Hugging Face's logo

din0s
/
t5-small-finetuned-en-to-it

Text Generation
Transformers
PyTorch
t5
text2text-generation
Generated from Trainer
Eval Results
text-generation-inference
Model card Files Community
1
din0s commited on
Commit
3eded7a
·
1 Parent(s): 5692cf6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +115 -0
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - ccmatrix
7
+ metrics:
8
+ - bleu
9
+ model-index:
10
+ - name: t5-small-finetuned-en-to-it
11
+ results:
12
+ - task:
13
+ name: Sequence-to-sequence Language Modeling
14
+ type: text2text-generation
15
+ dataset:
16
+ name: ccmatrix
17
+ type: ccmatrix
18
+ config: en-it
19
+ split: train[3000:15000]
20
+ args: en-it
21
+ metrics:
22
+ - name: Bleu
23
+ type: bleu
24
+ value: 7.3298
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # t5-small-finetuned-en-to-it
31
+
32
+ This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the ccmatrix dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 2.2698
35
+ - Bleu: 7.3298
36
+ - Gen Len: 62.3753
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 2e-05
56
+ - train_batch_size: 96
57
+ - eval_batch_size: 96
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 40
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
67
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
68
+ | No log | 1.0 | 125 | 3.0010 | 2.7294 | 56.4513 |
69
+ | No log | 2.0 | 250 | 2.8999 | 2.3228 | 81.4993 |
70
+ | No log | 3.0 | 375 | 2.8281 | 2.3065 | 92.3353 |
71
+ | 3.3202 | 4.0 | 500 | 2.7722 | 2.5982 | 91.8093 |
72
+ | 3.3202 | 5.0 | 625 | 2.7254 | 2.9279 | 89.0907 |
73
+ | 3.3202 | 6.0 | 750 | 2.6839 | 3.0747 | 89.2827 |
74
+ | 3.3202 | 7.0 | 875 | 2.6470 | 3.207 | 87.948 |
75
+ | 3.0355 | 8.0 | 1000 | 2.6132 | 3.355 | 85.2487 |
76
+ | 3.0355 | 9.0 | 1125 | 2.5835 | 3.8401 | 80.578 |
77
+ | 3.0355 | 10.0 | 1250 | 2.5552 | 4.2905 | 75.818 |
78
+ | 3.0355 | 11.0 | 1375 | 2.5323 | 4.3866 | 75.2433 |
79
+ | 2.8903 | 12.0 | 1500 | 2.5079 | 4.5687 | 74.906 |
80
+ | 2.8903 | 13.0 | 1625 | 2.4881 | 4.7844 | 71.5773 |
81
+ | 2.8903 | 14.0 | 1750 | 2.4668 | 4.876 | 71.68 |
82
+ | 2.8903 | 15.0 | 1875 | 2.4485 | 5.1292 | 70.118 |
83
+ | 2.7891 | 16.0 | 2000 | 2.4322 | 5.3297 | 68.894 |
84
+ | 2.7891 | 17.0 | 2125 | 2.4161 | 5.555 | 68.2293 |
85
+ | 2.7891 | 18.0 | 2250 | 2.4010 | 5.7113 | 67.2907 |
86
+ | 2.7891 | 19.0 | 2375 | 2.3892 | 5.9105 | 66.6287 |
87
+ | 2.713 | 20.0 | 2500 | 2.3756 | 6.0057 | 66.112 |
88
+ | 2.713 | 21.0 | 2625 | 2.3643 | 6.3118 | 64.6193 |
89
+ | 2.713 | 22.0 | 2750 | 2.3533 | 6.476 | 64.31 |
90
+ | 2.713 | 23.0 | 2875 | 2.3432 | 6.7102 | 63.5467 |
91
+ | 2.6584 | 24.0 | 3000 | 2.3342 | 6.7604 | 63.6567 |
92
+ | 2.6584 | 25.0 | 3125 | 2.3253 | 6.8418 | 63.6573 |
93
+ | 2.6584 | 26.0 | 3250 | 2.3180 | 6.9165 | 63.5893 |
94
+ | 2.6584 | 27.0 | 3375 | 2.3120 | 7.0217 | 63.1033 |
95
+ | 2.616 | 28.0 | 3500 | 2.3056 | 6.9148 | 63.598 |
96
+ | 2.616 | 29.0 | 3625 | 2.2987 | 6.9961 | 63.6267 |
97
+ | 2.616 | 30.0 | 3750 | 2.2935 | 7.2238 | 62.8373 |
98
+ | 2.616 | 31.0 | 3875 | 2.2892 | 7.1906 | 62.7793 |
99
+ | 2.587 | 32.0 | 4000 | 2.2849 | 7.2052 | 63.126 |
100
+ | 2.587 | 33.0 | 4125 | 2.2815 | 7.3272 | 62.526 |
101
+ | 2.587 | 34.0 | 4250 | 2.2782 | 7.3603 | 62.4313 |
102
+ | 2.587 | 35.0 | 4375 | 2.2756 | 7.3072 | 62.6307 |
103
+ | 2.5673 | 36.0 | 4500 | 2.2737 | 7.3586 | 62.1633 |
104
+ | 2.5673 | 37.0 | 4625 | 2.2718 | 7.3485 | 62.358 |
105
+ | 2.5673 | 38.0 | 4750 | 2.2707 | 7.3406 | 62.298 |
106
+ | 2.5673 | 39.0 | 4875 | 2.2700 | 7.3233 | 62.42 |
107
+ | 2.5591 | 40.0 | 5000 | 2.2698 | 7.3298 | 62.3753 |
108
+
109
+
110
+ ### Framework versions
111
+
112
+ - Transformers 4.22.1
113
+ - Pytorch 1.12.1
114
+ - Datasets 2.5.1
115
+ - Tokenizers 0.11.0