Hugging Face's logo

Bainbridge
/
gpt2-synth

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
1
g8a9 commited on
Commit
a222e1e
·
1 Parent(s): fe6a7b7

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: gpt2-synth
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
+ # gpt2-synth
14
+
15
+ This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.1783
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: 5e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 4
39
+ - seed: 21
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - lr_scheduler_warmup_ratio: 0.1
43
+ - num_epochs: 3.0
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 73.0212 | 0.02 | 10 | 65.7853 |
50
+ | 38.3819 | 0.04 | 20 | 20.2835 |
51
+ | 11.6035 | 0.07 | 30 | 9.2104 |
52
+ | 7.5582 | 0.09 | 40 | 3.6178 |
53
+ | 2.1601 | 0.11 | 50 | 1.5943 |
54
+ | 0.9769 | 0.13 | 60 | 0.9299 |
55
+ | 0.7577 | 0.15 | 70 | 0.6257 |
56
+ | 0.5434 | 0.18 | 80 | 0.4690 |
57
+ | 0.4756 | 0.2 | 90 | 0.5805 |
58
+ | 0.4247 | 0.22 | 100 | 0.3353 |
59
+ | 0.3179 | 0.24 | 110 | 0.2710 |
60
+ | 0.2476 | 0.26 | 120 | 0.2642 |
61
+ | 0.2604 | 0.29 | 130 | 0.2667 |
62
+ | 0.212 | 0.31 | 140 | 0.2723 |
63
+ | 0.2819 | 0.33 | 150 | 0.2356 |
64
+ | 0.2693 | 0.35 | 160 | 0.2283 |
65
+ | 0.2415 | 0.37 | 170 | 0.2297 |
66
+ | 0.2237 | 0.4 | 180 | 0.2207 |
67
+ | 0.2412 | 0.42 | 190 | 0.2204 |
68
+ | 0.2245 | 0.44 | 200 | 0.2191 |
69
+ | 0.2641 | 0.46 | 210 | 0.2112 |
70
+ | 0.22 | 0.48 | 220 | 0.2096 |
71
+ | 0.1912 | 0.51 | 230 | 0.2096 |
72
+ | 0.2152 | 0.53 | 240 | 0.2067 |
73
+ | 0.2497 | 0.55 | 250 | 0.2028 |
74
+ | 0.2042 | 0.57 | 260 | 0.2025 |
75
+ | 0.2263 | 0.59 | 270 | 0.2003 |
76
+ | 0.2047 | 0.62 | 280 | 0.1994 |
77
+ | 0.2081 | 0.64 | 290 | 0.1979 |
78
+ | 0.203 | 0.66 | 300 | 0.1954 |
79
+ | 0.1872 | 0.68 | 310 | 0.1954 |
80
+ | 0.1669 | 0.7 | 320 | 0.1958 |
81
+ | 0.1845 | 0.73 | 330 | 0.1935 |
82
+ | 0.1917 | 0.75 | 340 | 0.1913 |
83
+ | 0.2066 | 0.77 | 350 | 0.1880 |
84
+ | 0.1873 | 0.79 | 360 | 0.1880 |
85
+ | 0.1889 | 0.81 | 370 | 0.1867 |
86
+ | 0.2196 | 0.84 | 380 | 0.1853 |
87
+ | 0.2062 | 0.86 | 390 | 0.1848 |
88
+ | 0.1802 | 0.88 | 400 | 0.1836 |
89
+ | 0.1754 | 0.9 | 410 | 0.1828 |
90
+ | 0.1997 | 0.92 | 420 | 0.1813 |
91
+ | 0.2072 | 0.95 | 430 | 0.1790 |
92
+ | 0.19 | 0.97 | 440 | 0.1774 |
93
+ | 0.2208 | 0.99 | 450 | 0.1785 |
94
+ | 0.1706 | 1.01 | 460 | 0.1790 |
95
+ | 0.1534 | 1.03 | 470 | 0.1783 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.24.0
101
+ - Pytorch 1.11.0+cu113
102
+ - Datasets 2.6.1
103
+ - Tokenizers 0.12.1