Hugging Face's logo

Mirelle
/
t5-small-finetuned-ro-to-en

Transformers
PyTorch
TensorBoard
t5
text2text-generation
Generated from Trainer
Eval Results (legacy)
text-generation-inference
Model card Files
xet
Metrics Community
1
Mirelle commited on
Commit
081d363
·
1 Parent(s): dd59ce4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +92 -0
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - wmt16
7
+ metrics:
8
+ - bleu
9
+ model-index:
10
+ - name: t5-small-finetuned-ro-to-en
11
+ results:
12
+ - task:
13
+ name: Sequence-to-sequence Language Modeling
14
+ type: text2text-generation
15
+ dataset:
16
+ name: wmt16
17
+ type: wmt16
18
+ args: ro-en
19
+ metrics:
20
+ - name: Bleu
21
+ type: bleu
22
+ value: 13.4499
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # t5-small-finetuned-ro-to-en
29
+
30
+ This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the wmt16 dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 1.5877
33
+ - Bleu: 13.4499
34
+ - Gen Len: 17.5073
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 0.0001
54
+ - train_batch_size: 16
55
+ - eval_batch_size: 16
56
+ - seed: 42
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: linear
59
+ - num_epochs: 1
60
+ - mixed_precision_training: Native AMP
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
65
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
66
+ | 1.6167 | 0.05 | 2000 | 1.8649 | 9.7029 | 17.5753 |
67
+ | 1.4551 | 0.1 | 4000 | 1.7810 | 10.6382 | 17.5358 |
68
+ | 1.3723 | 0.16 | 6000 | 1.7369 | 11.1285 | 17.5158 |
69
+ | 1.3373 | 0.21 | 8000 | 1.7086 | 11.6173 | 17.5013 |
70
+ | 1.2935 | 0.26 | 10000 | 1.6890 | 12.0641 | 17.5038 |
71
+ | 1.2632 | 0.31 | 12000 | 1.6670 | 12.3012 | 17.5253 |
72
+ | 1.2463 | 0.37 | 14000 | 1.6556 | 12.3991 | 17.5153 |
73
+ | 1.2272 | 0.42 | 16000 | 1.6442 | 12.7392 | 17.4732 |
74
+ | 1.2052 | 0.47 | 18000 | 1.6328 | 12.8446 | 17.5143 |
75
+ | 1.1985 | 0.52 | 20000 | 1.6233 | 13.0892 | 17.4807 |
76
+ | 1.1821 | 0.58 | 22000 | 1.6153 | 13.1529 | 17.4952 |
77
+ | 1.1791 | 0.63 | 24000 | 1.6079 | 13.2964 | 17.5088 |
78
+ | 1.1698 | 0.68 | 26000 | 1.6038 | 13.3548 | 17.4842 |
79
+ | 1.154 | 0.73 | 28000 | 1.5957 | 13.3012 | 17.5053 |
80
+ | 1.1634 | 0.79 | 30000 | 1.5931 | 13.4203 | 17.5083 |
81
+ | 1.1487 | 0.84 | 32000 | 1.5893 | 13.3959 | 17.5123 |
82
+ | 1.1495 | 0.89 | 34000 | 1.5875 | 13.3745 | 17.4902 |
83
+ | 1.1458 | 0.94 | 36000 | 1.5877 | 13.4129 | 17.5043 |
84
+ | 1.1465 | 1.0 | 38000 | 1.5877 | 13.4499 | 17.5073 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - Transformers 4.12.5
90
+ - Pytorch 1.10.0+cu111
91
+ - Datasets 1.16.1
92
+ - Tokenizers 0.10.3