mse30 commited on
Commit
2dcf679
1 Parent(s): aa90f87

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +80 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - scientific_papers
7
+ metrics:
8
+ - rouge
9
+ model-index:
10
+ - name: bart-base-finetuned-pubmed
11
+ results:
12
+ - task:
13
+ name: Sequence-to-sequence Language Modeling
14
+ type: text2text-generation
15
+ dataset:
16
+ name: scientific_papers
17
+ type: scientific_papers
18
+ args: pubmed
19
+ metrics:
20
+ - name: Rouge1
21
+ type: rouge
22
+ value: 9.1984
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
+ # bart-base-finetuned-pubmed
29
+
30
+ This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the scientific_papers dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 1.9804
33
+ - Rouge1: 9.1984
34
+ - Rouge2: 4.3091
35
+ - Rougel: 7.9739
36
+ - Rougelsum: 8.6759
37
+ - Gen Len: 20.0
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: 2e-05
57
+ - train_batch_size: 4
58
+ - eval_batch_size: 4
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - num_epochs: 4
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
68
+ |:-------------:|:-----:|:------:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
69
+ | 2.2869 | 1.0 | 29981 | 2.1241 | 9.0852 | 4.1152 | 7.842 | 8.5395 | 20.0 |
70
+ | 2.1469 | 2.0 | 59962 | 2.0225 | 9.1609 | 4.2437 | 7.9311 | 8.6273 | 20.0 |
71
+ | 2.113 | 3.0 | 89943 | 1.9959 | 9.3086 | 4.3305 | 8.0363 | 8.7713 | 20.0 |
72
+ | 2.0632 | 4.0 | 119924 | 1.9804 | 9.1984 | 4.3091 | 7.9739 | 8.6759 | 20.0 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.11.3
78
+ - Pytorch 1.9.1+cu102
79
+ - Datasets 1.12.1
80
+ - Tokenizers 0.10.3