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
b437ee2
•
1 Parent(s): e213a21

Training in progress epoch 28

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  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: 3.1689
18
- - Train Accuracy: 0.0693
19
- - Validation Loss: 2.4375
20
- - Validation Accuracy: 0.0835
21
- - Epoch: 27
22
 
23
  ## Model description
24
 
@@ -72,6 +72,7 @@ The following hyperparameters were used during training:
72
  | 4.5898 | 0.0449 | 4.4688 | 0.0452 | 25 |
73
  | 4.3024 | 0.0472 | 3.8730 | 0.0551 | 26 |
74
  | 3.1689 | 0.0693 | 2.4375 | 0.0835 | 27 |
 
75
 
76
 
77
  ### 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: 2.3780
18
+ - Train Accuracy: 0.0844
19
+ - Validation Loss: 2.0498
20
+ - Validation Accuracy: 0.0922
21
+ - Epoch: 28
22
 
23
  ## Model description
24
 
 
72
  | 4.5898 | 0.0449 | 4.4688 | 0.0452 | 25 |
73
  | 4.3024 | 0.0472 | 3.8730 | 0.0551 | 26 |
74
  | 3.1689 | 0.0693 | 2.4375 | 0.0835 | 27 |
75
+ | 2.3780 | 0.0844 | 2.0498 | 0.0922 | 28 |
76
 
77
 
78
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8efbebf74701d57ba0132c9a86386824e0404d2c6c8782c84b14649ce09c567b
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac5a757e77a35ba6c5504e47a61bf35a90345cfd0fd418afbefee960cd37604
3
  size 499741936