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
ffbd818
•
1 Parent(s): 08b2874

Training in progress epoch 298

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: 0.7680
18
  - Train Accuracy: 0.1205
19
- - Validation Loss: 0.8105
20
- - Validation Accuracy: 0.1194
21
- - Epoch: 297
22
 
23
  ## Model description
24
 
@@ -342,6 +342,7 @@ The following hyperparameters were used during training:
342
  | 0.7690 | 0.1204 | 0.8242 | 0.1204 | 295 |
343
  | 0.7679 | 0.1205 | 0.7979 | 0.1208 | 296 |
344
  | 0.7680 | 0.1205 | 0.8105 | 0.1194 | 297 |
 
345
 
346
 
347
  ### 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: 0.7673
18
  - Train Accuracy: 0.1205
19
+ - Validation Loss: 0.8003
20
+ - Validation Accuracy: 0.1215
21
+ - Epoch: 298
22
 
23
  ## Model description
24
 
 
342
  | 0.7690 | 0.1204 | 0.8242 | 0.1204 | 295 |
343
  | 0.7679 | 0.1205 | 0.7979 | 0.1208 | 296 |
344
  | 0.7680 | 0.1205 | 0.8105 | 0.1194 | 297 |
345
+ | 0.7673 | 0.1205 | 0.8003 | 0.1215 | 298 |
346
 
347
 
348
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1c548b1c7474996177e6a8a4ea99a8b26bd7634f4ec080ffb8e9aa716c70324
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67cab66f81f46122dee0d0861129cd03006a73e46ef6a0adba6845d324f0d0ac
3
  size 499741936