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
3ca2291
•
1 Parent(s): c4fb21f

Training in progress epoch 163

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: 0.8633
18
- - Train Accuracy: 0.1181
19
- - Validation Loss: 0.8555
20
- - Validation Accuracy: 0.1185
21
- - Epoch: 162
22
 
23
  ## Model description
24
 
@@ -207,6 +207,7 @@ The following hyperparameters were used during training:
207
  | 0.8656 | 0.1180 | 0.8594 | 0.1188 | 160 |
208
  | 0.8649 | 0.1180 | 0.8535 | 0.1188 | 161 |
209
  | 0.8633 | 0.1181 | 0.8555 | 0.1185 | 162 |
 
210
 
211
 
212
  ### 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: 0.8622
18
+ - Train Accuracy: 0.1180
19
+ - Validation Loss: 0.8633
20
+ - Validation Accuracy: 0.1173
21
+ - Epoch: 163
22
 
23
  ## Model description
24
 
 
207
  | 0.8656 | 0.1180 | 0.8594 | 0.1188 | 160 |
208
  | 0.8649 | 0.1180 | 0.8535 | 0.1188 | 161 |
209
  | 0.8633 | 0.1181 | 0.8555 | 0.1185 | 162 |
210
+ | 0.8622 | 0.1180 | 0.8633 | 0.1173 | 163 |
211
 
212
 
213
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dad5ac6e5602c640a10ece3a9e9145e25e726fb967ce9bab4f0d7f28fb6b5fc
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b50705766b92fff7dde02c27b170e19f56f558f596731870839fc76b8a12b889
3
  size 499741936