.1312 | 0.32 | 3900 | 1.0869 |
95
+ | 1.1394 | 0.33 | 4000 | 1.0808 |
96
+ | 1.123 | 0.34 | 4100 | 1.0747 |
97
+ | 1.1154 | 0.35 | 4200 | 1.0715 |
98
+ | 1.1064 | 0.35 | 4300 | 1.0674 |
99
+ | 1.1245 | 0.36 | 4400 | 1.0620 |
100
+ | 1.1036 | 0.37 | 4500 | 1.0575 |
101
+ | 1.0963 | 0.38 | 4600 | 1.0568 |
102
+ | 1.0987 | 0.39 | 4700 | 1.0491 |
103
+ | 1.0859 | 0.39 | 4800 | 1.0443 |
104
+ | 1.0845 | 0.4 | 4900 | 1.0432 |
105
+ | 1.0938 | 0.41 | 5000 | 1.0410 |
106
+ | 1.087 | 0.42 | 5100 | 1.0334 |
107
+ | 1.077 | 0.43 | 5200 | 1.0324 |
108
+ | 1.0787 | 0.44 | 5300 | 1.0276 |
109
+ | 1.068 | 0.44 | 5400 | 1.0220 |
110
+ | 1.0748 | 0.45 | 5500 | 1.0199 |
111
+ | 1.0622 | 0.46 | 5600 | 1.0169 |
112
+ | 1.0555 | 0.47 | 5700 | 1.0153 |
113
+ | 1.0498 | 0.48 | 5800 | 1.0100 |
114
+ | 1.055 | 0.49 | 5900 | 1.0074 |
115
+ | 1.0424 | 0.49 | 6000 | 1.0020 |
116
+ | 1.0465 | 0.5 | 6100 | 0.9976 |
117
+ | 1.0414 | 0.51 | 6200 | 0.9942 |
118
+ | 1.0355 | 0.52 | 6300 | 0.9919 |
119
+ | 1.0234 | 0.53 | 6400 | 0.9883 |
120
+ | 1.0205 | 0.53 | 6500 | 0.9857 |
121
+ | 1.0316 | 0.54 | 6600 | 0.9805 |
122
+ | 1.0137 | 0.55 | 6700 | 0.9788 |
123
+ | 1.0222 | 0.56 | 6800 | 0.9773 |
124
+ | 1.0219 | 0.57 | 6900 | 0.9722 |
125
+ | 1.0032 | 0.58 | 7000 | 0.9706 |
126
+ | 1.0039 | 0.58 | 7100 | 0.9669 |
127
+ | 1.0166 | 0.59 | 7200 | 0.9635 |
128
+ | 1.0065 | 0.6 | 7300 | 0.9614 |
129
+ | 1.0087 | 0.61 | 7400 | 0.9574 |
130
+ | 0.9968 | 0.62 | 7500 | 0.9525 |
131
+ | 1.0031 | 0.62 | 7600 | 0.9503 |
132
+ | 0.99 | 0.63 | 7700 | 0.9491 |
133
+ | 0.9946 | 0.64 | 7800 | 0.9457 |
134
+ | 0.9944 | 0.65 | 7900 | 0.9424 |
135
+ | 0.9854 | 0.66 | 8000 | 0.9399 |
136
+ | 0.9797 | 0.67 | 8100 | 0.9364 |
137
+ | 0.9804 | 0.67 | 8200 | 0.9341 |
138
+ | 0.9835 | 0.68 | 8300 | 0.9318 |
139
+ | 0.9849 | 0.69 | 8400 | 0.9299 |
140
+ | 0.9753 | 0.7 | 8500 | 0.9274 |
141
+ | 0.975 | 0.71 | 8600 | 0.9238 |
142
+ | 0.9649 | 0.72 | 8700 | 0.9225 |
143
+ | 0.9654 | 0.72 | 8800 | 0.9202 |
144
+ | 0.958 | 0.73 | 8900 | 0.9167 |
145
+ | 0.9679 | 0.74 | 9000 | 0.9143 |
146
+ | 0.9631 | 0.75 | 9100 | 0.9110 |
147
+ | 0.9633 | 0.76 | 9200 | 0.9086 |
148
+ | 0.9495 | 0.76 | 9300 | 0.9071 |
149
+ | 0.9625 | 0.77 | 9400 | 0.9036 |
150
+ | 0.9519 | 0.78 | 9500 | 0.9023 |
151
+ | 0.9399 | 0.79 | 9600 | 0.8993 |
152
+ | 0.9624 | 0.8 | 9700 | 0.8973 |
153
+ | 0.9418 | 0.81 | 9800 | 0.8963 |
154
+ | 0.9394 | 0.81 | 9900 | 0.8933 |
155
+ | 0.947 | 0.82 | 10000 | 0.8919 |
156
+ | 0.9326 | 0.83 | 10100 | 0.8900 |
157
+ | 0.9326 | 0.84 | 10200 | 0.8886 |
158
+ | 0.9343 | 0.85 | 10300 | 0.8860 |
159
+ | 0.9263 | 0.85 | 10400 | 0.8841 |
160
+ | 0.9256 | 0.86 | 10500 | 0.8818 |
161
+ | 0.9373 | 0.87 | 10600 | 0.8807 |
162
+ | 0.9314 | 0.88 | 10700 | 0.8789 |
163
+ | 0.9203 | 0.89 | 10800 | 0.8770 |
164
+ | 0.927 | 0.9 | 10900 | 0.8754 |
165
+ | 0.934 | 0.9 | 11000 | 0.8744 |
166
+ | 0.9193 | 0.91 | 11100 | 0.8727 |
167
+ | 0.9185 | 0.92 | 11200 | 0.8714 |
168
+ | 0.9188 | 0.93 | 11300 | 0.8702 |
169
+ | 0.9165 | 0.94 | 11400 | 0.8693 |
170
+ | 0.9209 | 0.95 | 11500 | 0.8682 |
171
+ | 0.9241 | 0.95 | 11600 | 0.8670 |
172
+ | 0.9182 | 0.96 | 11700 | 0.8662 |
173
+ | 0.9076 | 0.97 | 11800 | 0.8653 |
174
+ | 0.9225 | 0.98 | 11900 | 0.8643 |
175
+ | 0.9094 | 0.99 | 12000 | 0.8640 |
176
+ | 0.913 | 0.99 | 12100 | 0.8635 |
177
+
178
+
179
+ ### Framework versions
180
+
181
+ - Transformers 4.33.0
182
+ - Pytorch 2.0.0
183
+ - Datasets 2.1.0
184
+ - Tokenizers 0.13.3
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.33.0"
6
+ }