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
e3b30ac
•
1 Parent(s): 11e13a3

Training in progress epoch 181

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: 0.8451
18
  - Train Accuracy: 0.1185
19
- - Validation Loss: 0.8672
20
- - Validation Accuracy: 0.1178
21
- - Epoch: 180
22
 
23
  ## Model description
24
 
@@ -225,6 +225,7 @@ The following hyperparameters were used during training:
225
  | 0.8466 | 0.1184 | 0.8608 | 0.1187 | 178 |
226
  | 0.8456 | 0.1184 | 0.8472 | 0.1186 | 179 |
227
  | 0.8451 | 0.1185 | 0.8672 | 0.1178 | 180 |
 
228
 
229
 
230
  ### 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: 0.8429
18
  - Train Accuracy: 0.1185
19
+ - Validation Loss: 0.8364
20
+ - Validation Accuracy: 0.1196
21
+ - Epoch: 181
22
 
23
  ## Model description
24
 
 
225
  | 0.8466 | 0.1184 | 0.8608 | 0.1187 | 178 |
226
  | 0.8456 | 0.1184 | 0.8472 | 0.1186 | 179 |
227
  | 0.8451 | 0.1185 | 0.8672 | 0.1178 | 180 |
228
+ | 0.8429 | 0.1185 | 0.8364 | 0.1196 | 181 |
229
 
230
 
231
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9f4666ecfe7f4ce6d1ca39054e5e1c874ef369a4ee77d1b89753910d57968f1
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7bf2846cb61234e792e0d6630c08224313047c5a2e1d69a0ee29b4fd762901f
3
  size 499741936