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
d8ceec1
•
1 Parent(s): 191b371

Training in progress epoch 147

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: 0.8838
18
  - Train Accuracy: 0.1175
19
- - Validation Loss: 0.8896
20
- - Validation Accuracy: 0.1177
21
- - Epoch: 146
22
 
23
  ## Model description
24
 
@@ -191,6 +191,7 @@ The following hyperparameters were used during training:
191
  | 0.8863 | 0.1174 | 0.8921 | 0.1184 | 144 |
192
  | 0.8848 | 0.1175 | 0.8848 | 0.1177 | 145 |
193
  | 0.8838 | 0.1175 | 0.8896 | 0.1177 | 146 |
 
194
 
195
 
196
  ### 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: 0.8822
18
  - Train Accuracy: 0.1175
19
+ - Validation Loss: 0.8945
20
+ - Validation Accuracy: 0.1181
21
+ - Epoch: 147
22
 
23
  ## Model description
24
 
 
191
  | 0.8863 | 0.1174 | 0.8921 | 0.1184 | 144 |
192
  | 0.8848 | 0.1175 | 0.8848 | 0.1177 | 145 |
193
  | 0.8838 | 0.1175 | 0.8896 | 0.1177 | 146 |
194
+ | 0.8822 | 0.1175 | 0.8945 | 0.1181 | 147 |
195
 
196
 
197
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32f386305d0964d698e8ab0f10b236db2ba6c3fa80f1a7583c1252b365496af5
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:275bddab45c792dc4f67d9476fada06d56bba0ecd69b0f727b9f4a512a3c1a7c
3
  size 499741936