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
f480acf
•
1 Parent(s): c40b861

Training in progress epoch 193

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  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: 0.8334
18
- - Train Accuracy: 0.1187
19
- - Validation Loss: 0.8486
20
- - Validation Accuracy: 0.1187
21
- - Epoch: 192
22
 
23
  ## Model description
24
 
@@ -237,6 +237,7 @@ The following hyperparameters were used during training:
237
  | 0.8348 | 0.1187 | 0.8457 | 0.1196 | 190 |
238
  | 0.8354 | 0.1187 | 0.8286 | 0.1191 | 191 |
239
  | 0.8334 | 0.1187 | 0.8486 | 0.1187 | 192 |
 
240
 
241
 
242
  ### 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: 0.8325
18
+ - Train Accuracy: 0.1188
19
+ - Validation Loss: 0.8535
20
+ - Validation Accuracy: 0.1182
21
+ - Epoch: 193
22
 
23
  ## Model description
24
 
 
237
  | 0.8348 | 0.1187 | 0.8457 | 0.1196 | 190 |
238
  | 0.8354 | 0.1187 | 0.8286 | 0.1191 | 191 |
239
  | 0.8334 | 0.1187 | 0.8486 | 0.1187 | 192 |
240
+ | 0.8325 | 0.1188 | 0.8535 | 0.1182 | 193 |
241
 
242
 
243
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92a049f6e8445aa257c58756008fa8ad845016e0bd7a7762ca933911773dbcbc
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02ed7b401394e43cbee3739c45879c38218a9b806edea532f77129dd6e2e8d6e
3
  size 499741936