Hugging Face's logo

apwic
/
summarization-base-3

Transformers
Safetensors
Indonesian
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
apwic commited on
Commit
2341077
·
verified ·
1 Parent(s): 6f3689b

Model save

Browse files
Files changed (1) hide show
  1. README.md +16 -18
README.md CHANGED
@@ -1,6 +1,4 @@
1
  ---
2
- language:
3
- - id
4
  license: apache-2.0
5
  base_model: LazarusNLP/IndoNanoT5-base
6
  tags:
@@ -19,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.5374
23
- - Rouge1: 0.4096
24
  - Rouge2: 0.0
25
- - Rougel: 0.4081
26
- - Rougelsum: 0.4102
27
  - Gen Len: 1.0
28
 
29
  ## Model description
@@ -43,9 +41,9 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 5e-05
47
- - train_batch_size: 4
48
- - eval_batch_size: 8
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
@@ -53,18 +51,18 @@ The following hyperparameters were used during training:
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
57
- |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
58
- | 0.6296 | 1.0 | 3568 | 0.5221 | 0.3678 | 0.0 | 0.3666 | 0.3673 | 1.0 |
59
- | 0.4308 | 2.0 | 7136 | 0.4927 | 0.4034 | 0.0 | 0.3999 | 0.4032 | 1.0 |
60
- | 0.3347 | 3.0 | 10704 | 0.5028 | 0.4081 | 0.0 | 0.407 | 0.4083 | 1.0 |
61
- | 0.2655 | 4.0 | 14272 | 0.5221 | 0.4264 | 0.0 | 0.4239 | 0.4268 | 1.0 |
62
- | 0.2179 | 5.0 | 17840 | 0.5374 | 0.4096 | 0.0 | 0.4081 | 0.4102 | 1.0 |
63
 
64
 
65
  ### Framework versions
66
 
67
  - Transformers 4.40.2
68
- - Pytorch 2.3.0+cu121
69
- - Datasets 2.19.1
70
  - Tokenizers 0.19.1
 
1
  ---
 
 
2
  license: apache-2.0
3
  base_model: LazarusNLP/IndoNanoT5-base
4
  tags:
 
17
 
18
  This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.7586
21
+ - Rouge1: 0.682
22
  - Rouge2: 0.0
23
+ - Rougel: 0.681
24
+ - Rougelsum: 0.6795
25
  - Gen Len: 1.0
26
 
27
  ## Model description
 
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
+ - learning_rate: 0.001
45
+ - train_batch_size: 16
46
+ - eval_batch_size: 32
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
56
+ | 1.2006 | 1.0 | 892 | 0.8184 | 0.6667 | 0.0 | 0.6667 | 0.6663 | 1.0 |
57
+ | 0.6791 | 2.0 | 1784 | 0.6924 | 0.6654 | 0.0 | 0.6613 | 0.6642 | 1.0 |
58
+ | 0.4848 | 3.0 | 2676 | 0.6634 | 0.7098 | 0.0 | 0.7089 | 0.7131 | 1.0 |
59
+ | 0.3381 | 4.0 | 3568 | 0.6800 | 0.696 | 0.0 | 0.6977 | 0.6988 | 1.0 |
60
+ | 0.2027 | 5.0 | 4460 | 0.7586 | 0.682 | 0.0 | 0.681 | 0.6795 | 1.0 |
61
 
62
 
63
  ### Framework versions
64
 
65
  - Transformers 4.40.2
66
+ - Pytorch 2.3.1+cu121
67
+ - Datasets 2.20.0
68
  - Tokenizers 0.19.1