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
75a6d73
•
1 Parent(s): a4f8081

Training in progress epoch 238

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: 0.8005
18
  - Train Accuracy: 0.1196
19
- - Validation Loss: 0.8267
20
- - Validation Accuracy: 0.1196
21
- - Epoch: 237
22
 
23
  ## Model description
24
 
@@ -282,6 +282,7 @@ The following hyperparameters were used during training:
282
  | 0.8011 | 0.1196 | 0.8262 | 0.1201 | 235 |
283
  | 0.8006 | 0.1196 | 0.8252 | 0.1195 | 236 |
284
  | 0.8005 | 0.1196 | 0.8267 | 0.1196 | 237 |
 
285
 
286
 
287
  ### 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: 0.7989
18
  - Train Accuracy: 0.1196
19
+ - Validation Loss: 0.8389
20
+ - Validation Accuracy: 0.1199
21
+ - Epoch: 238
22
 
23
  ## Model description
24
 
 
282
  | 0.8011 | 0.1196 | 0.8262 | 0.1201 | 235 |
283
  | 0.8006 | 0.1196 | 0.8252 | 0.1195 | 236 |
284
  | 0.8005 | 0.1196 | 0.8267 | 0.1196 | 237 |
285
+ | 0.7989 | 0.1196 | 0.8389 | 0.1199 | 238 |
286
 
287
 
288
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ad4ca1fbbfb0312364049045b0674d5bc87e9d4072cf95cb592359d4b239941
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a20a64c465f6c862677db7a1f005aeae2f73974a84a7e61a0152990ed265b6
3
  size 499741936