Hugging Face's logo

damand2061
/
innermore-x-indobert-base-uncased

Token Classification
Transformers
TensorFlow
bert
generated_from_keras_callback
Inference Endpoints
Model card Files Community
damand2061 commited on
Commit
917b883
•
1 Parent(s): b09a023

End of training

Browse files
Files changed (2) hide show
  1. README.md +23 -24
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,12 +15,12 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.0031
19
- - Validation Loss: 0.2408
20
- - Train Precision: 0.7359
21
- - Train Recall: 0.7424
22
- - Train F1: 0.7391
23
- - Train Accuracy: 0.9530
24
  - Epoch: 14
25
 
26
  ## Model description
@@ -45,28 +45,27 @@ The following hyperparameters were used during training:
45
 
46
  ### Training results
47
 
48
- | Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
49
- |:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
50
- | 0.7413 | 0.3807 | 0.1975 | 0.1397 | 0.1637 | 0.8856 | 0 |
51
- | 0.3455 | 0.2601 | 0.4828 | 0.4891 | 0.4859 | 0.9225 | 1 |
52
- | 0.1874 | 0.2015 | 0.6360 | 0.6332 | 0.6346 | 0.9423 | 2 |
53
- | 0.0954 | 0.2067 | 0.6857 | 0.6288 | 0.6560 | 0.9433 | 3 |
54
- | 0.0796 | 0.1834 | 0.6573 | 0.7118 | 0.6834 | 0.9506 | 4 |
55
- | 0.0496 | 0.1825 | 0.7222 | 0.7380 | 0.7300 | 0.9548 | 5 |
56
- | 0.0267 | 0.2132 | 0.6653 | 0.7205 | 0.6918 | 0.9493 | 6 |
57
- | 0.0264 | 0.2229 | 0.6833 | 0.7162 | 0.6994 | 0.9502 | 7 |
58
- | 0.0181 | 0.1976 | 0.7404 | 0.7598 | 0.75 | 0.9548 | 8 |
59
- | 0.0105 | 0.2145 | 0.7203 | 0.7424 | 0.7312 | 0.9534 | 9 |
60
- | 0.0073 | 0.2449 | 0.7093 | 0.7031 | 0.7061 | 0.9497 | 10 |
61
- | 0.0058 | 0.2400 | 0.7354 | 0.7162 | 0.7257 | 0.9530 | 11 |
62
- | 0.0050 | 0.2388 | 0.7319 | 0.7511 | 0.7414 | 0.9534 | 12 |
63
- | 0.0039 | 0.2407 | 0.7371 | 0.7467 | 0.7419 | 0.9534 | 13 |
64
- | 0.0031 | 0.2408 | 0.7359 | 0.7424 | 0.7391 | 0.9530 | 14 |
65
 
66
 
67
  ### Framework versions
68
 
69
  - Transformers 4.38.2
70
  - TensorFlow 2.15.0
71
- - Datasets 2.18.0
72
  - Tokenizers 0.15.2
 
15
 
16
  This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.0053
19
+ - Validation Loss: 0.1740
20
+ - Validation Precision: 0.7319
21
+ - Validation Recall: 0.7644
22
+ - Validation F1: 0.7478
23
+ - Validation Accuracy: 0.9582
24
  - Epoch: 14
25
 
26
  ## Model description
 
45
 
46
  ### Training results
47
 
48
+ | Train Loss | Validation Loss | Validation Precision | Validation Recall | Validation F1 | Validation Accuracy | Epoch |
49
+ |:----------:|:---------------:|:--------------------:|:-----------------:|:-------------:|:-------------------:|:-----:|
50
+ | 0.7318 | 0.4161 | 0.1453 | 0.1156 | 0.1287 | 0.8751 | 0 |
51
+ | 0.3556 | 0.2296 | 0.5610 | 0.5111 | 0.5349 | 0.9324 | 1 |
52
+ | 0.2050 | 0.1668 | 0.6972 | 0.6756 | 0.6862 | 0.9521 | 2 |
53
+ | 0.1289 | 0.1603 | 0.6807 | 0.72 | 0.6998 | 0.9531 | 3 |
54
+ | 0.0875 | 0.1874 | 0.7281 | 0.7022 | 0.7149 | 0.9521 | 4 |
55
+ | 0.0754 | 0.1931 | 0.6653 | 0.7156 | 0.6895 | 0.9479 | 5 |
56
+ | 0.0416 | 0.1637 | 0.6935 | 0.7644 | 0.7273 | 0.9554 | 6 |
57
+ | 0.0238 | 0.1413 | 0.7598 | 0.7733 | 0.7665 | 0.9638 | 7 |
58
+ | 0.0152 | 0.1494 | 0.7479 | 0.8044 | 0.7752 | 0.9634 | 8 |
59
+ | 0.0152 | 0.1946 | 0.7061 | 0.7156 | 0.7108 | 0.9531 | 9 |
60
+ | 0.0128 | 0.1815 | 0.7241 | 0.7467 | 0.7352 | 0.9554 | 10 |
61
+ | 0.0072 | 0.1766 | 0.7210 | 0.7467 | 0.7336 | 0.9568 | 11 |
62
+ | 0.0080 | 0.1860 | 0.6987 | 0.7422 | 0.7198 | 0.9531 | 12 |
63
+ | 0.0089 | 0.1826 | 0.7227 | 0.7644 | 0.7430 | 0.9563 | 13 |
64
+ | 0.0053 | 0.1740 | 0.7319 | 0.7644 | 0.7478 | 0.9582 | 14 |
65
 
66
 
67
  ### Framework versions
68
 
69
  - Transformers 4.38.2
70
  - TensorFlow 2.15.0
 
71
  - Tokenizers 0.15.2
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9eb722012b22407d31fa3270e90c47bec2de8b639613008bd55bb7a3333d89ca
3
  size 440208396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:648e7e9b75811bf3de2204d0139dd0ef22a8f9a276ee5fd646399b052bfd83c5
3
  size 440208396