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
a0597ba
•
1 Parent(s): bcfadde

Training in progress epoch 159

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: 0.8675
18
  - Train Accuracy: 0.1179
19
- - Validation Loss: 0.8804
20
- - Validation Accuracy: 0.1197
21
- - Epoch: 158
22
 
23
  ## Model description
24
 
@@ -203,6 +203,7 @@ The following hyperparameters were used during training:
203
  | 0.8705 | 0.1178 | 0.8804 | 0.1179 | 156 |
204
  | 0.8695 | 0.1178 | 0.8652 | 0.1190 | 157 |
205
  | 0.8675 | 0.1179 | 0.8804 | 0.1197 | 158 |
 
206
 
207
 
208
  ### 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: 0.8670
18
  - Train Accuracy: 0.1179
19
+ - Validation Loss: 0.8462
20
+ - Validation Accuracy: 0.1192
21
+ - Epoch: 159
22
 
23
  ## Model description
24
 
 
203
  | 0.8705 | 0.1178 | 0.8804 | 0.1179 | 156 |
204
  | 0.8695 | 0.1178 | 0.8652 | 0.1190 | 157 |
205
  | 0.8675 | 0.1179 | 0.8804 | 0.1197 | 158 |
206
+ | 0.8670 | 0.1179 | 0.8462 | 0.1192 | 159 |
207
 
208
 
209
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1110cc4e194085082061e5d7c791808dde267508bcf3e8375af9bf118ad5d70
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c16c9d9a5a4f9943181dd52afca75da72b4c5aa1d04cd0efef99041658816c7
3
  size 499741936