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
d954040
·
1 Parent(s): 127c9ce

Training in progress epoch 404

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: 0.7280
18
  - Train Accuracy: 0.1215
19
- - Validation Loss: 0.7896
20
- - Validation Accuracy: 0.1221
21
- - Epoch: 403
22
 
23
  ## Model description
24
 
@@ -448,6 +448,7 @@ The following hyperparameters were used during training:
448
  | 0.7290 | 0.1215 | 0.7983 | 0.1208 | 401 |
449
  | 0.7284 | 0.1215 | 0.7842 | 0.1219 | 402 |
450
  | 0.7280 | 0.1215 | 0.7896 | 0.1221 | 403 |
 
451
 
452
 
453
  ### 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: 0.7282
18
  - Train Accuracy: 0.1215
19
+ - Validation Loss: 0.7935
20
+ - Validation Accuracy: 0.1199
21
+ - Epoch: 404
22
 
23
  ## Model description
24
 
 
448
  | 0.7290 | 0.1215 | 0.7983 | 0.1208 | 401 |
449
  | 0.7284 | 0.1215 | 0.7842 | 0.1219 | 402 |
450
  | 0.7280 | 0.1215 | 0.7896 | 0.1221 | 403 |
451
+ | 0.7282 | 0.1215 | 0.7935 | 0.1199 | 404 |
452
 
453
 
454
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64d3f2c37808e45bc49bf004639251825fa0d4c8de25da70412f46cba98f37a0
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:209342f6c2f8c5add8c88ed781c5d99d75b9dc916d4d00278191aa8981a7efd3
3
  size 499741936