helenabon commited on
Commit
fc5e345
1 Parent(s): 9a6dcfb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: gpt2-kl_001_06_hscnspecial-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_001_06_hscnspecial-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: 0.5489
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
+ | 73.5243 | 0.02 | 10 | 69.5733 |
50
+ | 46.0785 | 0.04 | 20 | 32.9424 |
51
+ | 13.5445 | 0.06 | 30 | 10.6459 |
52
+ | 6.772 | 0.08 | 40 | 4.2120 |
53
+ | 3.5618 | 0.1 | 50 | 2.0539 |
54
+ | 1.4416 | 0.12 | 60 | 1.0919 |
55
+ | 1.0628 | 0.14 | 70 | 0.8710 |
56
+ | 0.8751 | 0.16 | 80 | 0.7180 |
57
+ | 0.7178 | 0.18 | 90 | 0.7504 |
58
+ | 0.7072 | 0.2 | 100 | 0.6374 |
59
+ | 0.5923 | 0.22 | 110 | 0.6286 |
60
+ | 0.6271 | 0.24 | 120 | 0.6355 |
61
+ | 0.6407 | 0.26 | 130 | 0.6217 |
62
+ | 0.6474 | 0.28 | 140 | 0.5978 |
63
+ | 0.5946 | 0.3 | 150 | 0.5985 |
64
+ | 0.6073 | 0.32 | 160 | 0.5887 |
65
+ | 0.5149 | 0.34 | 170 | 0.5773 |
66
+ | 0.6478 | 0.36 | 180 | 0.5671 |
67
+ | 0.6186 | 0.38 | 190 | 0.5593 |
68
+ | 0.5708 | 0.4 | 200 | 0.5572 |
69
+ | 0.6788 | 0.42 | 210 | 0.5545 |
70
+ | 0.6316 | 0.44 | 220 | 0.5503 |
71
+ | 0.5317 | 0.46 | 230 | 0.5508 |
72
+ | 0.5464 | 0.48 | 240 | 0.5475 |
73
+ | 0.548 | 0.5 | 250 | 0.5466 |
74
+ | 0.5488 | 0.52 | 260 | 0.5473 |
75
+ | 0.5551 | 0.54 | 270 | 0.5469 |
76
+ | 0.5867 | 0.56 | 280 | 0.5489 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.29.0.dev0
82
+ - Pytorch 1.12.0a0+bd13bc6
83
+ - Datasets 2.12.0
84
+ - Tokenizers 0.13.3