Hugging Face's logo

Bainbridge
/
gpt2-kl_1_06-hs_cn

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
g8a9 commited on
Commit
8c35fff
·
1 Parent(s): 7e908af

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +102 -0
README.md ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: gpt2-kl_1_06-hs_cn
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-kl_1_06-hs_cn
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: 0.5352
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
+ | 74.175 | 0.02 | 10 | 69.5742 |
50
+ | 46.6833 | 0.04 | 20 | 32.9573 |
51
+ | 14.147 | 0.06 | 30 | 10.6344 |
52
+ | 7.4081 | 0.08 | 40 | 4.2202 |
53
+ | 4.1981 | 0.1 | 50 | 2.0325 |
54
+ | 1.9903 | 0.12 | 60 | 1.0829 |
55
+ | 1.5743 | 0.14 | 70 | 0.8595 |
56
+ | 1.4537 | 0.16 | 80 | 0.7859 |
57
+ | 1.4022 | 0.18 | 90 | 0.7212 |
58
+ | 1.3332 | 0.2 | 100 | 0.6727 |
59
+ | 1.1681 | 0.22 | 110 | 0.6850 |
60
+ | 1.1991 | 0.24 | 120 | 0.5978 |
61
+ | 1.2297 | 0.26 | 130 | 0.6137 |
62
+ | 1.3475 | 0.28 | 140 | 0.5888 |
63
+ | 1.3468 | 0.3 | 150 | 0.5783 |
64
+ | 1.2516 | 0.32 | 160 | 0.5765 |
65
+ | 1.1055 | 0.34 | 170 | 0.5752 |
66
+ | 1.2874 | 0.36 | 180 | 0.5684 |
67
+ | 1.3511 | 0.38 | 190 | 0.5613 |
68
+ | 1.1492 | 0.4 | 200 | 0.5571 |
69
+ | 1.3802 | 0.42 | 210 | 0.5567 |
70
+ | 1.3072 | 0.44 | 220 | 0.5527 |
71
+ | 1.1026 | 0.46 | 230 | 0.5538 |
72
+ | 1.199 | 0.48 | 240 | 0.5497 |
73
+ | 1.1124 | 0.5 | 250 | 0.5513 |
74
+ | 1.1861 | 0.52 | 260 | 0.5495 |
75
+ | 1.1603 | 0.54 | 270 | 0.5434 |
76
+ | 1.2407 | 0.56 | 280 | 0.5451 |
77
+ | 1.1338 | 0.58 | 290 | 0.5437 |
78
+ | 1.0556 | 0.6 | 300 | 0.5428 |
79
+ | 1.2218 | 0.62 | 310 | 0.5392 |
80
+ | 1.3505 | 0.64 | 320 | 0.5408 |
81
+ | 1.1001 | 0.66 | 330 | 0.5426 |
82
+ | 1.1123 | 0.68 | 340 | 0.5385 |
83
+ | 1.1046 | 0.7 | 350 | 0.5385 |
84
+ | 1.1291 | 0.72 | 360 | 0.5383 |
85
+ | 1.2087 | 0.74 | 370 | 0.5378 |
86
+ | 1.1888 | 0.76 | 380 | 0.5380 |
87
+ | 1.1634 | 0.78 | 390 | 0.5363 |
88
+ | 1.249 | 0.8 | 400 | 0.5351 |
89
+ | 1.1197 | 0.82 | 410 | 0.5350 |
90
+ | 1.1508 | 0.84 | 420 | 0.5366 |
91
+ | 1.2025 | 0.86 | 430 | 0.5340 |
92
+ | 1.13 | 0.88 | 440 | 0.5347 |
93
+ | 1.1664 | 0.9 | 450 | 0.5371 |
94
+ | 1.048 | 0.92 | 460 | 0.5352 |
95
+
96
+
97
+ ### Framework versions
98
+
99
+ - Transformers 4.28.0
100
+ - Pytorch 1.11.0+cu113
101
+ - Datasets 2.11.0
102
+ - Tokenizers 0.12.1