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
c5b9d28
•
1 Parent(s): f463a2d

Training in progress epoch 114

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: 0.9379
18
  - Train Accuracy: 0.1161
19
- - Validation Loss: 0.9111
20
- - Validation Accuracy: 0.1175
21
- - Epoch: 113
22
 
23
  ## Model description
24
 
@@ -158,6 +158,7 @@ The following hyperparameters were used during training:
158
  | 0.9422 | 0.1160 | 0.9121 | 0.1167 | 111 |
159
  | 0.9412 | 0.1160 | 0.8970 | 0.1165 | 112 |
160
  | 0.9379 | 0.1161 | 0.9111 | 0.1175 | 113 |
 
161
 
162
 
163
  ### 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: 0.9362
18
  - Train Accuracy: 0.1161
19
+ - Validation Loss: 0.9048
20
+ - Validation Accuracy: 0.1176
21
+ - Epoch: 114
22
 
23
  ## Model description
24
 
 
158
  | 0.9422 | 0.1160 | 0.9121 | 0.1167 | 111 |
159
  | 0.9412 | 0.1160 | 0.8970 | 0.1165 | 112 |
160
  | 0.9379 | 0.1161 | 0.9111 | 0.1175 | 113 |
161
+ | 0.9362 | 0.1161 | 0.9048 | 0.1176 | 114 |
162
 
163
 
164
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86556cb3f4972656cfa1e153751582ba11cac47c403db99f2b99a10807cbfc0b
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f0ee3568bb63dcc0f27d39d6ab1d167b4484f928f8ceab2aef78cc900299d27
3
  size 499741936