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
ee94e2f
•
1 Parent(s): 4c0054a

Training in progress epoch 253

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: 0.7902
18
  - Train Accuracy: 0.1199
19
- - Validation Loss: 0.8232
20
- - Validation Accuracy: 0.1192
21
- - Epoch: 252
22
 
23
  ## Model description
24
 
@@ -297,6 +297,7 @@ The following hyperparameters were used during training:
297
  | 0.7916 | 0.1199 | 0.8242 | 0.1202 | 250 |
298
  | 0.7913 | 0.1198 | 0.8223 | 0.1182 | 251 |
299
  | 0.7902 | 0.1199 | 0.8232 | 0.1192 | 252 |
 
300
 
301
 
302
  ### 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: 0.7915
18
  - Train Accuracy: 0.1199
19
+ - Validation Loss: 0.8159
20
+ - Validation Accuracy: 0.1206
21
+ - Epoch: 253
22
 
23
  ## Model description
24
 
 
297
  | 0.7916 | 0.1199 | 0.8242 | 0.1202 | 250 |
298
  | 0.7913 | 0.1198 | 0.8223 | 0.1182 | 251 |
299
  | 0.7902 | 0.1199 | 0.8232 | 0.1192 | 252 |
300
+ | 0.7915 | 0.1199 | 0.8159 | 0.1206 | 253 |
301
 
302
 
303
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d2ac1ea5b23658d91367464253c989dd560cc3e2ac401cf09b410d40778ad65
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd0dad779c837b0f9b90f7c7e0fbf31eb64b6b39c0ca77627a877f7e7d082ab
3
  size 499741936