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
6655657
•
1 Parent(s): 3b16b08

Training in progress epoch 379

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: 0.7359
18
  - Train Accuracy: 0.1213
19
- - Validation Loss: 0.8105
20
- - Validation Accuracy: 0.1200
21
- - Epoch: 378
22
 
23
  ## Model description
24
 
@@ -423,6 +423,7 @@ The following hyperparameters were used during training:
423
  | 0.7366 | 0.1213 | 0.7842 | 0.1205 | 376 |
424
  | 0.7362 | 0.1213 | 0.7905 | 0.1205 | 377 |
425
  | 0.7359 | 0.1213 | 0.8105 | 0.1200 | 378 |
 
426
 
427
 
428
  ### 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: 0.7360
18
  - Train Accuracy: 0.1213
19
+ - Validation Loss: 0.8037
20
+ - Validation Accuracy: 0.1203
21
+ - Epoch: 379
22
 
23
  ## Model description
24
 
 
423
  | 0.7366 | 0.1213 | 0.7842 | 0.1205 | 376 |
424
  | 0.7362 | 0.1213 | 0.7905 | 0.1205 | 377 |
425
  | 0.7359 | 0.1213 | 0.8105 | 0.1200 | 378 |
426
+ | 0.7360 | 0.1213 | 0.8037 | 0.1203 | 379 |
427
 
428
 
429
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb643b147bc3ca0026573bf8d0f9f5c8ca7732dd026051211560401e5881aef4
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b4468ab3d730ab9ced5bb2cfd05252dde7064db30d2884af3829966dd454c7
3
  size 499741936