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
5962e38
•
1 Parent(s): ebd3445

Training in progress epoch 135

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: 0.8999
18
- - Train Accuracy: 0.1170
19
- - Validation Loss: 0.8979
20
- - Validation Accuracy: 0.1181
21
- - Epoch: 134
22
 
23
  ## Model description
24
 
@@ -179,6 +179,7 @@ The following hyperparameters were used during training:
179
  | 0.9035 | 0.1170 | 0.8989 | 0.1180 | 132 |
180
  | 0.9023 | 0.1170 | 0.8965 | 0.1179 | 133 |
181
  | 0.8999 | 0.1170 | 0.8979 | 0.1181 | 134 |
 
182
 
183
 
184
  ### 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: 0.8981
18
+ - Train Accuracy: 0.1171
19
+ - Validation Loss: 0.8799
20
+ - Validation Accuracy: 0.1186
21
+ - Epoch: 135
22
 
23
  ## Model description
24
 
 
179
  | 0.9035 | 0.1170 | 0.8989 | 0.1180 | 132 |
180
  | 0.9023 | 0.1170 | 0.8965 | 0.1179 | 133 |
181
  | 0.8999 | 0.1170 | 0.8979 | 0.1181 | 134 |
182
+ | 0.8981 | 0.1171 | 0.8799 | 0.1186 | 135 |
183
 
184
 
185
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c524ec2539566fd6512297bc1a97dcf24afc9529033315181ff8b5109484096
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:886cc55236ebc1e3b9d31756070f53b04fc0da278a53e6242a64f640a3ddcc35
3
  size 499741936