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
5ace5c0
•
1 Parent(s): cc608da

Training in progress epoch 153

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: 0.8747
18
  - Train Accuracy: 0.1177
19
- - Validation Loss: 0.8730
20
- - Validation Accuracy: 0.1178
21
- - Epoch: 152
22
 
23
  ## Model description
24
 
@@ -197,6 +197,7 @@ The following hyperparameters were used during training:
197
  | 0.8780 | 0.1176 | 0.875 | 0.1178 | 150 |
198
  | 0.8756 | 0.1176 | 0.8862 | 0.1170 | 151 |
199
  | 0.8747 | 0.1177 | 0.8730 | 0.1178 | 152 |
 
200
 
201
 
202
  ### 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: 0.8737
18
  - Train Accuracy: 0.1177
19
+ - Validation Loss: 0.8696
20
+ - Validation Accuracy: 0.1195
21
+ - Epoch: 153
22
 
23
  ## Model description
24
 
 
197
  | 0.8780 | 0.1176 | 0.875 | 0.1178 | 150 |
198
  | 0.8756 | 0.1176 | 0.8862 | 0.1170 | 151 |
199
  | 0.8747 | 0.1177 | 0.8730 | 0.1178 | 152 |
200
+ | 0.8737 | 0.1177 | 0.8696 | 0.1195 | 153 |
201
 
202
 
203
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:438cf3c1bec9dbf9f4f2e5074c41123cb4dc1c0c994ed378ef2ccaef458b2673
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7d81ad34bb845c1f06f3212f7da420ed903bf99678034b8d091388526699c8
3
  size 499741936