Hugging Face's logo

muhammadravi251001
/
fine-tuned-DatasetQAS-IDK-MRC-with-indobert-large-p2-with-ITTL-with-freeze-LR-1e-05

Question Answering
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
muhammadravi251001 commited on
Commit
a29974a
路
1 Parent(s): edd7754

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -19
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: 1.2350
20
- - Exact Match: 51.1780
21
- - F1: 58.2552
22
 
23
  ## Model description
24
 
@@ -51,22 +51,25 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|:-------:|
54
- | 6.3549 | 0.49 | 36 | 2.5315 | 35.6021 | 38.6809 |
55
- | 3.4833 | 0.98 | 72 | 1.9930 | 29.4503 | 35.6743 |
56
- | 2.159 | 1.48 | 108 | 1.7112 | 34.0314 | 42.0735 |
57
- | 2.159 | 1.97 | 144 | 1.5184 | 41.4921 | 49.0573 |
58
- | 1.7177 | 2.46 | 180 | 1.3694 | 45.4188 | 52.5772 |
59
- | 1.3513 | 2.95 | 216 | 1.3089 | 46.5969 | 53.4113 |
60
- | 1.1821 | 3.45 | 252 | 1.2472 | 50.0 | 57.1100 |
61
- | 1.1821 | 3.94 | 288 | 1.2501 | 50.2618 | 57.5052 |
62
- | 1.1072 | 4.44 | 324 | 1.2351 | 51.7016 | 58.5137 |
63
- | 0.9642 | 4.93 | 360 | 1.1886 | 51.5707 | 58.3268 |
64
- | 0.9642 | 5.42 | 396 | 1.2090 | 52.6178 | 59.7784 |
65
- | 0.9117 | 5.91 | 432 | 1.2313 | 52.3560 | 59.4634 |
66
- | 0.8479 | 6.41 | 468 | 1.2177 | 52.6178 | 59.8866 |
67
- | 0.8001 | 6.9 | 504 | 1.2314 | 51.3089 | 58.6387 |
68
- | 0.8001 | 7.4 | 540 | 1.2804 | 51.9634 | 59.4951 |
69
- | 0.7724 | 7.89 | 576 | 1.2350 | 51.1780 | 58.2552 |
 
 
 
70
 
71
 
72
  ### Framework versions
 
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: 1.2708
20
+ - Exact Match: 52.7487
21
+ - F1: 60.8071
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|:-------:|
54
+ | 6.4745 | 0.49 | 36 | 2.5724 | 35.6021 | 37.8405 |
55
+ | 3.5197 | 0.98 | 72 | 1.9912 | 28.0105 | 35.4278 |
56
+ | 2.1756 | 1.48 | 108 | 1.6669 | 35.7330 | 43.0612 |
57
+ | 2.1756 | 1.97 | 144 | 1.5047 | 39.3979 | 46.1664 |
58
+ | 1.6725 | 2.46 | 180 | 1.3222 | 45.9424 | 52.9355 |
59
+ | 1.336 | 2.95 | 216 | 1.3205 | 44.1099 | 51.6851 |
60
+ | 1.176 | 3.45 | 252 | 1.2526 | 47.5131 | 55.3298 |
61
+ | 1.176 | 3.94 | 288 | 1.2778 | 47.3822 | 54.7110 |
62
+ | 1.1089 | 4.44 | 324 | 1.2291 | 49.8691 | 57.2303 |
63
+ | 0.967 | 4.93 | 360 | 1.1944 | 52.4869 | 60.2202 |
64
+ | 0.967 | 5.42 | 396 | 1.2122 | 53.7958 | 61.3033 |
65
+ | 0.9202 | 5.91 | 432 | 1.2348 | 54.0576 | 61.6263 |
66
+ | 0.8719 | 6.41 | 468 | 1.2206 | 55.2356 | 62.9267 |
67
+ | 0.8205 | 6.9 | 504 | 1.2472 | 53.9267 | 61.6359 |
68
+ | 0.8205 | 7.4 | 540 | 1.2764 | 52.3560 | 60.2681 |
69
+ | 0.7907 | 7.89 | 576 | 1.2382 | 55.3665 | 63.0145 |
70
+ | 0.7533 | 8.38 | 612 | 1.2812 | 52.4869 | 60.4214 |
71
+ | 0.7533 | 8.87 | 648 | 1.2474 | 53.1414 | 60.6338 |
72
+ | 0.7345 | 9.37 | 684 | 1.2708 | 52.7487 | 60.8071 |
73
 
74
 
75
  ### Framework versions