Hugging Face's logo

baskorowicaksono
/
transformers-qa-kaggle-tpu

Question Answering
Transformers
TensorFlow
distilbert
generated_from_keras_callback
Inference Endpoints
Model card Files Community
baskorowicaksono commited on
Commit
3ef1cd8
•
1 Parent(s): 20f4adb

Upload TFDistilBertForQuestionAnswering

Browse files
Files changed (2) hide show
  1. README.md +21 -21
  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 [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.2138
19
- - Train End Logits Accuracy: 0.9272
20
- - Train Start Logits Accuracy: 0.9265
21
- - Validation Loss: 4.0782
22
- - Validation End Logits Accuracy: 0.4815
23
- - Validation Start Logits Accuracy: 0.4488
24
  - Epoch: 14
25
 
26
  ## Model description
@@ -47,21 +47,21 @@ The following hyperparameters were used during training:
47
 
48
  | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
49
  |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
50
- | 2.2397 | 0.4602 | 0.4288 | 2.0601 | 0.4944 | 0.4670 | 0 |
51
- | 1.7080 | 0.5695 | 0.5404 | 2.0597 | 0.5098 | 0.4782 | 1 |
52
- | 1.4423 | 0.6244 | 0.5975 | 2.0398 | 0.5124 | 0.4779 | 2 |
53
- | 1.2221 | 0.6718 | 0.6455 | 2.1899 | 0.5121 | 0.4832 | 3 |
54
- | 1.0321 | 0.7138 | 0.6920 | 2.2860 | 0.5067 | 0.4742 | 4 |
55
- | 0.8740 | 0.7502 | 0.7307 | 2.4042 | 0.4981 | 0.4677 | 5 |
56
- | 0.7420 | 0.7809 | 0.7666 | 2.6543 | 0.4954 | 0.4595 | 6 |
57
- | 0.6254 | 0.8107 | 0.7988 | 2.7405 | 0.4938 | 0.4607 | 7 |
58
- | 0.5325 | 0.8337 | 0.8255 | 3.0218 | 0.4911 | 0.4613 | 8 |
59
- | 0.4537 | 0.8550 | 0.8491 | 3.1804 | 0.4917 | 0.4550 | 9 |
60
- | 0.3860 | 0.8751 | 0.8707 | 3.4298 | 0.4880 | 0.4524 | 10 |
61
- | 0.3284 | 0.8914 | 0.8890 | 3.5952 | 0.4826 | 0.4480 | 11 |
62
- | 0.2844 | 0.9053 | 0.9033 | 3.6105 | 0.4856 | 0.4510 | 12 |
63
- | 0.2462 | 0.9176 | 0.9151 | 3.8751 | 0.4785 | 0.4504 | 13 |
64
- | 0.2138 | 0.9272 | 0.9265 | 4.0782 | 0.4815 | 0.4488 | 14 |
65
 
66
 
67
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.2278
19
+ - Train End Logits Accuracy: 0.9244
20
+ - Train Start Logits Accuracy: 0.9207
21
+ - Validation Loss: 3.8999
22
+ - Validation End Logits Accuracy: 0.4812
23
+ - Validation Start Logits Accuracy: 0.4542
24
  - Epoch: 14
25
 
26
  ## Model description
 
47
 
48
  | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
49
  |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
50
+ | 2.2837 | 0.4519 | 0.4182 | 2.1117 | 0.4890 | 0.4658 | 0 |
51
+ | 1.7361 | 0.5642 | 0.5326 | 2.0268 | 0.5035 | 0.4788 | 1 |
52
+ | 1.4664 | 0.6186 | 0.5893 | 2.0023 | 0.5093 | 0.4833 | 2 |
53
+ | 1.2479 | 0.6661 | 0.6379 | 2.1252 | 0.5057 | 0.4744 | 3 |
54
+ | 1.0596 | 0.7076 | 0.6832 | 2.2703 | 0.4975 | 0.4690 | 4 |
55
+ | 0.8999 | 0.7434 | 0.7214 | 2.3834 | 0.4968 | 0.4714 | 5 |
56
+ | 0.7661 | 0.7760 | 0.7557 | 2.5503 | 0.4906 | 0.4654 | 6 |
57
+ | 0.6520 | 0.8042 | 0.7892 | 2.7740 | 0.4922 | 0.4540 | 7 |
58
+ | 0.5549 | 0.8313 | 0.8156 | 3.0625 | 0.4884 | 0.4607 | 8 |
59
+ | 0.4739 | 0.8512 | 0.8405 | 3.1365 | 0.4862 | 0.4535 | 9 |
60
+ | 0.4072 | 0.8691 | 0.8620 | 3.2969 | 0.4830 | 0.4509 | 10 |
61
+ | 0.3515 | 0.8863 | 0.8786 | 3.4301 | 0.4852 | 0.4530 | 11 |
62
+ | 0.3025 | 0.9010 | 0.8954 | 3.5350 | 0.4814 | 0.4548 | 12 |
63
+ | 0.2646 | 0.9127 | 0.9083 | 3.7923 | 0.4832 | 0.4539 | 13 |
64
+ | 0.2278 | 0.9244 | 0.9207 | 3.8999 | 0.4812 | 0.4542 | 14 |
65
 
66
 
67
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d827e5849b70dfbafd600c27dfa28e32ba28b189f450df6999657812ae07fed
3
  size 539068392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02c0e61cb45581251255d8eb2a8f34a1ffa03940ef45e8532f1d2e385c172dac
3
  size 539068392