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
3185af1
•
1 Parent(s): 46ec587

Training in progress epoch 416

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: 0.7246
18
  - Train Accuracy: 0.1216
19
- - Validation Loss: 0.7861
20
- - Validation Accuracy: 0.1214
21
- - Epoch: 415
22
 
23
  ## Model description
24
 
@@ -460,6 +460,7 @@ The following hyperparameters were used during training:
460
  | 0.7256 | 0.1215 | 0.8066 | 0.1200 | 413 |
461
  | 0.7246 | 0.1216 | 0.7749 | 0.1213 | 414 |
462
  | 0.7246 | 0.1216 | 0.7861 | 0.1214 | 415 |
 
463
 
464
 
465
  ### 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: 0.7238
18
  - Train Accuracy: 0.1216
19
+ - Validation Loss: 0.8101
20
+ - Validation Accuracy: 0.1204
21
+ - Epoch: 416
22
 
23
  ## Model description
24
 
 
460
  | 0.7256 | 0.1215 | 0.8066 | 0.1200 | 413 |
461
  | 0.7246 | 0.1216 | 0.7749 | 0.1213 | 414 |
462
  | 0.7246 | 0.1216 | 0.7861 | 0.1214 | 415 |
463
+ | 0.7238 | 0.1216 | 0.8101 | 0.1204 | 416 |
464
 
465
 
466
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf71ecaa93ee6cbebe99fa9a8f5985ae57bff38d648d15f1a2b9ec576276fcc9
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea3c38755ddc09b2b6ef96c8f9e324f391cc7e82de6ad06619651de4e6c5e91f
3
  size 499741936