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
f90d0ae
•
1 Parent(s): 19dcc8d

Training in progress epoch 240

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: 0.7989
18
- - Train Accuracy: 0.1196
19
- - Validation Loss: 0.8394
20
- - Validation Accuracy: 0.1185
21
- - Epoch: 239
22
 
23
  ## Model description
24
 
@@ -284,6 +284,7 @@ The following hyperparameters were used during training:
284
  | 0.8005 | 0.1196 | 0.8267 | 0.1196 | 237 |
285
  | 0.7989 | 0.1196 | 0.8389 | 0.1199 | 238 |
286
  | 0.7989 | 0.1196 | 0.8394 | 0.1185 | 239 |
 
287
 
288
 
289
  ### 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: 0.7983
18
+ - Train Accuracy: 0.1197
19
+ - Validation Loss: 0.8110
20
+ - Validation Accuracy: 0.1208
21
+ - Epoch: 240
22
 
23
  ## Model description
24
 
 
284
  | 0.8005 | 0.1196 | 0.8267 | 0.1196 | 237 |
285
  | 0.7989 | 0.1196 | 0.8389 | 0.1199 | 238 |
286
  | 0.7989 | 0.1196 | 0.8394 | 0.1185 | 239 |
287
+ | 0.7983 | 0.1197 | 0.8110 | 0.1208 | 240 |
288
 
289
 
290
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be0bb0f9ca2ccd4f90d55224055d98dbf4b5de42880f0ad8bcebe41dee22b538
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05f4a67aa39f36b9f767ee6daaee408cad3682a5dd59e7998bff25faa3b02fa9
3
  size 499741936