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
be77c2a
•
1 Parent(s): 7111837

Training in progress epoch 296

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: 0.7690
18
- - Train Accuracy: 0.1204
19
- - Validation Loss: 0.8242
20
- - Validation Accuracy: 0.1204
21
- - Epoch: 295
22
 
23
  ## Model description
24
 
@@ -340,6 +340,7 @@ The following hyperparameters were used during training:
340
  | 0.7697 | 0.1204 | 0.8091 | 0.1210 | 293 |
341
  | 0.7686 | 0.1204 | 0.8154 | 0.1195 | 294 |
342
  | 0.7690 | 0.1204 | 0.8242 | 0.1204 | 295 |
 
343
 
344
 
345
  ### 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: 0.7679
18
+ - Train Accuracy: 0.1205
19
+ - Validation Loss: 0.7979
20
+ - Validation Accuracy: 0.1208
21
+ - Epoch: 296
22
 
23
  ## Model description
24
 
 
340
  | 0.7697 | 0.1204 | 0.8091 | 0.1210 | 293 |
341
  | 0.7686 | 0.1204 | 0.8154 | 0.1195 | 294 |
342
  | 0.7690 | 0.1204 | 0.8242 | 0.1204 | 295 |
343
+ | 0.7679 | 0.1205 | 0.7979 | 0.1208 | 296 |
344
 
345
 
346
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b3568a9a0af6ae16299100e1868637f974a7188922c57a41e1c6e40034ccbeb
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68c7e9169a1188ff37dd7bdd3db616feecfb2a3b035a53887117f4e1595a97a7
3
  size 499741936