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
975137e
•
1 Parent(s): 7efe436

Training in progress epoch 142

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: 0.8898
18
  - Train Accuracy: 0.1173
19
- - Validation Loss: 0.8911
20
- - Validation Accuracy: 0.1177
21
- - Epoch: 141
22
 
23
  ## Model description
24
 
@@ -186,6 +186,7 @@ The following hyperparameters were used during training:
186
  | 0.8929 | 0.1172 | 0.8804 | 0.1180 | 139 |
187
  | 0.8915 | 0.1173 | 0.8848 | 0.1183 | 140 |
188
  | 0.8898 | 0.1173 | 0.8911 | 0.1177 | 141 |
 
189
 
190
 
191
  ### 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: 0.8894
18
  - Train Accuracy: 0.1173
19
+ - Validation Loss: 0.9033
20
+ - Validation Accuracy: 0.1173
21
+ - Epoch: 142
22
 
23
  ## Model description
24
 
 
186
  | 0.8929 | 0.1172 | 0.8804 | 0.1180 | 139 |
187
  | 0.8915 | 0.1173 | 0.8848 | 0.1183 | 140 |
188
  | 0.8898 | 0.1173 | 0.8911 | 0.1177 | 141 |
189
+ | 0.8894 | 0.1173 | 0.9033 | 0.1173 | 142 |
190
 
191
 
192
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae856f55901b6e66fbde4b706a8572cdc62b56f9c526628a9a6a2a5c007ce79d
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ee609d665fed52c544ac61284a7b8d9cf2bc74e928a300af006c753fc8a6b2
3
  size 499741936