Hugging Face's logo

Labira
/
LabiraPJOK_1_100

Question Answering
Transformers
TensorFlow
bert
generated_from_keras_callback
Model card Files Community
Labira commited on
Commit
a146e4e
路
1 Parent(s): fe314a9

Training in progress epoch 8

Browse files
Files changed (2) hide show
  1. README.md +9 -3
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -16,9 +16,9 @@ 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 an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Train Loss: 0.4330
20
- - Validation Loss: 4.9959
21
- - Epoch: 2
22
 
23
  ## Model description
24
 
@@ -47,6 +47,12 @@ The following hyperparameters were used during training:
47
  | 0.5573 | 6.1112 | 0 |
48
  | 0.2525 | 4.7174 | 1 |
49
  | 0.4330 | 4.9959 | 2 |
 
 
 
 
 
 
50
 
51
 
52
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Train Loss: 0.0296
20
+ - Validation Loss: 6.5959
21
+ - Epoch: 8
22
 
23
  ## Model description
24
 
 
47
  | 0.5573 | 6.1112 | 0 |
48
  | 0.2525 | 4.7174 | 1 |
49
  | 0.4330 | 4.9959 | 2 |
50
+ | 0.2496 | 5.5703 | 3 |
51
+ | 0.1868 | 5.9061 | 4 |
52
+ | 0.1491 | 6.0854 | 5 |
53
+ | 0.1951 | 6.3417 | 6 |
54
+ | 0.0492 | 6.4913 | 7 |
55
+ | 0.0296 | 6.5959 | 8 |
56
 
57
 
58
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe7dba4e1c4480d9b4e8033a8aeef1ca6aa5f912294f01d27aa62dea5a3eb1b2
3
  size 440145872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f40a398058c76a1eb55b4ec43925dd4cab46e7fd5d2bac370526278b8365569
3
  size 440145872