Hugging Face's logo

damand2061
/
innermore-x-indobertweet-base-uncased

Token Classification
Transformers
TensorFlow
Indonesian
bert
generated_from_keras_callback
Inference Endpoints
Model card Files Community
damand2061 commited on
Commit
d726631
·
1 Parent(s): 05c6c8f

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/indobertweet-base-uncased](https://huggingface.co/indolem/indobertweet-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.0022
19
- - Validation Loss: 0.1782
20
- - Train Precision: 0.8152
21
- - Train Recall: 0.7350
22
- - Train F1: 0.7730
23
- - Train Accuracy: 0.9629
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
- | 0.5919 | 0.3227 | 0.6263 | 0.2650 | 0.3724 | 0.9078 | 0 |
51
- | 0.2379 | 0.1878 | 0.6948 | 0.6325 | 0.6622 | 0.9434 | 1 |
52
- | 0.1314 | 0.1674 | 0.6711 | 0.6453 | 0.6580 | 0.9477 | 2 |
53
- | 0.0852 | 0.1958 | 0.6562 | 0.7179 | 0.6857 | 0.9425 | 3 |
54
- | 0.0506 | 0.1677 | 0.7907 | 0.7265 | 0.7572 | 0.9539 | 4 |
55
- | 0.0239 | 0.1493 | 0.7689 | 0.7393 | 0.7538 | 0.9615 | 5 |
56
- | 0.0194 | 0.1679 | 0.8102 | 0.7479 | 0.7778 | 0.9610 | 6 |
57
- | 0.0122 | 0.1739 | 0.7328 | 0.7265 | 0.7296 | 0.9563 | 7 |
58
- | 0.0084 | 0.2116 | 0.8118 | 0.6453 | 0.7190 | 0.9539 | 8 |
59
- | 0.0059 | 0.1724 | 0.8 | 0.7179 | 0.7568 | 0.9591 | 9 |
60
- | 0.0037 | 0.1744 | 0.7972 | 0.7222 | 0.7578 | 0.9601 | 10 |
61
- | 0.0029 | 0.1771 | 0.7981 | 0.7265 | 0.7606 | 0.9601 | 11 |
62
- | 0.0020 | 0.1769 | 0.8047 | 0.7393 | 0.7706 | 0.9620 | 12 |
63
- | 0.0020 | 0.1773 | 0.8152 | 0.7350 | 0.7730 | 0.9629 | 13 |
64
- | 0.0022 | 0.1782 | 0.8152 | 0.7350 | 0.7730 | 0.9629 | 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/indobertweet-base-uncased](https://huggingface.co/indolem/indobertweet-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.0062
19
+ - Validation Loss: 0.1791
20
+ - Validation Precision: 0.8073
21
+ - Validation Recall: 0.7652
22
+ - Validation F1: 0.7857
23
+ - Validation Accuracy: 0.9622
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
+ | 0.8107 | 0.5161 | 0.1270 | 0.1348 | 0.1308 | 0.8446 | 0 |
51
+ | 0.4721 | 0.3254 | 0.3232 | 0.2304 | 0.2690 | 0.9003 | 1 |
52
+ | 0.3198 | 0.2431 | 0.4776 | 0.5087 | 0.4926 | 0.9211 | 2 |
53
+ | 0.1784 | 0.1581 | 0.6741 | 0.6565 | 0.6652 | 0.9497 | 3 |
54
+ | 0.1177 | 0.1304 | 0.7890 | 0.7478 | 0.7679 | 0.9627 | 4 |
55
+ | 0.0666 | 0.1428 | 0.7545 | 0.7348 | 0.7445 | 0.9598 | 5 |
56
+ | 0.0499 | 0.1526 | 0.7456 | 0.7391 | 0.7424 | 0.9584 | 6 |
57
+ | 0.0339 | 0.1677 | 0.7945 | 0.7565 | 0.7751 | 0.9627 | 7 |
58
+ | 0.0261 | 0.1598 | 0.6996 | 0.7087 | 0.7041 | 0.9540 | 8 |
59
+ | 0.0178 | 0.1792 | 0.7668 | 0.7435 | 0.7550 | 0.9598 | 9 |
60
+ | 0.0127 | 0.1943 | 0.8186 | 0.7261 | 0.7696 | 0.9593 | 10 |
61
+ | 0.0102 | 0.1825 | 0.7890 | 0.7478 | 0.7679 | 0.9598 | 11 |
62
+ | 0.0083 | 0.1765 | 0.8102 | 0.7609 | 0.7848 | 0.9622 | 12 |
63
+ | 0.0062 | 0.1778 | 0.8018 | 0.7565 | 0.7785 | 0.9618 | 13 |
64
+ | 0.0062 | 0.1791 | 0.8073 | 0.7652 | 0.7857 | 0.9622 | 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 sha256:9753cd004d14680f58b1c06b5c66ebf257e324ef1a64ff6b8dfd433c03303cfa
3
  size 440208396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f8b990b85608a24a58335109f700e15f851d31f8854b64532f4e45e549f4ec4
3
  size 440208396