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
ec3b5d4
•
1 Parent(s): d954d0c

Training in progress epoch 467

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: 0.7127
18
  - Train Accuracy: 0.1219
19
- - Validation Loss: 0.8013
20
- - Validation Accuracy: 0.1207
21
- - Epoch: 466
22
 
23
  ## Model description
24
 
@@ -511,6 +511,7 @@ The following hyperparameters were used during training:
511
  | 0.7134 | 0.1219 | 0.7788 | 0.1219 | 464 |
512
  | 0.7125 | 0.1219 | 0.7759 | 0.1210 | 465 |
513
  | 0.7127 | 0.1219 | 0.8013 | 0.1207 | 466 |
 
514
 
515
 
516
  ### 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: 0.7129
18
  - Train Accuracy: 0.1219
19
+ - Validation Loss: 0.7812
20
+ - Validation Accuracy: 0.1214
21
+ - Epoch: 467
22
 
23
  ## Model description
24
 
 
511
  | 0.7134 | 0.1219 | 0.7788 | 0.1219 | 464 |
512
  | 0.7125 | 0.1219 | 0.7759 | 0.1210 | 465 |
513
  | 0.7127 | 0.1219 | 0.8013 | 0.1207 | 466 |
514
+ | 0.7129 | 0.1219 | 0.7812 | 0.1214 | 467 |
515
 
516
 
517
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0adf63aa238c988c40ff28aac9451eda64e0d800ce0d2ed78163f31c438af6ee
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fdae889650e3e44a4b38d5cac0278081c3b764912d1ef118cda77c234616be4
3
  size 499741936