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
94ae0fd
·
1 Parent(s): 7dc78f5

Training in progress epoch 166

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: 0.8598
18
  - Train Accuracy: 0.1181
19
- - Validation Loss: 0.8813
20
- - Validation Accuracy: 0.1185
21
- - Epoch: 165
22
 
23
  ## Model description
24
 
@@ -210,6 +210,7 @@ The following hyperparameters were used during training:
210
  | 0.8622 | 0.1180 | 0.8633 | 0.1173 | 163 |
211
  | 0.8603 | 0.1181 | 0.8667 | 0.1177 | 164 |
212
  | 0.8598 | 0.1181 | 0.8813 | 0.1185 | 165 |
 
213
 
214
 
215
  ### 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: 0.8591
18
  - Train Accuracy: 0.1181
19
+ - Validation Loss: 0.8862
20
+ - Validation Accuracy: 0.1176
21
+ - Epoch: 166
22
 
23
  ## Model description
24
 
 
210
  | 0.8622 | 0.1180 | 0.8633 | 0.1173 | 163 |
211
  | 0.8603 | 0.1181 | 0.8667 | 0.1177 | 164 |
212
  | 0.8598 | 0.1181 | 0.8813 | 0.1185 | 165 |
213
+ | 0.8591 | 0.1181 | 0.8862 | 0.1176 | 166 |
214
 
215
 
216
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b27bdb72b8e7f73557f1da887ca6dc9f467da2cc06e07c65da8cd544ffab276
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c559a700c66c91a32ade8c32d240a2543ea6afab4bca795bc5364632e7b09b7
3
  size 499741936