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
2065c52
•
1 Parent(s): c15b342

Training in progress epoch 168

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: 0.8580
18
  - Train Accuracy: 0.1181
19
- - Validation Loss: 0.8853
20
- - Validation Accuracy: 0.1177
21
- - Epoch: 167
22
 
23
  ## Model description
24
 
@@ -212,6 +212,7 @@ The following hyperparameters were used during training:
212
  | 0.8598 | 0.1181 | 0.8813 | 0.1185 | 165 |
213
  | 0.8591 | 0.1181 | 0.8862 | 0.1176 | 166 |
214
  | 0.8580 | 0.1181 | 0.8853 | 0.1177 | 167 |
 
215
 
216
 
217
  ### 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: 0.8573
18
  - Train Accuracy: 0.1181
19
+ - Validation Loss: 0.8691
20
+ - Validation Accuracy: 0.1181
21
+ - Epoch: 168
22
 
23
  ## Model description
24
 
 
212
  | 0.8598 | 0.1181 | 0.8813 | 0.1185 | 165 |
213
  | 0.8591 | 0.1181 | 0.8862 | 0.1176 | 166 |
214
  | 0.8580 | 0.1181 | 0.8853 | 0.1177 | 167 |
215
+ | 0.8573 | 0.1181 | 0.8691 | 0.1181 | 168 |
216
 
217
 
218
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7cbf0f20e378da5e36d9eb30e95e1937224254be14c5d2dee2ad8eff2968eaa
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41cbbc23559d2b67e52593d8a1565053e0aa60d82306a0c762196b18ddc37d16
3
  size 499741936