Hugging Face's logo

ahazeemi
/
bart-base-en-to-de

Text2Text Generation
Transformers
PyTorch
bart
generated_from_trainer
Inference Endpoints
Model card Files Community
ahazeemi commited on
Commit
f0f3d5c
•
1 Parent(s): 7c49234

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +88 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - bleu
7
+ model-index:
8
+ - name: bart-base-en-to-de
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
+ # bart-base-en-to-de
16
+
17
+ This model is a fine-tuned version of [ahazeemi/bart-base-finetuned-en-to-de](https://huggingface.co/ahazeemi/bart-base-finetuned-en-to-de) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.9665
20
+ - Bleu: 4.7851
21
+ - Gen Len: 19.453
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 3e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 1
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
+ |:-------------:|:-----:|:------:|:---------------:|:------:|:-------:|
53
+ | 1.319 | 0.04 | 5000 | 1.1247 | 4.4467 | 19.447 |
54
+ | 1.295 | 0.07 | 10000 | 1.1012 | 4.4235 | 19.458 |
55
+ | 1.2901 | 0.11 | 15000 | 1.0923 | 4.4386 | 19.4423 |
56
+ | 1.2678 | 0.14 | 20000 | 1.0803 | 4.5259 | 19.4557 |
57
+ | 1.267 | 0.18 | 25000 | 1.0724 | 4.5534 | 19.4653 |
58
+ | 1.2444 | 0.21 | 30000 | 1.0591 | 4.4944 | 19.4623 |
59
+ | 1.2365 | 0.25 | 35000 | 1.0509 | 4.5736 | 19.446 |
60
+ | 1.2137 | 0.28 | 40000 | 1.0400 | 4.5346 | 19.4553 |
61
+ | 1.214 | 0.32 | 45000 | 1.0340 | 4.5733 | 19.4543 |
62
+ | 1.218 | 0.35 | 50000 | 1.0283 | 4.6076 | 19.4693 |
63
+ | 1.2118 | 0.39 | 55000 | 1.0225 | 4.6192 | 19.454 |
64
+ | 1.1948 | 0.43 | 60000 | 1.0152 | 4.6082 | 19.4553 |
65
+ | 1.1932 | 0.46 | 65000 | 1.0128 | 4.665 | 19.449 |
66
+ | 1.1889 | 0.5 | 70000 | 1.0028 | 4.6929 | 19.4493 |
67
+ | 1.2154 | 0.53 | 75000 | 1.0004 | 4.7151 | 19.4477 |
68
+ | 1.194 | 0.57 | 80000 | 0.9950 | 4.6655 | 19.467 |
69
+ | 1.1847 | 0.6 | 85000 | 0.9966 | 4.708 | 19.451 |
70
+ | 1.1848 | 0.64 | 90000 | 0.9897 | 4.7794 | 19.458 |
71
+ | 1.1762 | 0.67 | 95000 | 0.9866 | 4.7204 | 19.4523 |
72
+ | 1.1818 | 0.71 | 100000 | 0.9803 | 4.7137 | 19.458 |
73
+ | 1.1613 | 0.75 | 105000 | 0.9788 | 4.7652 | 19.4573 |
74
+ | 1.1738 | 0.78 | 110000 | 0.9775 | 4.8088 | 19.453 |
75
+ | 1.1569 | 0.82 | 115000 | 0.9752 | 4.7522 | 19.4577 |
76
+ | 1.1631 | 0.85 | 120000 | 0.9713 | 4.7301 | 19.4513 |
77
+ | 1.1517 | 0.89 | 125000 | 0.9690 | 4.7935 | 19.456 |
78
+ | 1.1577 | 0.92 | 130000 | 0.9686 | 4.791 | 19.4543 |
79
+ | 1.1607 | 0.96 | 135000 | 0.9676 | 4.7529 | 19.4533 |
80
+ | 1.153 | 0.99 | 140000 | 0.9665 | 4.7851 | 19.453 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.22.2
86
+ - Pytorch 1.12.0+cu116
87
+ - Datasets 2.5.1
88
+ - Tokenizers 0.12.1