Hugging Face's logo

tf-tpu
/
roberta-base-epochs-500-no-wd

Fill-Mask
Transformers
TensorFlow
roberta
generated_from_keras_callback
Inference Endpoints
Model card Files Community
2
sayakpaul HF staff commited on
Commit
829c5a8
·
1 Parent(s): 3fd7a64

Training in progress epoch 139

Browse files
Files changed (2) hide show
  1. README.md +5 -4
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.8948
18
  - Train Accuracy: 0.1172
19
- - Validation Loss: 0.9019
20
- - Validation Accuracy: 0.1172
21
- - Epoch: 138
22
 
23
  ## Model description
24
 
@@ -183,6 +183,7 @@ The following hyperparameters were used during training:
183
  | 0.8976 | 0.1171 | 0.8984 | 0.1174 | 136 |
184
  | 0.8957 | 0.1172 | 0.8857 | 0.1181 | 137 |
185
  | 0.8948 | 0.1172 | 0.9019 | 0.1172 | 138 |
 
186
 
187
 
188
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.8929
18
  - Train Accuracy: 0.1172
19
+ - Validation Loss: 0.8804
20
+ - Validation Accuracy: 0.1180
21
+ - Epoch: 139
22
 
23
  ## Model description
24
 
 
183
  | 0.8976 | 0.1171 | 0.8984 | 0.1174 | 136 |
184
  | 0.8957 | 0.1172 | 0.8857 | 0.1181 | 137 |
185
  | 0.8948 | 0.1172 | 0.9019 | 0.1172 | 138 |
186
+ | 0.8929 | 0.1172 | 0.8804 | 0.1180 | 139 |
187
 
188
 
189
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d9d3fdf3c5cdb69477688386fa5f5322034c93195d1bd8523d89f9ac6d24a4a
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6324ca593cfb6c5170c07e5d5219bd04a7fc6d07deeae959ab2f12c678af9a3
3
  size 499741936