santiviquez commited on
Commit
b7b782c
1 Parent(s): df7d714

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +95 -0
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - summarization
5
+ - generated_from_trainer
6
+ datasets:
7
+ - samsum
8
+ metrics:
9
+ - rouge
10
+ model-index:
11
+ - name: t5-small-finetuned-samsum-en
12
+ results:
13
+ - task:
14
+ name: Sequence-to-sequence Language Modeling
15
+ type: text2text-generation
16
+ dataset:
17
+ name: samsum
18
+ type: samsum
19
+ args: samsum
20
+ metrics:
21
+ - name: Rouge1
22
+ type: rouge
23
+ value: 42.3215
24
+ ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # t5-small-finetuned-samsum-en
30
+
31
+ This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the samsum dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 1.7863
34
+ - Rouge1: 42.3215
35
+ - Rouge2: 19.4644
36
+ - Rougel: 35.3715
37
+ - Rougelsum: 39.1274
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 5.6e-05
57
+ - train_batch_size: 10
58
+ - eval_batch_size: 10
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - num_epochs: 20
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
67
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
68
+ | 2.2448 | 1.0 | 300 | 1.8993 | 39.5059 | 17.0654 | 32.9974 | 36.6153 |
69
+ | 2.0428 | 2.0 | 600 | 1.8499 | 40.0529 | 17.4367 | 33.4804 | 37.057 |
70
+ | 1.9626 | 3.0 | 900 | 1.8278 | 40.7994 | 17.918 | 34.0773 | 37.6219 |
71
+ | 1.8992 | 4.0 | 1200 | 1.8118 | 41.3782 | 18.5579 | 34.7794 | 38.4994 |
72
+ | 1.8429 | 5.0 | 1500 | 1.8006 | 41.8624 | 18.7592 | 34.9262 | 38.7019 |
73
+ | 1.8057 | 6.0 | 1800 | 1.7988 | 41.1316 | 18.5242 | 34.7271 | 38.2821 |
74
+ | 1.775 | 7.0 | 2100 | 1.7856 | 42.2036 | 19.3343 | 35.4442 | 39.2114 |
75
+ | 1.7376 | 8.0 | 2400 | 1.7797 | 41.9569 | 18.9482 | 35.1953 | 38.7609 |
76
+ | 1.7096 | 9.0 | 2700 | 1.7780 | 42.6065 | 19.2152 | 35.4563 | 39.2736 |
77
+ | 1.6885 | 10.0 | 3000 | 1.7826 | 42.1595 | 18.8477 | 34.8679 | 38.9388 |
78
+ | 1.6581 | 11.0 | 3300 | 1.7809 | 42.291 | 19.0846 | 35.1938 | 38.894 |
79
+ | 1.6392 | 12.0 | 3600 | 1.7824 | 42.3588 | 19.4507 | 35.4588 | 39.2067 |
80
+ | 1.6258 | 13.0 | 3900 | 1.7806 | 42.0932 | 19.002 | 35.0112 | 38.8053 |
81
+ | 1.6042 | 14.0 | 4200 | 1.7828 | 42.0564 | 19.3141 | 35.2479 | 38.8301 |
82
+ | 1.5993 | 15.0 | 4500 | 1.7824 | 42.6056 | 19.5164 | 35.4112 | 39.2322 |
83
+ | 1.5869 | 16.0 | 4800 | 1.7839 | 42.1505 | 19.1529 | 35.0853 | 38.8788 |
84
+ | 1.5778 | 17.0 | 5100 | 1.7827 | 42.5416 | 19.5103 | 35.5507 | 39.293 |
85
+ | 1.5716 | 18.0 | 5400 | 1.7865 | 42.3028 | 19.3783 | 35.3466 | 39.0594 |
86
+ | 1.5615 | 19.0 | 5700 | 1.7857 | 42.4001 | 19.5111 | 35.4686 | 39.1614 |
87
+ | 1.5606 | 20.0 | 6000 | 1.7863 | 42.3215 | 19.4644 | 35.3715 | 39.1274 |
88
+
89
+
90
+ ### Framework versions
91
+
92
+ - Transformers 4.19.2
93
+ - Pytorch 1.11.0+cu113
94
+ - Datasets 2.2.2
95
+ - Tokenizers 0.12.1