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
87ce5af
•
1 Parent(s): 94ea9f1

Training in progress epoch 497

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: 0.7079
18
  - Train Accuracy: 0.1221
19
- - Validation Loss: 0.7900
20
- - Validation Accuracy: 0.1211
21
- - Epoch: 496
22
 
23
  ## Model description
24
 
@@ -541,6 +541,7 @@ The following hyperparameters were used during training:
541
  | 0.7075 | 0.1221 | 0.7764 | 0.1201 | 494 |
542
  | 0.7078 | 0.1220 | 0.7842 | 0.1216 | 495 |
543
  | 0.7079 | 0.1221 | 0.7900 | 0.1211 | 496 |
 
544
 
545
 
546
  ### 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: 0.7085
18
  - Train Accuracy: 0.1221
19
+ - Validation Loss: 0.7744
20
+ - Validation Accuracy: 0.1212
21
+ - Epoch: 497
22
 
23
  ## Model description
24
 
 
541
  | 0.7075 | 0.1221 | 0.7764 | 0.1201 | 494 |
542
  | 0.7078 | 0.1220 | 0.7842 | 0.1216 | 495 |
543
  | 0.7079 | 0.1221 | 0.7900 | 0.1211 | 496 |
544
+ | 0.7085 | 0.1221 | 0.7744 | 0.1212 | 497 |
545
 
546
 
547
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d386f5a88403e20150762701fd4d89a5e0d536c748cf3cca3f8af75aff291810
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ec10b0429679944efd4935abe3cd65a06f435b0b2b192fb4c4f2135e263c95
3
  size 499741936