eslamxm commited on
Commit
e4146c3
1 Parent(s): 5fc8800

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -0
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - summarization
5
+ - mt5
6
+ - es
7
+ - spanish
8
+ - abstractive summarization
9
+ - generated_from_trainer
10
+ datasets:
11
+ - wiki_lingua
12
+ model-index:
13
+ - name: mt5-base-finetuned-Spanish
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # mt5-base-finetuned-Spanish
21
+
22
+ This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the wiki_lingua dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 3.1727
25
+ - Rouge-1: 28.11
26
+ - Rouge-2: 12.09
27
+ - Rouge-l: 24.62
28
+ - Gen Len: 18.73
29
+ - Bertscore: 72.25
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 0.0005
49
+ - train_batch_size: 4
50
+ - eval_batch_size: 4
51
+ - seed: 42
52
+ - gradient_accumulation_steps: 8
53
+ - total_train_batch_size: 32
54
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
+ - lr_scheduler_type: linear
56
+ - lr_scheduler_warmup_steps: 250
57
+ - num_epochs: 5
58
+ - label_smoothing_factor: 0.1
59
+
60
+ ### Training results
61
+
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.19.4
67
+ - Pytorch 1.11.0+cu113
68
+ - Datasets 2.3.0
69
+ - Tokenizers 0.12.1