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
73c26f2
·
1 Parent(s): 96c7c70

Training in progress epoch 173

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: 0.8522
18
  - Train Accuracy: 0.1183
19
- - Validation Loss: 0.8721
20
- - Validation Accuracy: 0.1190
21
- - Epoch: 172
22
 
23
  ## Model description
24
 
@@ -217,6 +217,7 @@ The following hyperparameters were used during training:
217
  | 0.8541 | 0.1182 | 0.8652 | 0.1187 | 170 |
218
  | 0.8541 | 0.1183 | 0.8477 | 0.1198 | 171 |
219
  | 0.8522 | 0.1183 | 0.8721 | 0.1190 | 172 |
 
220
 
221
 
222
  ### 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: 0.8516
18
  - Train Accuracy: 0.1183
19
+ - Validation Loss: 0.8965
20
+ - Validation Accuracy: 0.1173
21
+ - Epoch: 173
22
 
23
  ## Model description
24
 
 
217
  | 0.8541 | 0.1182 | 0.8652 | 0.1187 | 170 |
218
  | 0.8541 | 0.1183 | 0.8477 | 0.1198 | 171 |
219
  | 0.8522 | 0.1183 | 0.8721 | 0.1190 | 172 |
220
+ | 0.8516 | 0.1183 | 0.8965 | 0.1173 | 173 |
221
 
222
 
223
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ece6418227b185fd7aafed45c92d0c373417636850ef9000f3390804ca50173c
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b461265d971c7b3636c5836e603e3d60d588e7949bea55b3c72fae654abc8f
3
  size 499741936