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
9598240
•
1 Parent(s): ceffe07

Training in progress epoch 443

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: 0.7176
18
  - Train Accuracy: 0.1218
19
- - Validation Loss: 0.7764
20
- - Validation Accuracy: 0.1213
21
- - Epoch: 442
22
 
23
  ## Model description
24
 
@@ -487,6 +487,7 @@ The following hyperparameters were used during training:
487
  | 0.7177 | 0.1218 | 0.7744 | 0.1214 | 440 |
488
  | 0.7176 | 0.1218 | 0.7754 | 0.1209 | 441 |
489
  | 0.7176 | 0.1218 | 0.7764 | 0.1213 | 442 |
 
490
 
491
 
492
  ### 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: 0.7170
18
  - Train Accuracy: 0.1218
19
+ - Validation Loss: 0.7812
20
+ - Validation Accuracy: 0.1203
21
+ - Epoch: 443
22
 
23
  ## Model description
24
 
 
487
  | 0.7177 | 0.1218 | 0.7744 | 0.1214 | 440 |
488
  | 0.7176 | 0.1218 | 0.7754 | 0.1209 | 441 |
489
  | 0.7176 | 0.1218 | 0.7764 | 0.1213 | 442 |
490
+ | 0.7170 | 0.1218 | 0.7812 | 0.1203 | 443 |
491
 
492
 
493
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:facff0804f6eebb220236c5787697823c86db892e4cdb45ce587e64670275ed3
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ef44cd076c24679c42e3b12d18d2f35affd8767dd773c3833a821a3dbfb67f
3
  size 499741936