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
e83441e
·
1 Parent(s): bf464b2

Training in progress epoch 350

Browse files
Files changed (2) hide show
  1. README.md +5 -4
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
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: 0.7460
18
- - Train Accuracy: 0.1211
19
- - Validation Loss: 0.7964
20
- - Validation Accuracy: 0.1208
21
- - Epoch: 349
22
 
23
  ## Model description
24
 
@@ -394,6 +394,7 @@ The following hyperparameters were used during training:
394
  | 0.7473 | 0.1210 | 0.8140 | 0.1201 | 347 |
395
  | 0.7468 | 0.1210 | 0.8066 | 0.1201 | 348 |
396
  | 0.7460 | 0.1211 | 0.7964 | 0.1208 | 349 |
 
397
 
398
 
399
  ### Framework versions
 
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: 0.7460
18
+ - Train Accuracy: 0.1210
19
+ - Validation Loss: 0.8184
20
+ - Validation Accuracy: 0.1206
21
+ - Epoch: 350
22
 
23
  ## Model description
24
 
 
394
  | 0.7473 | 0.1210 | 0.8140 | 0.1201 | 347 |
395
  | 0.7468 | 0.1210 | 0.8066 | 0.1201 | 348 |
396
  | 0.7460 | 0.1211 | 0.7964 | 0.1208 | 349 |
397
+ | 0.7460 | 0.1210 | 0.8184 | 0.1206 | 350 |
398
 
399
 
400
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcffb751e4fc366a727c0c93fa43dc6d79375fca7d6844cc25eda91a51397121
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ac386cf578c691758b88b9a0a87ad08ba8496130ce0b90f3676c9eef351099
3
  size 499741936