Hugging Face's logo

jmassot
/
masked-lm-tpu

Fill-Mask
Transformers
TensorFlow
roberta
generated_from_keras_callback
Inference Endpoints
Model card Files Community
jmassot commited on
Commit
49b09a3
·
1 Parent(s): 2bfb22f

Training in progress epoch 9

Browse files
Files changed (2) hide show
  1. README.md +7 -5
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 9.9906
19
- - Train Accuracy: 0.0011
20
- - Validation Loss: 9.8881
21
- - Validation Accuracy: 0.0097
22
- - Epoch: 7
23
 
24
  ## Model description
25
 
@@ -53,6 +53,8 @@ The following hyperparameters were used during training:
53
  | 10.1135 | 0.0000 | 10.0415 | 0.0001 | 5 |
54
  | 10.0630 | 0.0001 | 9.9697 | 0.0013 | 6 |
55
  | 9.9906 | 0.0011 | 9.8881 | 0.0097 | 7 |
 
 
56
 
57
 
58
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 9.8173
19
+ - Train Accuracy: 0.0164
20
+ - Validation Loss: 9.6999
21
+ - Validation Accuracy: 0.0210
22
+ - Epoch: 9
23
 
24
  ## Model description
25
 
 
53
  | 10.1135 | 0.0000 | 10.0415 | 0.0001 | 5 |
54
  | 10.0630 | 0.0001 | 9.9697 | 0.0013 | 6 |
55
  | 9.9906 | 0.0011 | 9.8881 | 0.0097 | 7 |
56
+ | 9.9059 | 0.0070 | 9.7998 | 0.0183 | 8 |
57
+ | 9.8173 | 0.0164 | 9.6999 | 0.0210 | 9 |
58
 
59
 
60
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:481aa1743c06c9d5f93e89afd868eb65a9d052c85d2c4a88eaf6f156467fed18
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74194acfd8c194309e872eac6f4136c5c39ca03c30ab176617100a107e41f22
3
  size 499741936