Hugging Face's logo

node-py
/
my_awesome_eli5_clm-model

TensorFlow
bert
generated_from_keras_callback
Model card Files Community
node-py commited on
Commit
291212b
•
1 Parent(s): 65d8e26

Training in progress epoch 50

Browse files
Files changed (2) hide show
  1. README.md +4 -2
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,8 +14,8 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.7162
18
- - Epoch: 48
19
 
20
  ## Model description
21
 
@@ -90,6 +90,8 @@ The following hyperparameters were used during training:
90
  | 0.7966 | 46 |
91
  | 0.7552 | 47 |
92
  | 0.7162 | 48 |
 
 
93
 
94
 
95
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.6420
18
+ - Epoch: 50
19
 
20
  ## Model description
21
 
 
90
  | 0.7966 | 46 |
91
  | 0.7552 | 47 |
92
  | 0.7162 | 48 |
93
+ | 0.6754 | 49 |
94
+ | 0.6420 | 50 |
95
 
96
 
97
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59a77c7f69da7d210b9f665be2398a710e63c79c9b427980351c8a648218ba04
3
  size 475933304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28f4d871a9f9829988ca45149ca544881c93784e8b4926ae65a5d8689a529fc
3
  size 475933304