Hugging Face's logo

Labira
/
LabiraPJOK_1_1000

Question Answering
Transformers
TensorFlow
bert
generated_from_keras_callback
Model card Files Community
Labira commited on
Commit
c349c2c
路
1 Parent(s): 9ec3f8c

Training in progress epoch 508

Browse files
Files changed (2) hide show
  1. README.md +10 -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: 0.0070
20
- - Validation Loss: 10.9719
21
- - Epoch: 501
22
 
23
  ## Model description
24
 
@@ -546,6 +546,13 @@ The following hyperparameters were used during training:
546
  | 0.0020 | 10.4749 | 499 |
547
  | 0.0012 | 10.5782 | 500 |
548
  | 0.0070 | 10.9719 | 501 |
 
 
 
 
 
 
 
549
 
550
 
551
  ### 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: 0.0002
20
+ - Validation Loss: 11.1940
21
+ - Epoch: 508
22
 
23
  ## Model description
24
 
 
546
  | 0.0020 | 10.4749 | 499 |
547
  | 0.0012 | 10.5782 | 500 |
548
  | 0.0070 | 10.9719 | 501 |
549
+ | 0.0006 | 11.2452 | 502 |
550
+ | 0.0001 | 11.3432 | 503 |
551
+ | 0.0001 | 11.3358 | 504 |
552
+ | 0.0010 | 11.4342 | 505 |
553
+ | 0.0001 | 11.5136 | 506 |
554
+ | 0.0001 | 11.3794 | 507 |
555
+ | 0.0002 | 11.1940 | 508 |
556
 
557
 
558
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4adc2f7657e116d62ecc9d3eea53543912f5b9b91c1533255ed5e8b1063cfd14
3
  size 440145872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8978d6a1e118ea71ae7d5969fe4e7d7416b48f3040d41ce6fd8740af265e8fa
3
  size 440145872