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
c4a0a41
•
1 Parent(s): 669f4ba

Training in progress epoch 246

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  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: 0.7951
18
- - Train Accuracy: 0.1197
19
- - Validation Loss: 0.8320
20
- - Validation Accuracy: 0.1187
21
- - Epoch: 245
22
 
23
  ## Model description
24
 
@@ -290,6 +290,7 @@ The following hyperparameters were used during training:
290
  | 0.7954 | 0.1197 | 0.8242 | 0.1189 | 243 |
291
  | 0.7962 | 0.1197 | 0.8291 | 0.1197 | 244 |
292
  | 0.7951 | 0.1197 | 0.8320 | 0.1187 | 245 |
 
293
 
294
 
295
  ### 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: 0.7944
18
+ - Train Accuracy: 0.1198
19
+ - Validation Loss: 0.8389
20
+ - Validation Accuracy: 0.1184
21
+ - Epoch: 246
22
 
23
  ## Model description
24
 
 
290
  | 0.7954 | 0.1197 | 0.8242 | 0.1189 | 243 |
291
  | 0.7962 | 0.1197 | 0.8291 | 0.1197 | 244 |
292
  | 0.7951 | 0.1197 | 0.8320 | 0.1187 | 245 |
293
+ | 0.7944 | 0.1198 | 0.8389 | 0.1184 | 246 |
294
 
295
 
296
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b6615737baae42ab1f6614cce64c41371fb47dbb109768c021e146bdf08d753
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc529b5a225364a1cb6f2796a15550fab4b1d49f2ddbdd747fa6425f058a566
3
  size 499741936