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
e863158
•
1 Parent(s): 99a0002

Training in progress epoch 491

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: 0.7083
18
  - Train Accuracy: 0.1221
19
- - Validation Loss: 0.7905
20
- - Validation Accuracy: 0.1205
21
- - Epoch: 490
22
 
23
  ## Model description
24
 
@@ -535,6 +535,7 @@ The following hyperparameters were used during training:
535
  | 0.7079 | 0.1221 | 0.7876 | 0.1206 | 488 |
536
  | 0.7082 | 0.1221 | 0.7778 | 0.1210 | 489 |
537
  | 0.7083 | 0.1221 | 0.7905 | 0.1205 | 490 |
 
538
 
539
 
540
  ### 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: 0.7084
18
  - Train Accuracy: 0.1221
19
+ - Validation Loss: 0.7842
20
+ - Validation Accuracy: 0.1212
21
+ - Epoch: 491
22
 
23
  ## Model description
24
 
 
535
  | 0.7079 | 0.1221 | 0.7876 | 0.1206 | 488 |
536
  | 0.7082 | 0.1221 | 0.7778 | 0.1210 | 489 |
537
  | 0.7083 | 0.1221 | 0.7905 | 0.1205 | 490 |
538
+ | 0.7084 | 0.1221 | 0.7842 | 0.1212 | 491 |
539
 
540
 
541
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b55e00e04e5bc288e3bbc74e67b5d0c49e63d65bc1a82f8b7355c84f6c2b915b
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60ab22e431dc44fa6221e70b09cd9736244264d6bbad358c1da1f9bd181e75e9
3
  size 499741936