Hugging Face's logo

buddhilive
/
albert-finetuned-squad

Question Answering
Transformers
TensorFlow
albert
generated_from_keras_callback
Inference Endpoints
Model card Files Community
buddhilive commited on
Commit
f4a8b81
•
1 Parent(s): 8e8f351

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +4 -6
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.4981
19
- - Validation Loss: 0.9740
20
- - Epoch: 2
21
 
22
  ## Model description
23
 
@@ -43,9 +43,7 @@ The following hyperparameters were used during training:
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
- | 1.5351 | 1.0064 | 0 |
47
- | 0.6483 | 0.9740 | 1 |
48
- | 0.4981 | 0.9740 | 2 |
49
 
50
 
51
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 1.5688
19
+ - Validation Loss: 0.0
20
+ - Epoch: 0
21
 
22
  ## Model description
23
 
 
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
+ | 1.5688 | 0.0 | 0 |
 
 
47
 
48
 
49
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e1a4470e17b21982ecfde9c2526c24a6d8faf9e9d7caad3ae803b8a159c15ab
3
  size 44417688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab655ee4610e8c25f8b64ee8680333bc23ca9288d97eff280436c28e1e1f90f4
3
  size 44417688