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
1545c89
•
1 Parent(s): 2a47519

Training in progress epoch 334

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: 0.7523
18
  - Train Accuracy: 0.1209
19
- - Validation Loss: 0.8110
20
- - Validation Accuracy: 0.1197
21
- - Epoch: 333
22
 
23
  ## Model description
24
 
@@ -378,6 +378,7 @@ The following hyperparameters were used during training:
378
  | 0.7536 | 0.1208 | 0.8013 | 0.1209 | 331 |
379
  | 0.7531 | 0.1209 | 0.8149 | 0.1197 | 332 |
380
  | 0.7523 | 0.1209 | 0.8110 | 0.1197 | 333 |
 
381
 
382
 
383
  ### 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: 0.7521
18
  - Train Accuracy: 0.1209
19
+ - Validation Loss: 0.7998
20
+ - Validation Accuracy: 0.1208
21
+ - Epoch: 334
22
 
23
  ## Model description
24
 
 
378
  | 0.7536 | 0.1208 | 0.8013 | 0.1209 | 331 |
379
  | 0.7531 | 0.1209 | 0.8149 | 0.1197 | 332 |
380
  | 0.7523 | 0.1209 | 0.8110 | 0.1197 | 333 |
381
+ | 0.7521 | 0.1209 | 0.7998 | 0.1208 | 334 |
382
 
383
 
384
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:427bfa040b3826a4ad1d4e70ef23ef7194187367d4b9375dc49a08c4340192db
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70012c52341277f1cb93b37021f32ac481413bbccf6ac30a975e5f1f9768635
3
  size 499741936