Hugging Face's logo

muhammadravi251001
/
fine-tuned-DatasetQAS-TYDI-QA-ID-with-indobert-large-p2-with-ITTL-with-freeze-LR-1e-05

Question Answering
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Model card Files Metrics Community
muhammadravi251001 commited on
Commit
8188b23
路
1 Parent(s): 6f31356

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -29
README.md CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [indobenchmark/indobert-large-p2](https://huggingface.co/indobenchmark/indobert-large-p2) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.1892
20
- - Exact Match: 58.9789
21
- - F1: 73.0396
22
 
23
  ## Model description
24
 
@@ -38,10 +38,10 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
- - train_batch_size: 4
42
- - eval_batch_size: 4
43
  - seed: 42
44
- - gradient_accumulation_steps: 32
45
  - total_train_batch_size: 128
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
@@ -51,31 +51,30 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|:-------:|
54
- | 6.1098 | 0.5 | 19 | 3.5303 | 13.9085 | 24.6309 |
55
- | 6.1098 | 0.99 | 38 | 2.7480 | 19.8944 | 30.2361 |
56
- | 3.4912 | 1.49 | 57 | 2.3191 | 23.5915 | 35.2255 |
57
- | 3.4912 | 1.99 | 76 | 1.9976 | 32.5704 | 44.6210 |
58
- | 3.4912 | 2.49 | 95 | 1.6643 | 39.9648 | 52.7259 |
59
- | 2.0016 | 2.98 | 114 | 1.4262 | 45.5986 | 60.0405 |
60
- | 2.0016 | 3.48 | 133 | 1.3436 | 49.4718 | 64.5087 |
61
- | 1.3527 | 3.98 | 152 | 1.2679 | 53.1690 | 68.1412 |
62
- | 1.3527 | 4.47 | 171 | 1.2358 | 53.3451 | 68.5112 |
63
- | 1.3527 | 4.97 | 190 | 1.2014 | 54.4014 | 69.0833 |
64
- | 1.0423 | 5.47 | 209 | 1.1913 | 56.6901 | 70.8291 |
65
- | 1.0423 | 5.97 | 228 | 1.1920 | 57.0423 | 71.9055 |
66
- | 1.0423 | 6.46 | 247 | 1.1878 | 57.7465 | 72.6003 |
67
- | 0.8939 | 6.96 | 266 | 1.1776 | 57.9225 | 72.4830 |
68
- | 0.8939 | 7.46 | 285 | 1.1858 | 58.2746 | 72.6829 |
69
- | 0.8044 | 7.95 | 304 | 1.1846 | 58.2746 | 72.7730 |
70
- | 0.8044 | 8.45 | 323 | 1.1872 | 58.9789 | 73.3965 |
71
- | 0.8044 | 8.95 | 342 | 1.1921 | 58.8028 | 73.3149 |
72
- | 0.7391 | 9.45 | 361 | 1.1910 | 58.9789 | 73.1201 |
73
- | 0.7391 | 9.94 | 380 | 1.1892 | 58.9789 | 73.0396 |
74
 
75
 
76
  ### Framework versions
77
 
78
- - Transformers 4.28.1
79
- - Pytorch 2.0.1+cu117
80
  - Datasets 2.2.0
81
- - Tokenizers 0.13.3
 
16
 
17
  This model is a fine-tuned version of [indobenchmark/indobert-large-p2](https://huggingface.co/indobenchmark/indobert-large-p2) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.2003
20
+ - Exact Match: 60.2113
21
+ - F1: 73.9948
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 2
43
  - seed: 42
44
+ - gradient_accumulation_steps: 64
45
  - total_train_batch_size: 128
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|:-------:|
54
+ | 6.2316 | 0.5 | 19 | 3.5321 | 11.9718 | 21.8197 |
55
+ | 6.2316 | 0.99 | 38 | 2.6566 | 19.1901 | 31.9985 |
56
+ | 3.5132 | 1.5 | 57 | 2.1442 | 27.2887 | 40.7031 |
57
+ | 3.5132 | 1.99 | 76 | 1.6755 | 41.5493 | 53.9850 |
58
+ | 3.5132 | 2.5 | 95 | 1.4228 | 48.2394 | 61.2829 |
59
+ | 1.845 | 2.99 | 114 | 1.2882 | 52.8169 | 66.2197 |
60
+ | 1.845 | 3.5 | 133 | 1.2352 | 54.7535 | 68.3725 |
61
+ | 1.2542 | 3.99 | 152 | 1.2033 | 56.6901 | 70.5019 |
62
+ | 1.2542 | 4.5 | 171 | 1.2117 | 57.9225 | 72.0740 |
63
+ | 1.2542 | 4.99 | 190 | 1.1748 | 58.4507 | 71.9264 |
64
+ | 0.9877 | 5.5 | 209 | 1.1763 | 58.8028 | 72.2772 |
65
+ | 0.9877 | 5.99 | 228 | 1.1827 | 59.5070 | 73.5652 |
66
+ | 0.9877 | 6.5 | 247 | 1.1789 | 59.8592 | 73.2748 |
67
+ | 0.8293 | 6.99 | 266 | 1.1835 | 60.0352 | 73.4695 |
68
+ | 0.8293 | 7.5 | 285 | 1.1669 | 59.8592 | 73.7145 |
69
+ | 0.7663 | 7.99 | 304 | 1.1912 | 60.3873 | 74.3001 |
70
+ | 0.7663 | 8.5 | 323 | 1.1828 | 60.2113 | 74.1533 |
71
+ | 0.7663 | 8.99 | 342 | 1.2046 | 60.3873 | 74.0424 |
72
+ | 0.7068 | 9.5 | 361 | 1.2003 | 60.2113 | 73.9948 |
 
73
 
74
 
75
  ### Framework versions
76
 
77
+ - Transformers 4.26.1
78
+ - Pytorch 1.13.1+cu117
79
  - Datasets 2.2.0
80
+ - Tokenizers 0.13.2