Hugging Face's logo

Docty
/
question_and_answer

Question Answering
Transformers
TensorFlow
distilbert
generated_from_keras_callback
Model card Files Community
Docty commited on
Commit
cc5cd6b
路
1 Parent(s): bb7f5aa

Training in progress epoch 1

Browse files
Files changed (2) hide show
  1. README.md +4 -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 [distilbert/distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert/distilbert-base-cased-distilled-squad) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Train Loss: 1.2112
20
- - Validation Loss: 0.6667
21
- - Epoch: 0
22
 
23
  ## Model description
24
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
45
  | Train Loss | Validation Loss | Epoch |
46
  |:----------:|:---------------:|:-----:|
47
  | 1.2112 | 0.6667 | 0 |
 
48
 
49
 
50
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [distilbert/distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert/distilbert-base-cased-distilled-squad) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Train Loss: 0.5043
20
+ - Validation Loss: 0.6306
21
+ - Epoch: 1
22
 
23
  ## Model description
24
 
 
45
  | Train Loss | Validation Loss | Epoch |
46
  |:----------:|:---------------:|:-----:|
47
  | 1.2112 | 0.6667 | 0 |
48
+ | 0.5043 | 0.6306 | 1 |
49
 
50
 
51
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6147928cca2fe6ea517fcea620e9129b9837bb2f7516a7f452f0ed54c58892ba
3
  size 260895720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e28afe23658cb018f3507106a07f29025ace312df02a44059a4162eed29847f
3
  size 260895720