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
a6a6c50
•
1 Parent(s): 8a56929

Training in progress epoch 397

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: 0.7302
18
- - Train Accuracy: 0.1215
19
- - Validation Loss: 0.8008
20
- - Validation Accuracy: 0.1202
21
- - Epoch: 396
22
 
23
  ## Model description
24
 
@@ -441,6 +441,7 @@ The following hyperparameters were used during training:
441
  | 0.7310 | 0.1215 | 0.7993 | 0.1207 | 394 |
442
  | 0.7300 | 0.1214 | 0.8057 | 0.1208 | 395 |
443
  | 0.7302 | 0.1215 | 0.8008 | 0.1202 | 396 |
 
444
 
445
 
446
  ### 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: 0.7306
18
+ - Train Accuracy: 0.1214
19
+ - Validation Loss: 0.7817
20
+ - Validation Accuracy: 0.1212
21
+ - Epoch: 397
22
 
23
  ## Model description
24
 
 
441
  | 0.7310 | 0.1215 | 0.7993 | 0.1207 | 394 |
442
  | 0.7300 | 0.1214 | 0.8057 | 0.1208 | 395 |
443
  | 0.7302 | 0.1215 | 0.8008 | 0.1202 | 396 |
444
+ | 0.7306 | 0.1214 | 0.7817 | 0.1212 | 397 |
445
 
446
 
447
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b53e4297131c1509abf4f205af7e47c578071546c6e8d1f38ed9fa6dcdd000ff
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c717813dd9d59fd2d3ce082b641a67654f22202b3c66acd00c6a1365b497dc00
3
  size 499741936