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
8e4fb3c
•
1 Parent(s): a24b50b

Training in progress epoch 419

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: 0.7243
18
  - Train Accuracy: 0.1216
19
- - Validation Loss: 0.7896
20
- - Validation Accuracy: 0.1219
21
- - Epoch: 418
22
 
23
  ## Model description
24
 
@@ -463,6 +463,7 @@ The following hyperparameters were used during training:
463
  | 0.7238 | 0.1216 | 0.8101 | 0.1204 | 416 |
464
  | 0.7244 | 0.1216 | 0.7939 | 0.1213 | 417 |
465
  | 0.7243 | 0.1216 | 0.7896 | 0.1219 | 418 |
 
466
 
467
 
468
  ### 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: 0.7233
18
  - Train Accuracy: 0.1216
19
+ - Validation Loss: 0.7891
20
+ - Validation Accuracy: 0.1216
21
+ - Epoch: 419
22
 
23
  ## Model description
24
 
 
463
  | 0.7238 | 0.1216 | 0.8101 | 0.1204 | 416 |
464
  | 0.7244 | 0.1216 | 0.7939 | 0.1213 | 417 |
465
  | 0.7243 | 0.1216 | 0.7896 | 0.1219 | 418 |
466
+ | 0.7233 | 0.1216 | 0.7891 | 0.1216 | 419 |
467
 
468
 
469
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9ef9c58a703413db7ce0f399b96fc7f3c968365db312f3da1d46b20994f13ff
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a531b47982abe5759ddcdbe71db459b9f0d08226b53bf94fd8bff70bc914e7
3
  size 499741936