SungWei commited on
Commit
bc864e0
1 Parent(s): 5a12cea

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: t5-small
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - billsum
8
+ metrics:
9
+ - rouge
10
+ model-index:
11
+ - name: my_awesome_billsum_model
12
+ results:
13
+ - task:
14
+ name: Sequence-to-sequence Language Modeling
15
+ type: text2text-generation
16
+ dataset:
17
+ name: billsum
18
+ type: billsum
19
+ config: default
20
+ split: ca_test
21
+ args: default
22
+ metrics:
23
+ - name: Rouge1
24
+ type: rouge
25
+ value: 0.1823
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # my_awesome_billsum_model
32
+
33
+ This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the billsum dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 2.4704
36
+ - Rouge1: 0.1823
37
+ - Rouge2: 0.0873
38
+ - Rougel: 0.1534
39
+ - Rougelsum: 0.1535
40
+ - Gen Len: 19.0
41
+
42
+ ## Model description
43
+
44
+ More information needed
45
+
46
+ ## Intended uses & limitations
47
+
48
+ More information needed
49
+
50
+ ## Training and evaluation data
51
+
52
+ More information needed
53
+
54
+ ## Training procedure
55
+
56
+ ### Training hyperparameters
57
+
58
+ The following hyperparameters were used during training:
59
+ - learning_rate: 2e-05
60
+ - train_batch_size: 8
61
+ - eval_batch_size: 16
62
+ - seed: 42
63
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
+ - lr_scheduler_type: linear
65
+ - num_epochs: 4
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
70
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
71
+ | No log | 1.0 | 124 | 2.6597 | 0.1355 | 0.05 | 0.114 | 0.1142 | 19.0 |
72
+ | No log | 2.0 | 248 | 2.5295 | 0.1577 | 0.0686 | 0.1332 | 0.1334 | 19.0 |
73
+ | No log | 3.0 | 372 | 2.4850 | 0.1726 | 0.0783 | 0.1447 | 0.1449 | 19.0 |
74
+ | No log | 4.0 | 496 | 2.4704 | 0.1823 | 0.0873 | 0.1534 | 0.1535 | 19.0 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.31.0
80
+ - Pytorch 2.0.1
81
+ - Datasets 2.14.1
82
+ - Tokenizers 0.13.3