Hugging Face's logo

muhammadravi251001
/
fine-tuned-DatasetQAS-TYDI-QA-ID-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05

Question Answering
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
muhammadravi251001 commited on
Commit
e43f0fb
路
1 Parent(s): df3f72c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -23
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 [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.1951
20
- - Exact Match: 57.3192
21
- - F1: 71.6264
22
 
23
  ## Model description
24
 
@@ -51,26 +51,26 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|:-------:|
54
- | 6.2799 | 0.5 | 19 | 3.8156 | 9.1711 | 20.6259 |
55
- | 6.2799 | 1.0 | 38 | 2.7508 | 17.8131 | 30.1002 |
56
- | 3.8612 | 1.5 | 57 | 2.4120 | 22.3986 | 35.0535 |
57
- | 3.8612 | 2.0 | 76 | 2.2445 | 28.0423 | 39.9012 |
58
- | 3.8612 | 2.5 | 95 | 2.0980 | 30.8642 | 42.4491 |
59
- | 2.3571 | 3.0 | 114 | 1.9564 | 34.2152 | 46.9171 |
60
- | 2.3571 | 3.5 | 133 | 1.8323 | 38.9771 | 51.9091 |
61
- | 1.9544 | 4.0 | 152 | 1.6545 | 42.1517 | 55.5272 |
62
- | 1.9544 | 4.5 | 171 | 1.5614 | 45.3263 | 60.0259 |
63
- | 1.9544 | 5.0 | 190 | 1.4898 | 48.8536 | 63.3488 |
64
- | 1.5802 | 5.5 | 209 | 1.3821 | 52.0282 | 67.0726 |
65
- | 1.5802 | 6.0 | 228 | 1.3286 | 53.6155 | 68.3149 |
66
- | 1.5802 | 6.5 | 247 | 1.2813 | 55.3792 | 69.5619 |
67
- | 1.3498 | 7.0 | 266 | 1.2538 | 55.3792 | 69.7318 |
68
- | 1.3498 | 7.5 | 285 | 1.2344 | 56.0847 | 70.5363 |
69
- | 1.1896 | 8.0 | 304 | 1.2111 | 56.7901 | 71.1736 |
70
- | 1.1896 | 8.5 | 323 | 1.2004 | 57.1429 | 71.2681 |
71
- | 1.1896 | 9.0 | 342 | 1.2010 | 56.9665 | 71.4279 |
72
- | 1.1406 | 9.5 | 361 | 1.1961 | 57.1429 | 71.5634 |
73
- | 1.1406 | 10.0 | 380 | 1.1951 | 57.3192 | 71.6264 |
74
 
75
 
76
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.2740
20
+ - Exact Match: 56.0847
21
+ - F1: 70.6246
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|:-------:|
54
+ | 6.306 | 0.5 | 19 | 3.7982 | 6.5256 | 20.3655 |
55
+ | 6.306 | 1.0 | 38 | 2.8932 | 14.1093 | 26.0679 |
56
+ | 3.9254 | 1.5 | 57 | 2.4798 | 19.4004 | 32.1438 |
57
+ | 3.9254 | 2.0 | 76 | 2.2955 | 26.1023 | 37.6331 |
58
+ | 3.9254 | 2.5 | 95 | 2.1688 | 26.9841 | 39.2632 |
59
+ | 2.4328 | 3.0 | 114 | 2.0701 | 30.1587 | 41.3438 |
60
+ | 2.4328 | 3.5 | 133 | 1.9789 | 33.1570 | 45.0539 |
61
+ | 2.1127 | 4.0 | 152 | 1.8465 | 37.2134 | 48.9042 |
62
+ | 2.1127 | 4.5 | 171 | 1.7699 | 38.9771 | 50.9760 |
63
+ | 2.1127 | 5.0 | 190 | 1.6885 | 41.0935 | 54.1550 |
64
+ | 1.7875 | 5.5 | 209 | 1.5785 | 45.1499 | 58.6783 |
65
+ | 1.7875 | 6.0 | 228 | 1.4954 | 49.2063 | 62.7869 |
66
+ | 1.7875 | 6.5 | 247 | 1.4186 | 51.8519 | 65.7461 |
67
+ | 1.5267 | 7.0 | 266 | 1.3734 | 53.4392 | 67.6141 |
68
+ | 1.5267 | 7.5 | 285 | 1.3419 | 54.1446 | 68.2563 |
69
+ | 1.3317 | 8.0 | 304 | 1.3116 | 55.5556 | 69.1996 |
70
+ | 1.3317 | 8.5 | 323 | 1.2936 | 56.0847 | 69.9806 |
71
+ | 1.3317 | 9.0 | 342 | 1.2900 | 56.2610 | 70.1634 |
72
+ | 1.2556 | 9.5 | 361 | 1.2771 | 55.7319 | 70.1143 |
73
+ | 1.2556 | 10.0 | 380 | 1.2740 | 56.0847 | 70.6246 |
74
 
75
 
76
  ### Framework versions