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
fe57908
•
1 Parent(s): a214d20

Training in progress epoch 157

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: 0.8705
18
  - Train Accuracy: 0.1178
19
- - Validation Loss: 0.8804
20
- - Validation Accuracy: 0.1179
21
- - Epoch: 156
22
 
23
  ## Model description
24
 
@@ -201,6 +201,7 @@ The following hyperparameters were used during training:
201
  | 0.8736 | 0.1177 | 0.8726 | 0.1184 | 154 |
202
  | 0.8716 | 0.1178 | 0.8647 | 0.1186 | 155 |
203
  | 0.8705 | 0.1178 | 0.8804 | 0.1179 | 156 |
 
204
 
205
 
206
  ### 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: 0.8695
18
  - Train Accuracy: 0.1178
19
+ - Validation Loss: 0.8652
20
+ - Validation Accuracy: 0.1190
21
+ - Epoch: 157
22
 
23
  ## Model description
24
 
 
201
  | 0.8736 | 0.1177 | 0.8726 | 0.1184 | 154 |
202
  | 0.8716 | 0.1178 | 0.8647 | 0.1186 | 155 |
203
  | 0.8705 | 0.1178 | 0.8804 | 0.1179 | 156 |
204
+ | 0.8695 | 0.1178 | 0.8652 | 0.1190 | 157 |
205
 
206
 
207
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f194aab9f0cb7a38b6c92fbedb1f269bad4ba312badc519c4bd75e34741852b3
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1192dbb9a090a130359f1e4c4ed7da18f9cb96e9e70b0a0d066abd77f19086e
3
  size 499741936