eslamxm commited on
Commit
59d62b2
1 Parent(s): 054fe8a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +67 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - summarization
4
+ - fa
5
+ - mbart
6
+ - Abstractive Summarization
7
+ - generated_from_trainer
8
+ datasets:
9
+ - pn_summary
10
+ model-index:
11
+ - name: mbart-finetuned-fa
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # mbart-finetuned-fa
19
+
20
+ This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the pn_summary dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 3.2877
23
+ - Rouge-1: 44.07
24
+ - Rouge-2: 25.81
25
+ - Rouge-l: 38.96
26
+ - Gen Len: 41.7
27
+ - Bertscore: 78.95
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 0.0005
47
+ - train_batch_size: 4
48
+ - eval_batch_size: 4
49
+ - seed: 42
50
+ - gradient_accumulation_steps: 8
51
+ - total_train_batch_size: 32
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_steps: 250
55
+ - num_epochs: 5
56
+ - label_smoothing_factor: 0.1
57
+
58
+ ### Training results
59
+
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.20.0
65
+ - Pytorch 1.11.0+cu113
66
+ - Datasets 2.3.2
67
+ - Tokenizers 0.12.1