Hugging Face's logo

apwic
/
indosum-base-1

Transformers
Safetensors
Indonesian
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
apwic commited on
Commit
1d75a08
•
1 Parent(s): 2600d01

Model save

Browse files
Files changed (1) hide show
  1. README.md +17 -17
README.md CHANGED
@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.7285
21
- - Rouge1: 71.2709
22
- - Rouge2: 63.9704
23
- - Rougel: 68.0718
24
- - Rougelsum: 70.4345
25
- - Gen Len: 98.3792
26
 
27
  ## Model description
28
 
@@ -42,8 +42,8 @@ More information needed
42
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 0.001
45
- - train_batch_size: 4
46
- - eval_batch_size: 8
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
@@ -51,18 +51,18 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
- |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
56
- | 1.5428 | 1.0 | 3566 | 0.9651 | 65.543 | 57.2356 | 62.3412 | 64.6125 | 103.0561 |
57
- | 0.8422 | 2.0 | 7132 | 0.7883 | 68.7622 | 61.187 | 65.4631 | 67.9119 | 95.1615 |
58
- | 0.6457 | 3.0 | 10698 | 0.7254 | 69.2705 | 61.8962 | 66.1101 | 68.4083 | 102.7557 |
59
- | 0.4948 | 4.0 | 14264 | 0.6871 | 71.0668 | 63.8176 | 67.9618 | 70.2487 | 100.2109 |
60
- | 0.348 | 5.0 | 17830 | 0.7285 | 71.2709 | 63.9704 | 68.0718 | 70.4345 | 98.3792 |
61
 
62
 
63
  ### Framework versions
64
 
65
  - Transformers 4.40.2
66
- - Pytorch 2.3.0+cu121
67
- - Datasets 2.19.1
68
  - Tokenizers 0.19.1
 
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: 0.7478
21
+ - Rouge1: 72.0587
22
+ - Rouge2: 64.7973
23
+ - Rougel: 68.9279
24
+ - Rougelsum: 71.3028
25
+ - Gen Len: 99.3765
26
 
27
  ## Model description
28
 
 
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
+ | 1.1904 | 1.0 | 892 | 0.8053 | 65.8257 | 57.6167 | 62.6222 | 65.0027 | 95.8598 |
57
+ | 0.6851 | 2.0 | 1784 | 0.6779 | 67.8889 | 60.0878 | 64.5868 | 66.9914 | 96.2911 |
58
+ | 0.4856 | 3.0 | 2676 | 0.6460 | 70.9241 | 63.6363 | 67.8555 | 70.153 | 96.9212 |
59
+ | 0.3358 | 4.0 | 3568 | 0.6565 | 69.9002 | 62.4 | 66.5928 | 69.0347 | 101.8745 |
60
+ | 0.1973 | 5.0 | 4460 | 0.7478 | 72.0587 | 64.7973 | 68.9279 | 71.3028 | 99.3765 |
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