g8a9 commited on
Commit
abd8f7a
·
1 Parent(s): e2cb372

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: gpt2-kl_1_07-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_07-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: 0.5400
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
+ | 74.3984 | 0.02 | 10 | 69.5824 |
50
+ | 46.8803 | 0.04 | 20 | 32.9798 |
51
+ | 14.3833 | 0.06 | 30 | 10.6415 |
52
+ | 7.575 | 0.08 | 40 | 4.6376 |
53
+ | 3.743 | 0.1 | 50 | 2.0118 |
54
+ | 2.2075 | 0.12 | 60 | 1.0526 |
55
+ | 1.7704 | 0.14 | 70 | 0.9221 |
56
+ | 1.6742 | 0.16 | 80 | 0.7326 |
57
+ | 1.6277 | 0.18 | 90 | 0.6323 |
58
+ | 1.5239 | 0.2 | 100 | 0.6305 |
59
+ | 1.4315 | 0.22 | 110 | 0.6303 |
60
+ | 1.4175 | 0.24 | 120 | 0.6087 |
61
+ | 1.4311 | 0.26 | 130 | 0.6332 |
62
+ | 1.551 | 0.28 | 140 | 0.5729 |
63
+ | 1.594 | 0.3 | 150 | 0.5792 |
64
+ | 1.4637 | 0.32 | 160 | 0.5718 |
65
+ | 1.3139 | 0.34 | 170 | 0.5715 |
66
+ | 1.5152 | 0.36 | 180 | 0.5667 |
67
+ | 1.5807 | 0.38 | 190 | 0.5628 |
68
+ | 1.3656 | 0.4 | 200 | 0.5642 |
69
+ | 1.622 | 0.42 | 210 | 0.5629 |
70
+ | 1.5337 | 0.44 | 220 | 0.5561 |
71
+ | 1.3122 | 0.46 | 230 | 0.5596 |
72
+ | 1.4214 | 0.48 | 240 | 0.5549 |
73
+ | 1.3091 | 0.5 | 250 | 0.5594 |
74
+ | 1.408 | 0.52 | 260 | 0.5501 |
75
+ | 1.3621 | 0.54 | 270 | 0.5445 |
76
+ | 1.472 | 0.56 | 280 | 0.5457 |
77
+ | 1.3257 | 0.58 | 290 | 0.5445 |
78
+ | 1.2563 | 0.6 | 300 | 0.5443 |
79
+ | 1.451 | 0.62 | 310 | 0.5410 |
80
+ | 1.5655 | 0.64 | 320 | 0.5384 |
81
+ | 1.3168 | 0.66 | 330 | 0.5416 |
82
+ | 1.3216 | 0.68 | 340 | 0.5391 |
83
+ | 1.3135 | 0.7 | 350 | 0.5400 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.28.0
89
+ - Pytorch 1.11.0+cu113
90
+ - Datasets 2.11.0
91
+ - Tokenizers 0.12.1